To see the other types of publications on this topic, follow the link: Time series of satellite images.
Dissertations / Theses on the topic 'Time series of satellite images'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Time series of satellite images.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Vázquez, Navarro Margarita R. "Life cycle of contrails from a time series of geostationary satellite images." kostenfrei, 2009. http://edoc.ub.uni-muenchen.de/10913/.
Full text
2
Vazquez, Navarro Margarita R. "Life cycle of contrails from a time series of geostationary satellite images." Diss., lmu, 2009. http://nbn-resolving.de/urn:nbn:de:bvb:19-109135.
Full text
3
Kalinicheva, Ekaterina. "Unsupervised satellite image time series analysis using deep learning techniques." Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS335.
Full textAbstract:
Cette thèse présente un ensemble d'algorithmes non-supervisés pour l'analyse générique de séries temporelles d'images satellites (STIS). Nos algorithmes exploitent des méthodes de machine learning et, notamment, les réseaux de neurones afin de détecter les différentes entités spatio-temporelles et leurs changements éventuels dans le temps. Nous visons à identifier trois types de comportement temporel : les zones sans changements, les changements saisonniers, les changements non triviaux (changements permanents comme les constructions, la rotation des cultures agricoles, etc).Par conséquent, nous proposons deux frameworks : pour la détection et le clustering des changements non-triviaux et pour le clustering des changements saisonniers et des zones sans changements. Le premier framework est composé de deux étapes : la détection de changements bi-temporels et leur interprétation dans le contexte multi-temporel avec une approche basée graphes. La détection de changements bi-temporels est faite pour chaque couple d’images consécutives et basée sur la transformation des features avec les autoencodeurs (AEs). A l’étape suivante, les changements à différentes dates qui appartiennent à la même zone géographique forment les graphes d’évolution qui sont par la suite clusterisés avec un modèle AE de réseaux de neurones récurrents. Le deuxième framework présente le clustering basé objets de STIS. Premièrement, la STIS est encodée en image unique avec un AE convolutif 3D multi-vue. Dans un deuxième temps, nous faisons la segmentation en deux étapes en utilisant à la fois l’image encodée et la STIS. Finalement, les segments obtenus sont clusterisés avec leurs descripteurs encodésThis thesis presents a set of unsupervised algorithms for satellite image time series (SITS) analysis. Our methods exploit machine learning algorithms and, in particular, neural networks to detect different spatio-temporal entities and their eventual changes in the time.In our thesis, we aim to identify three different types of temporal behavior: no change areas, seasonal changes (vegetation and other phenomena that have seasonal recurrence) and non-trivial changes (permanent changes such as constructions or demolishment, crop rotation, etc). Therefore, we propose two frameworks: one for detection and clustering of non-trivial changes and another for clustering of “stable” areas (seasonal changes and no change areas). The first framework is composed of two steps which are bi-temporal change detection and the interpretation of detected changes in a multi-temporal context with graph-based approaches. The bi-temporal change detection is performed for each pair of consecutive images of the SITS and is based on feature translation with autoencoders (AEs). At the next step, the changes from different timestamps that belong to the same geographic area form evolution change graphs. The graphs are then clustered using a recurrent neural networks AE model to identify different types of change behavior. For the second framework, we propose an approach for object-based SITS clustering. First, we encode SITS with a multi-view 3D convolutional AE in a single image. Second, we perform a two steps SITS segmentation using the encoded SITS and original images. Finally, the obtained segments are clustered exploiting their encoded descriptors
4
Wegner, Maus Victor, Gilberto Camara, Marius Appel, and Edzer Pebesma. "dtwSat: Time-Weighted Dynamic Time Warping for Satellite Image Time Series Analysis in R." Foundation for Open Access Statistics, 2019. http://epub.wu.ac.at/6808/1/v88i05.pdf.
Full textAbstract:
The opening of large archives of satellite data such as LANDSAT, MODIS and the SENTINELs has given researchers unprecedented access to data, allowing them to better quantify and understand local and global land change. The need to analyze such large data sets has led to the development of automated and semi-automated methods for satellite image time series analysis. However, few of the proposed methods for remote sensing time series analysis are available as open source software. In this paper we present the R package dtwSat. This package provides an implementation of the time-weighted dynamic time warping method for land cover mapping using sequence of multi-band satellite images. Methods based on dynamic time warping are flexible to handle irregular sampling and out-of-phase time series, and they have achieved significant results in time series analysis. Package dtwSat is available from the Comprehensive R Archive Network (CRAN) and contributes to making methods for satellite time series analysis available to a larger audience. The package supports the full cycle of land cover classification using image time series, ranging from selecting temporal patterns to visualizing and assessing the results.
5
LI, YUANXUN. "SVM Object Based Classification Using Dense Satellite Imagery Time Series." Thesis, KTH, Geoinformatik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233340.
Full text
6
Sanchez, Eduardo Hugo. "Learning disentangled representations of satellite image time series in a weakly supervised manner." Thesis, Toulouse 3, 2021. http://www.theses.fr/2021TOU30032.
Full textAbstract:
Cette thèse se focalise sur l'apprentissage de représentations de séries temporelles d'images satellites via des méthodes d'apprentissage non supervisé. Le but principal est de créer une représentation qui capture l'information la plus pertinente de la série temporelle afin d'effectuer d'autres applications d'imagerie satellite. Cependant, l'extraction d'information à partir de la donnée satellite implique de nombreux défis. D'un côté, les modèles doivent traiter d'énormes volumes d'images fournis par les satellites. D'un autre côté, il est impossible pour les opérateurs humains d'étiqueter manuellement un tel volume d'images pour chaque tâche (par exemple, la classification, la segmentation, la détection de changement, etc.). Par conséquent, les méthodes d'apprentissage supervisé qui ont besoin des étiquettes ne peuvent pas être appliquées pour analyser la donnée satellite. Pour résoudre ce problème, des algorithmes d'apprentissage non supervisé ont été proposés pour apprendre la structure de la donnée au lieu d'apprendre une tâche particulière. L'apprentissage non supervisé est une approche puissante, car aucune étiquette n'est nécessaire et la connaissance acquise sur la donnée peut être transférée vers d'autres tâches permettant un apprentissage plus rapide avec moins d'étiquettes. Dans ce travail, on étudie le problème de l'apprentissage de représentations démêlées de séries temporelles d'images satellites. Le but consiste à créer une représentation partagée qui capture l'information spatiale de la série temporelle et une représentation exclusive qui capture l'information temporelle spécifique à chaque image. On présente les avantages de créer des représentations spatio-temporelles. Par exemple, l'information spatiale est utile pour effectuer la classification ou la segmentation d'images de manière invariante dans le temps tandis que l'information temporelle est utile pour la détection de changement. Pour ce faire, on analyse plusieurs modèles d'apprentissage non supervisé tels que l'auto-encodeur variationnel (VAE) et les réseaux antagonistes génératifs (GANs) ainsi que les extensions de ces modèles pour effectuer le démêlage des représentations. Considérant les résultats impressionnants qui ont été obtenus par les modèles génératifs et reconstructifs, on propose un nouveau modèle qui crée une représentation spatiale et une représentation temporelle de la donnée satellite. On montre que les représentations démêlées peuvent être utilisées pour effectuer plusieurs tâches de vision par ordinateur surpassant d'autres modèles de l'état de l'art. Cependant, nos expériences suggèrent que les modèles génératifs et reconstructifs présentent des inconvénients liés à la dimensionnalité de la représentation, à la complexité de l'architecture et au manque de garanties sur le démêlage. Pour surmonter ces limitations, on étudie une méthode récente basée sur l'estimation et la maximisation de l'informations mutuelle sans compter sur la reconstruction ou la génération d'image. On propose un nouveau modèle qui étend le principe de maximisation de l'information mutuelle pour démêler le domaine de représentation. En plus des expériences réalisées sur la donnée satellite, on montre que notre modèle est capable de traiter différents types de données en étant plus performant que les méthodes basées sur les GANs et les VAEs. De plus, on prouve que notre modèle demande moins de puissance de calcul et pourtant est plus efficace. Enfin, on montre que notre modèle est utile pour créer une représentation qui capture uniquement l'information de classe entre deux images appartenant à la même catégorie. Démêler la classe ou la catégorie d'une image des autres facteurs de variation permet de calculer la similarité entre pixels et effectuer la segmentation d'image d'une manière faiblement superviséeThis work focuses on learning data representations of satellite image time series via an unsupervised learning approach. The main goal is to enforce the data representation to capture the relevant information from the time series to perform other applications of satellite imagery. However, extracting information from satellite data involves many challenges since models need to deal with massive amounts of images provided by Earth observation satellites. Additionally, it is impossible for human operators to label such amount of images manually for each individual task (e.g. classification, segmentation, change detection, etc.). Therefore, we cannot use the supervised learning framework which achieves state-of-the-art results in many tasks.To address this problem, unsupervised learning algorithms have been proposed to learn the data structure instead of performing a specific task. Unsupervised learning is a powerful approach since no labels are required during training and the knowledge acquired can be transferred to other tasks enabling faster learning with few labels.In this work, we investigate the problem of learning disentangled representations of satellite image time series where a shared representation captures the spatial information across the images of the time series and an exclusive representation captures the temporal information which is specific to each image. We present the benefits of disentangling the spatio-temporal information of time series, e.g. the spatial information is useful to perform time-invariant image classification or segmentation while the knowledge about the temporal information is useful for change detection. To accomplish this, we analyze some of the most prevalent unsupervised learning models such as the variational autoencoder (VAE) and the generative adversarial networks (GANs) as well as the extensions of these models to perform representation disentanglement. Encouraged by the successful results achieved by generative and reconstructive models, we propose a novel framework to learn spatio-temporal representations of satellite data. We prove that the learned disentangled representations can be used to perform several computer vision tasks such as classification, segmentation, information retrieval and change detection outperforming other state-of-the-art models. Nevertheless, our experiments suggest that generative and reconstructive models present some drawbacks related to the dimensionality of the data representation, architecture complexity and the lack of disentanglement guarantees. In order to overcome these limitations, we explore a recent method based on mutual information estimation and maximization for representation learning without relying on image reconstruction or image generation. We propose a new model that extends the mutual information maximization principle to disentangle the representation domain into two parts. In addition to the experiments performed on satellite data, we show that our model is able to deal with different kinds of datasets outperforming the state-of-the-art methods based on GANs and VAEs. Furthermore, we show that our mutual information based model is less computationally demanding yet more effective. Finally, we show that our model is useful to create a data representation that only captures the class information between two images belonging to the same category. Disentangling the class or category of an image from other factors of variation provides a powerful tool to compute the similarity between pixels and perform image segmentation in a weakly-supervised manner
7
Wang, Zhihao. "Land Cover Classification on Satellite Image Time Series Using Deep Learning Models." The Ohio State University, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu159559249009195.
Full text
8
Karasiak, Nicolas. "Cartographie des essences forestières à partir de séries temporelles d’images satellitaires à hautes résolutions : stabilité des prédictions, autocorrélation spatiale et cohérence avec la phénologie observée in situ." Thesis, Toulouse, INPT, 2020. http://www.theses.fr/2020INPT0115.
Full textAbstract:
La forêt a un rôle essentiel sur terre, que ce soit pour stocker le carbone et ainsi lutter contre le réchauffement climatique ou encore fournir un habitat à de nombreuses espèces. Or la composition de la forêt (la localisation des essences ou leur diversité) a une influence sur les services écologiques rendus. Dans ce contexte, il est important de cartographier les forêts et les essences qui la composent. La télédétection, en particulier à partir d’images satellitaires, apparat comme le moyen le plus adéquat pour caractériser un vaste territoire. Avec l’arrivée de constellations satellitaires comme Sentinel-2 ou Landsat-8 et leur gratuité d’acquisition pour l’utilisateur, il devient possible d’envisager l’usage de séries temporelles d’images satellites à haute résolution spatiale, spectrale et temporelle à l’aide d’algorithmes d’apprentissage automatique. Si de nombreux travaux ont étudié le potentiel des images satellitaires pour identifier les essences, rares sont ceux qui utilisent des séries temporelles (plusieurs images par an) avec une haute résolution spatiale et en tenant compte de l’autocorrélation spatiale des références, i.e. la ressemblance des échantillons spatialement proches les uns des autres. Or, en ne prenant pas en compte ce phénomène, des biais d’évaluation peuvent survenir et ainsi surestimer la qualité des modèles d’apprentissage. Il s’agit aussi de mieux cerner les verrous méthodologiques afin de comprendre pourquoi il peut être facile ou compliqué pour un algorithme d’identifier une essence d’une autre. L’objectif général de la thèse vise à étudier le potentiel et les verrous concernant la reconnaissance des essences forestières à partir des séries temporelles d’images satellite à haute résolution spatiale, spectrale, et temporelle. Le premier objectif consiste à étudier la stabilité temporelle des prédictions à partir d’une archive de neuf ans du satellite Formosat-2. Plus particulièrement, les travaux portent sur la mise en place d’une méthode de validation qui soit le plus fidèle à la qualité observée des cartographies. Le second objectif s’intéresse au lien entre les évènements phénologiques in situ (pousse des feuilles en début de saison, ou perte et coloration des feuilles en fin de saison) et ce qu’il est observable par télédétection. Outre la capacité de détecter ces évènements, il sera étudié si ce qui permet aux algorithmes de différencier les essences les unes des autres est lié à des comportements spécifiques par espèceForests have a key role on earth, whether to store carbon and so reducing the global warming or to provide a place for many species. However, the composition of the forest (the location of the tree species or their diversity) has an influence on the ecological services provided. In this context, it seems critical to map tree species that make it up the forest. Remote sensing, especially from satellite images, appears to be the most appropriate way to map large areas. Thanks to the satellite constellations such as Sentinel-2 or Landsat-8 and their free acquisition for the user, the use of time series of satellite images with high spatial, spectral and temporal resolution using automatic learning algorithms is now easy to access. While many works have studied the potential of satellite images to identify tree species, few use time series (several images per year) with high spatial resolution and taking into account the spatial autocorrelation of references, i.e. the spectral similarity of spatially close samples. However, by not taking this phenomenon into account, evaluation biases may occur and thus overestimate the quality of the learning models. It is also a question of better identifying the methodological barriers in order to understand why it can be easy or complicated for an algorithm to identify one species from another. The general objective of the thesis is to study the potential and the obstacles concerning the idenficiation of forest tree species from satellite images time series with high spatial, spectral and temporal resolution. The first objective is to study the temporal stability of predictions from a nine-year archive of the Formosat-2 satellite. More specifically, the work focuses on the implementation of a validation method that is as faithful as possible to the observed quality of the maps. The second objective focuses on the link between in situ phenological events (leaf growth at the beginning of the season, or leaf loss and coloration at the end of the season) and what can be observed by remote sensing. In addition to the ability to detect these events, it will be studied whether what allows the algorithms to identify tree species from each other is related to species-specific behaviors
9
Petitjean, François. "Dynamic time warping : apports théoriques pour l'analyse de données temporelles : application à la classification de séries temporelles d'images satellites." Thesis, Strasbourg, 2012. http://www.theses.fr/2012STRAD023.
Full textAbstract:
Les séries temporelles d’images satellites (STIS) sont des données cruciales pour l’observation de la terre. Les séries temporelles actuelles sont soit des séries à haute résolution temporelle (Spot-Végétation, MODIS), soit des séries à haute résolution spatiale (Landsat). Dans les années à venir, les séries temporelles d’images satellites à hautes résolutions spatiale et temporelle vont être produites par le programme Sentinel de l’ESA. Afin de traiter efficacement ces immenses quantités de données qui vont être produites (par exemple, Sentinel-2 couvrira la surface de la terre tous les cinq jours, avec des résolutions spatiales allant de 10m à 60m et disposera de 13 bandes spectrales), de nouvelles méthodes ont besoin d’être développées. Cette thèse se focalise sur la comparaison des profils d’évolution radiométrique, et plus précisément la mesure de similarité « Dynamic Time Warping », qui constitue un outil permettant d’exploiter la structuration temporelle des séries d’images satellitesSatellite Image Time Series are becoming increasingly available and will continue to do so in the coming years thanks to the launch of space missions, which aim at providing a coverage of the Earth every few days with high spatial resolution (ESA’s Sentinel program). In the case of optical imagery, it will be possible to produce land use and cover change maps with detailed nomenclatures. However, due to meteorological phenomena, such as clouds, these time series will become irregular in terms of temporal sampling. In order to consistently handle the huge amount of information that will be produced (for instance, Sentinel-2 will cover the entire Earth’s surface every five days, with 10m to 60m spatial resolution and 13 spectral bands), new methods have to be developed. This Ph.D. thesis focuses on the “Dynamic Time Warping” similarity measure, which is able to take the most of the temporal structure of the data, in order to provide an efficient and relevant analysis of the remotely observed phenomena
10
Shen, Meicheng. "Statistical Estimation of Vegetation Production in the Northern High Latitude Region based on Satellite Image Time Series." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu1563552594966495.
Full text
11
Lopes, Maïlys. "Ecological monitoring of semi-natural grasslands : statistical analysis of dense satellite image time series with high spatial resolution." Thesis, Toulouse, INPT, 2017. http://www.theses.fr/2017INPT0095/document.
Full textAbstract:
Les prairies représentent une source importante de biodiversité dans les paysages agricoles qu’il est important de surveiller. Les satellites de nouvelle génération tels que Sentinel-2 offrent de nouvelles opportunités pour le suivi des prairies grâce à leurs hautes résolutions spatiale et temporelle combinées. Cependant, le nouveau type de données fourni par ces satellites implique des problèmes liés au big data et à la grande dimension des données en raison du nombre croissant de pixels à traiter et du nombre élevé de variables spectro-temporelles. Cette thèse explore le potentiel des satellites de nouvelle génération pour le suivi de la biodiversité et des facteurs qui influencent la biodiversité dans les prairies semi-naturelles. Des outils adaptés à l’analyse statistique des prairies à partir de séries temporelles d’images satellites (STIS) denses à haute résolution spatiale sont proposés. Tout d’abord, nous montrons que la réponse spectrotemporelle des prairies est caractérisée par sa variabilité au sein des prairies et parmi les prairies. Puis, pour les analyses statistiques, les prairies sont modélisées à l’échelle de l’objet pour être cohérent avec les modèles écologiques qui représentent les prairies à l’échelle de la parcelle. Nous proposons de modéliser la distribution des pixels dans une prairie par une loi gaussienne. A partir de cette modélisation, des mesures de similarité entre deux lois gaussiennes robustes à la grande dimension sont développées pour la classification des prairies en utilisant des STIS denses: High-Dimensional Kullback-Leibler Divergence et -Gaussian Mean Kernel. Cette dernière est plus performante que les méthodes conventionnelles utilisées avec les machines à vecteur de support (SVM) pour la classification du mode de gestion et de l’âge des prairies. Enfin, des indicateurs de biodiversité des prairies issus de STIS denses sont proposés à travers des mesures d’hétérogénéité spectro-temporelle dérivées du clustering non supervisé des prairies. Leur corrélation avec l’indice de Shannon est significative mais faible. Les résultats suggèrent que les variations spectro-temporelles mesurées à partir de STIS à 10 mètres de résolution spatiale et qui couvrent la période où ont lieu les pratiques agricoles sont plus liées à l’intensité des pratiques qu’à la diversité en espèces. Ainsi, bien que les propriétés spatiales et temporelles de Sentinel-2 semblent limitées pour estimer directement la diversité en espèces des prairies, ce satellite devrait permettre le suivi continu des facteurs influençant la biodiversité dans les prairies. Dans cette thèse, nous avons proposé des méthodes qui prennent en compte l’hétérogénéité au sein des prairies et qui permettent l’utilisation de toute l’information spectrale et temporelle fournie par les satellites de nouvelle générationGrasslands are a significant source of biodiversity in farmed landscapes that is important to monitor. New generation satellites such as Sentinel-2 offer new opportunities for grassland’s monitoring thanks to their combined high spatial and temporal resolutions. Conversely, the new type of data provided by these sensors involves big data and high dimensional issues because of the increasing number of pixels to process and the large number of spectro-temporal variables. This thesis explores the potential of the new generation satellites to monitor biodiversity and factors that influence biodiversity in semi-natural grasslands. Tools suitable for the statistical analysis of grasslands using dense satellite image time series (SITS) with high spatial resolution are provided. First, we show that the spectro-temporal response of grasslands is characterized by its variability within and among the grasslands. Then, for the statistical analysis, grasslands are modeled at the object level to be consistent with ecological models that represent grasslands at the field scale. We propose to model the distribution of pixels in a grassland by a Gaussian distribution. Following this modeling, similarity measures between two Gaussian distributions robust to the high dimension are developed for the lassification of grasslands using dense SITS: the High-Dimensional Kullback-Leibler Divergence and the -Gaussian Mean Kernel. The latter outperforms conventional methods used with Support Vector Machines for the classification of grasslands according to their management practices and to their age. Finally, indicators of grassland biodiversity issued from dense SITS are proposed through spectro-temporal heterogeneity measures derived from the unsupervised clustering of grasslands. Their correlation with the Shannon index is significant but low. The results suggest that the spectro-temporal variations measured from SITS at a spatial resolution of 10 meters covering the period when the practices occur are more related to the intensity of management practices than to the species diversity. Therefore, although the spatial and spectral properties of Sentinel-2 seem limited to assess the species diversity in grasslands directly, this satellite should make possible the continuous monitoring of factors influencing biodiversity in grasslands. In this thesis, we provided methods that account for the heterogeneity within grasslands and enable the use of all the spectral and temporal information provided by new generation satellites
12
Carpentier, Benjamin. "Deep Learning for Earth Observation: improvement of classification methods for land cover mapping : Semantic segmentation of satellite image time series." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-299578.
Full textAbstract:
Satellite Image Time Series (SITS) are becoming available at high spatial, spectral and temporal resolutions across the globe by the latest remote sensing sensors. These series of images can be highly valuable when exploited by classification systems to produce frequently updated and accurate land cover maps. The richness of spectral, spatial and temporal features in SITS is a promising source of data for developing better classification algorithms. However, machine learning methods such as Random Forests (RFs), despite their fruitful application to SITS to produce land cover maps, are structurally unable to properly handle intertwined spatial, spectral and temporal dynamics without breaking the structure of the data. Therefore, the present work proposes a comparative study of various deep learning algorithms from the Convolutional Neural Network (CNN) family and evaluate their performance on SITS classification. They are compared to the processing chain coined iota2, developed by the CESBIO and based on a RF model. Experiments are carried out in an operational context using with sparse annotations from 290 labeled polygons. Less than 80 000 pixel time series belonging to 8 land cover classes from a year of Sentinel- 2 monthly syntheses are used. Results show on a test set of 131 polygons that CNNs using 3D convolutions in space and time are more accurate than 1D temporal, stacked 2D and RF approaches. Best-performing models are CNNs using spatio-temporal features, namely 3D-CNN, 2D-CNN and SpatioTempCNN, a two-stream model using both 1D and 3D convolutions.Tidsserier av satellitbilder (SITS) blir tillgängliga med hög rumslig, spektral och tidsmässig upplösning över hela världen med hjälp av de senaste fjärranalyssensorerna. Dessa bildserier kan vara mycket värdefulla när de utnyttjas av klassificeringssystem för att ta fram ofta uppdaterade och exakta kartor över marktäcken. Den stora mängden spektrala, rumsliga och tidsmässiga egenskaper i SITS är en lovande datakälla för utveckling av bättre algoritmer. Metoder för maskininlärning som Random Forests (RF), trots att de har tillämpats på SITS för att ta fram kartor över landtäckning, är strukturellt sett oförmögna att hantera den sammanflätade rumsliga, spektrala och temporala dynamiken utan att bryta sönder datastrukturen. I detta arbete föreslås därför en jämförande studie av olika algoritmer från Konvolutionellt Neuralt Nätverk (CNN) -familjen och en utvärdering av deras prestanda för SITS-klassificering. De jämförs med behandlingskedjan iota2, som utvecklats av CESBIO och bygger på en RF-modell. Försöken utförs i ett operativt sammanhang med glesa annotationer från 290 märkta polygoner. Mindre än 80 000 pixeltidsserier som tillhör 8 marktäckeklasser från ett års månatliga Sentinel-2-synteser används. Resultaten visar att CNNs som använder 3D-falsningar i tid och rum är mer exakta än 1D temporala, staplade 2D- och RF-metoder. Bäst presterande modeller är CNNs som använder spatiotemporala egenskaper, nämligen 3D-CNN, 2D-CNN och SpatioTempCNN, en modell med två flöden som använder både 1D- och 3D-falsningar.
13
Braget, Austin Ray. "Time series analysis of phenometrics and long-term vegetation trends for the Flint Hills ecoregion using moderate resolution satellite imagery." Thesis, Kansas State University, 2017. http://hdl.handle.net/2097/35553.
Full textAbstract:
Master of ArtsDepartment of Geography
J. M. Shawn Hutchinson
Grasslands of the Flint Hills are often burned as a land management practice. Remote sensing can be used to help better manage prairie landscapes by providing useful information about the long-term trends in grassland vegetation greenness and helping to quantify regional differences in vegetation development. Using MODIS 16-day NDVI composite imagery between the years 2001-10 for the entire Flint Hills ecoregion, BFAST was used to determine trend, seasonal, and noise components of the image time series. To explain the trend, 4 factors were considered including hydrologic soil group, burn frequency, and precipitation deviation from the 30 year normal. In addition, the time series data was processed using TIMESAT to extract eight different phenometrics: Growing season length, start of season, end of season, middle of season, maximum value, small integral, left derivative, and right derivative. Phenometrics were produced for each year of the study and an ANOVA was performed on the means of all eight phenometrics to assess if significant differences existed across the study area. A K-means cluster analysis was also performed by aggregating pixel-level phenometrics at the county level to identify administrative divisions exhibiting similar vegetation development. For the study period, the area of negatively and positively trending grassland were similar (41-43%). Logistic regression showed that the log odds of a pixel experiencing a negative trend were higher in sites with clay soils and higher burning frequencies and lower for pixels having higher than normal precipitation and loam soils. Significant differences existed for all phenometrics when considering the ecoregion as a whole. On a phenometric-by-phenometric basis, unexpected groupings of counties often showed statistically similar values. Similarly, when considering all phenometrics at the same time, counties clustered in surprising patterns. Results suggest that long-term trends in grassland conditions warrant further attention and may rival other sources of grassland change (e.g., conversion, transition to savannah) in importance. Analyses of phenometrics indicates that factors other than natural gradients in temperature and precipitation play a significant role in the annual cycle of grassland vegetation development. Unanticipated, and sometimes geographically disparate, groups of counties were shown to be similar in the context of specific phenology metrics and this may prove useful in future implementations of smoke management plans within the Flint Hills.
14
Barnie, Talfan Donald. "Estimating lava effusion rates from geostationary satellite thermal images : a novel time series analysis and linear inversion approach applied to the eruptions of Afar, Ethiopia, between 2007 and 2010." Thesis, University of Cambridge, 2015. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.708893.
Full text
15
Williams, Danielle M. "Time series analysis of vegetation dynamics and burn scar mapping at Smoky Hill Air National Guard Range, Kansas using moderate resolution satellite imagery." Thesis, Kansas State University, 2016. http://hdl.handle.net/2097/34462.
Full textAbstract:
Master of ArtsDepartment of Geography
J. M. Shawn Hutchinson
Military installations are important assets for the proper training of armed forces. To ensure the continued viability of training lands, management practices need to be implemented to sustain the necessary environmental conditions for safe and effective training. For this study two analyses were done, a contemporary burn history and a time series analysis. The study area is Smoky Hill Air National Guard Range (ANGR), an Impact Area (within the range) and a non-military Comparison Site. Landsat 5 TM / 7 ETM+ imagery was used to create an 11 year composite burn history image. NDVI values were derived from MODIS imagery for the time series analysis using the statistical package BFAST. Results from both studies were combined to make conclusions about training impacts at Smoky Hill ANGR and determine if BFAST is a viable environmental management tool. Based on this study the training within Smoky Hill ANGR does not seem to be having a negative effect on the overall vegetation condition. It was also discovered that BFAST was able to accurately detect known vegetation disturbances. BFAST is a viable environmental management tool if the limitations are understood.
16
Pelletier, Charlotte. "Cartographie de l'occupation des sols à partir de séries temporelles d'images satellitaires à hautes résolutions : identification et traitement des données mal étiquetées." Thesis, Toulouse 3, 2017. http://www.theses.fr/2017TOU30241/document.
Full textAbstract:
L'étude des surfaces continentales est devenue ces dernières années un enjeu majeur à l'échelle mondiale pour la gestion et le suivi des territoires, notamment en matière de consommation des terres agricoles et d'étalement urbain. Dans ce contexte, les cartes d'occupation du sol caractérisant la couverture biophysique des terres émergées jouent un rôle essentiel pour la cartographie des surfaces continentales. La production de ces cartes sur de grandes étendues s'appuie sur des données satellitaires qui permettent de photographier les surfaces continentales fréquemment et à faible coût. Le lancement de nouvelles constellations satellitaires - Landsat-8 et Sentinel-2 - permet depuis quelques années l'acquisition de séries temporelles à hautes résolutions. Ces dernières sont utilisées dans des processus de classification supervisée afin de produire les cartes d'occupation du sol. L'arrivée de ces nouvelles données ouvre de nouvelles perspectives, mais questionne sur le choix des algorithmes de classification et des données à fournir en entrée du système de classification. Outre les données satellitaires, les algorithmes de classification supervisée utilisent des échantillons d'apprentissage pour définir leur règle de décision. Dans notre cas, ces échantillons sont étiquetés, \ie{} la classe associée à une occupation des sols est connue. Ainsi, la qualité de la carte d'occupation des sols est directement liée à la qualité des étiquettes des échantillons d'apprentissage. Or, la classification sur de grandes étendues nécessite un grand nombre d'échantillons, qui caractérise la diversité des paysages. Cependant, la collecte de données de référence est une tâche longue et fastidieuse. Ainsi, les échantillons d'apprentissage sont bien souvent extraits d'anciennes bases de données pour obtenir un nombre conséquent d'échantillons sur l'ensemble de la surface à cartographier. Cependant, l'utilisation de ces anciennes données pour classer des images satellitaires plus récentes conduit à la présence de nombreuses données mal étiquetées parmi les échantillons d'apprentissage. Malheureusement, l'utilisation de ces échantillons mal étiquetés dans le processus de classification peut engendrer des erreurs de classification, et donc une détérioration de la qualité de la carte produite. L'objectif général de la thèse vise à améliorer la classification des nouvelles séries temporelles d'images satellitaires à hautes résolutions. Le premier objectif consiste à déterminer la stabilité et la robustesse des méthodes de classification sur de grandes étendues. Plus particulièrement, les travaux portent sur l'analyse d'algorithmes de classification et la sensibilité de ces algorithmes vis-à-vis de leurs paramètres et des données en entrée du système de classification. De plus, la robustesse de ces algorithmes à la présence des données imparfaites est étudiée. Le second objectif s'intéresse aux erreurs présentes dans les données d'apprentissage, connues sous le nom de données mal étiquetées. Dans un premier temps, des méthodes de détection de données mal étiquetées sont proposées et étudiées. Dans un second temps, un cadre méthodologique est proposé afin de prendre en compte les données mal étiquetées dans le processus de classification. L'objectif est de réduire l'influence des données mal étiquetées sur les performances de l'algorithme de classification, et donc d'améliorer la carte d'occupation des sols produiteLand surface monitoring is a key challenge for diverse applications such as environment, forestry, hydrology and geology. Such monitoring is particularly helpful for the management of territories and the prediction of climate trends. For this purpose, mapping approaches that employ satellite-based Earth Observations at different spatial and temporal scales are used to obtain the land surface characteristics. More precisely, supervised classification algorithms that exploit satellite data present many advantages compared to other mapping methods. In addition, the recent launches of new satellite constellations - Landsat-8 and Sentinel-2 - enable the acquisition of satellite image time series at high spatial and spectral resolutions, that are of great interest to describe vegetation land cover. These satellite data open new perspectives, but also interrogate the choice of classification algorithms and the choice of input data. In addition, learning classification algorithms over large areas require a substantial number of instances per land cover class describing landscape variability. Accordingly, training data can be extracted from existing maps or specific existing databases, such as crop parcel farmer's declaration or government databases. When using these databases, the main drawbacks are the lack of accuracy and update problems due to a long production time. Unfortunately, the use of these imperfect training data lead to the presence of mislabeled training instance that may impact the classification performance, and so the quality of the produced land cover map. Taking into account the above challenges, this Ph.D. work aims at improving the classification of new satellite image time series at high resolutions. The work has been divided into two main parts. The first Ph.D. goal consists in studying different classification systems by evaluating two classification algorithms with several input datasets. In addition, the stability and the robustness of the classification methods are discussed. The second goal deals with the errors contained in the training data. Firstly, methods for the detection of mislabeled data are proposed and analyzed. Secondly, a filtering method is proposed to take into account the mislabeled data in the classification framework. The objective is to reduce the influence of mislabeled data on the classification performance, and thus to improve the produced land cover map
17
Jayaweera, Mary Chrishani. "Towards the Use of Satellite Data in Security Policy-Related Prediction." Thesis, Uppsala universitet, Avdelningen för visuell information och interaktion, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-452880.
Full textAbstract:
Inadequate economic data makes it more difficult for its incorporation in security-policy related prediction and there is a need for alternative datasets. Satellite data, more specifically nighttime lights data, can be used as a proxy for the economy. In this project, the correlation between nighttime lights and the economy between 1992 and 2018 is explored for five countries in Africa: Nigeria, Libya, the Central African Republic, the Republic of the Congo and Ghana. Data from two different satellite series, DMSP-OLS and VIIRS-DNB are used, and the extracted datasets are calibrated for the differences or intercalibrated. There was found to be a high correlation for two of the countries, the Republic of the Congo and Ghana. The biggest improvement can be made by developing the intercalibration method. A pitfall of the method is that it is not generally applicable as unique circumstances seen for Nigeria show in the correlation results.
18
Julius, Alexandria Marie. "Characterizing Disaster Resilience Using Very High Resolution Time-Sequence Stereo Imagery." The Ohio State University, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=osu1524211742718203.
Full text
19
Hedhli, Ihsen. "Modèles de classification hiérarchiques d'images satellitaires multi-résolutions, multi-temporelles et multi-capteurs. Application aux désastres naturels." Thesis, Nice, 2016. http://www.theses.fr/2016NICE4006/document.
Full textAbstract:
Les moyens mis en œuvre pour surveiller la surface de la Terre, notamment les zones urbaines, en cas de catastrophes naturelles telles que les inondations ou les tremblements de terre, et pour évaluer l’impact de ces événements, jouent un rôle primordial du point de vue sociétal, économique et humain. Dans ce cadre, des méthodes de classification précises et efficaces sont des outils particulièrement importants pour aider à l’évaluation rapide et fiable des changements au sol et des dommages provoqués. Étant données l’énorme quantité et la variété des données Haute Résolution (HR) disponibles grâce aux missions satellitaires de dernière génération et de différents types, telles que Pléiades, COSMO-SkyMed ou RadarSat-2 la principale difficulté est de trouver un classifieur qui puisse prendre en compte des données multi-bande, multi-résolution, multi-date et éventuellement multi-capteur tout en gardant un temps de calcul acceptable. Les approches de classification multi-date/multi-capteur et multi-résolution sont fondées sur une modélisation statistique explicite. En fait, le modèle développé consiste en un classifieur bayésien supervisé qui combine un modèle statistique conditionnel par classe intégrant des informations pixel par pixel à la même résolution et un champ de Markov hiérarchique fusionnant l’information spatio-temporelle et multi-résolution, en se basant sur le critère des Modes Marginales a Posteriori (MPM en anglais), qui vise à affecter à chaque pixel l’étiquette optimale en maximisant récursivement la probabilité marginale a posteriori, étant donné l’ensemble des observations multi-temporelles ou multi-capteurThe capabilities to monitor the Earth's surface, notably in urban and built-up areas, for example in the framework of the protection from environmental disasters such as floods or earthquakes, play important roles in multiple social, economic, and human viewpoints. In this framework, accurate and time-efficient classification methods are important tools required to support the rapid and reliable assessment of ground changes and damages induced by a disaster, in particular when an extensive area has been affected. Given the substantial amount and variety of data available currently from last generation very-high resolution (VHR) satellite missions such as Pléiades, COSMO-SkyMed, or RadarSat-2, the main methodological difficulty is to develop classifiers that are powerful and flexible enough to utilize the benefits of multiband, multiresolution, multi-date, and possibly multi-sensor input imagery. With the proposed approaches, multi-date/multi-sensor and multi-resolution fusion are based on explicit statistical modeling. The method combines a joint statistical model of multi-sensor and multi-temporal images through hierarchical Markov random field (MRF) modeling, leading to statistical supervised classification approaches. We have developed novel hierarchical Markov random field models, based on the marginal posterior modes (MPM) criterion, that support information extraction from multi-temporal and/or multi-sensor information and allow the joint supervised classification of multiple images taken over the same area at different times, from different sensors, and/or at different spatial resolutions. The developed methods have been experimentally validated with complex optical multispectral (Pléiades), X-band SAR (COSMO-Skymed), and C-band SAR (RadarSat-2) imagery taken from the Haiti site
20
Julea, Andreea Maria. "Extraction de motifs spatio-temporels dans des séries d'images de télédétection : application à des données optiques et radar." Phd thesis, Université de Grenoble, 2011. http://tel.archives-ouvertes.fr/tel-00652810.
Full textAbstract:
Les Séries Temporelles d'Images Satellitaires (STIS), visant la même scène en évolution, sont très intéressantes parce qu'elles acquièrent conjointement des informations temporelles et spatiales. L'extraction de ces informations pour aider les experts dans l'interprétation des données satellitaires devient une nécessité impérieuse. Dans ce mémoire, nous exposons comment on peut adapter l'extraction de motifs séquentiels fréquents à ce contexte spatio-temporel dans le but d'identifier des ensembles de pixels connexes qui partagent la même évolution temporelle. La démarche originale est basée sur la conjonction de la contrainte de support avec différentes contraintes de connexité qui peuvent filtrer ou élaguer l'espace de recherche pour obtenir efficacement des motifs séquentiels fréquents groupés (MSFG) avec signification pour l'utilisateur. La méthode d'extraction proposée est non supervisée et basée sur le niveau pixel. Pour vérifier la généricité du concept de MSFG et la capacité de la méthode proposée d'offrir des résultats intéressants à partir des SITS, sont réalisées des expérimentations sur des données réelles optiques et radar.
21
Agoua, Xwégnon. "Développement de méthodes spatio-temporelles pour la prévision à court terme de la production photovoltaïque." Thesis, Paris Sciences et Lettres (ComUE), 2017. http://www.theses.fr/2017PSLEM066/document.
Full textAbstract:
L’évolution du contexte énergétique mondial et la lutte contre le changement climatique ont conduit à l’accroissement des capacités de production d’énergie renouvelable. Les énergies renouvelables sont caractérisées par une forte variabilité due à leur dépendance aux conditions météorologiques. La maîtrise de cette variabilité constitue un enjeu important pour les opérateurs du système électrique, mais aussi pour l’atteinte des objectifs européens de réduction des émissions de gaz à effet de serre, d’amélioration de l’efficacité énergétique et de l’augmentation de la part des énergies renouvelables. Dans le cas du photovoltaïque(PV), la maîtrise de la variabilité de la production passe par la mise en place d’outils qui permettent de prévoir la production future des centrales. Ces prévisions contribuent entre autres à l’augmentation du niveau de pénétration du PV,à l’intégration optimale dans le réseau électrique, à l’amélioration de la gestion des centrales PV et à la participation aux marchés de l’électricité. L’objectif de cette thèse est de contribuer à l’amélioration de la prédictibilité à court-terme (moins de 6 heures) de la production PV. Dans un premier temps, nous analysons la variabilité spatio-temporelle de la production PV et proposons une méthode de réduction de la non-stationnarité des séries de production. Nous proposons ensuite un modèle spatio-temporel de prévision déterministe qui exploite les corrélations spatio-temporelles entre les centrales réparties sur une région. Les centrales sont utilisées comme un réseau de capteurs qui permettent d’anticiper les sources de variabilité. Nous proposons aussi une méthode automatique de sélection des variables qui permet de résoudre les problèmes de dimension et de parcimonie du modèle spatio-temporel. Un modèle spatio-temporel probabiliste a aussi été développé aux fins de produire des prévisions performantes non seulement du niveau moyen de la production future mais de toute sa distribution. Enfin nous proposons, un modèle qui exploite les observations d’images satellites pour améliorer la prévision court-terme de la production et une comparaison de l’apport de différentes sources de données sur les performances de prévisionThe evolution of the global energy context and the challenges of climate change have led to anincrease in the production capacity of renewable energy. Renewable energies are characterized byhigh variability due to their dependence on meteorological conditions. Controlling this variabilityis an important challenge for the operators of the electricity systems, but also for achieving the Europeanobjectives of reducing greenhouse gas emissions, improving energy efficiency and increasing the share of renewable energies in EU energy consumption. In the case of photovoltaics (PV), the control of the variability of the production requires to predict with minimum errors the future production of the power stations. These forecasts contribute to increasing the level of PV penetration and optimal integration in the power grid, improving PV plant management and participating in electricity markets. The objective of this thesis is to contribute to the improvement of the short-term predictability (less than 6 hours) of PV production. First, we analyze the spatio-temporal variability of PV production and propose a method to reduce the nonstationarity of the production series. We then propose a deterministic prediction model that exploits the spatio-temporal correlations between the power plants of a spatial grid. The power stationsare used as a network of sensors to anticipate sources of variability. We also propose an automaticmethod for selecting variables to solve the dimensionality and sparsity problems of the space-time model. A probabilistic spatio-temporal model has also been developed to produce efficient forecasts not only of the average level of future production but of its entire distribution. Finally, we propose a model that exploits observations of satellite images to improve short-term forecasting of PV production
22
Rodes, Arnau Isabel. "Estimation de l'occupation des sols à grande échelle pour l'exploitation d'images d'observation de la Terre à hautes résolutions spatiale, spectrale et temporelle." Thesis, Toulouse 3, 2016. http://www.theses.fr/2016TOU30375/document.
Full textAbstract:
Les missions spatiales d'observation de la Terre de nouvelle génération telles que Sentinel-2 (préparé par l'Agence Spatiale Européenne ESA dans le cadre du programme Copernicus, auparavant appelé Global Monitoring for Environment and Security ou GMES) ou Venµs, conjointement développé par l'Agence Spatiale Française (Centre National d 'Études Spatiales CNES) et l'Agence Spatiale Israélienne (ISA), vont révolutionner la surveillance de l'environnement d' aujourd'hui avec le rendement de volumes inédits de données en termes de richesse spectrale, de revisite temporelle et de résolution spatiale. Venµs livrera des images dans 12 bandes spectrales de 412 à 910 nm, une répétitivité de 2 jours et une résolution spatiale de 10 m; les satellites jumeaux Sentinel-2 assureront une couverture dans 13 bandes spectrales de 443 à 2200 nm, avec une répétitivité de 5 jours, et des résolutions spatiales de 10 à 60m. La production efficace de cartes d'occupation des sols basée sur l'exploitation de tels volumes d'information pour grandes surfaces est un défi à la fois en termes de coûts de traitement mais aussi de variabilité des données. En général, les méthodes classiques font soit usage des approches surveillées (trop coûteux en termes de travaux manuels pour les grandes surfaces), ou soit ciblent des modèles locaux spécialisés pour des problématiques précises (ne s'appliquent pas à autres terrains ou applications), ou comprennent des modèles physiques complexes avec coûts de traitement rédhibitoires. Ces approches existantes actuelles sont donc inefficaces pour l'exploitation du nouveau type de données que les nouvelles missions fourniront, et un besoin se fait sentir pour la mise en œuvre de méthodes précises, rapides et peu supervisées qui permettent la généralisation à l'échelle de grandes zones avec des résolutions élevées. Afin de permettre l'exploitation des volumes de données précédemment décrits, l'objectif de ce travail est la conception et validation d'une approche entièrement automatique qui permet l'estimation de la couverture terrestre de grandes surfaces avec imagerie d'observation de la Terre de haute résolution spatiale, spectrale et temporelle, généralisable à des paysages différents, et offrant un temps de calcul opérationnel avec ensembles de données satellitaires simulés, en préparation des prochaines missions. Cette approche est basée sur l'intégration d'algorithmes de traitement de données, tels que les techniques d'apprentissage de modèles et de classification, et des connaissances liées à l'occupation des sols sur des questions écologiques et agricoles, telles que les variables avec un impact sur la croissance de la végétation ou les pratiques de production. Par exemple, la nouvelle introduction de température comme axe temporel pour un apprentissage des modèles ultérieurs intègre un facteur établi de la croissance de la végétation à des techniques d'apprentissage automatiques pour la caractérisation des paysages. Une attention particulière est accordée au traitement de différentes questions, telles que l'automatisation, les informations manquantes (déterminées par des passages satellitaires, des effets de réflexion des nuages, des ombres ou encore la présence de neige), l'apprentissage et les données de validation limitées, les échantillonnages temporels irréguliers (différent nombre d'images disponible pour chaque période et région, données inégalement réparties dans le temps), la variabilité des données, et enfin la possibilité de travailler avec différents ensembles de données et nomenclaturesThe new generation Earth observation missions such as Sentinel-2 (a twin-satellite initiative prepared by the European Space Agency, ESA, in the frame of the Copernicus programme, previously known as Global Monitoring for Environment and Security or GMES) and Venµs, jointly developed by the French Space Agency (Centre National d'Études Spatiales, CNES) and the Israeli Space Agency (ISA), will revolutionize present-day environmental monitoring with the yielding of unseen volumes of data in terms of spectral richness, temporal revisit and spatial resolution. Venµs will deliver images in 12 spectral bands from 412 to 910 nm, a repetitivity of 2 days, and a spatial resolution of 10 m; the twin Sentinel-2 satellites will provide coverage in 13 spectral bands from 443 to 2200 nm, with a repetitivity of 5 days, and spatial resolutions of 10 to 60m. The efficient production of land cover maps based on the exploitation of such volumes of information for large areas is challenging both in terms of processing costs and data variability. In general, conventional methods either make use of supervised approaches (too costly in terms of manual work for large areas), target specialised local models for precise problem areas (not applicable to other terrains or applications), or include complex physical models with inhibitory processing costs. These existent present-day approaches are thus inefficient for the exploitation of the new type of data that the new missions will provide, and a need arises for the implementation of accurate, fast and minimally supervised methods that allow for generalisation to large scale areas with high resolutions. In order to allow for the exploitation of the previously described volumes of data, the objective of this thesis is the conception, design, and validation of a fully automatic approach that allows the estimation of large-area land cover with high spatial, spectral and temporal resolution Earth observation imagery, being generalisable to different landscapes, and offering operational computation times with simulated satellite data sets, in preparation of the coming missions
23
Sainte, Fare Garnot Vivien. "Learning spatio-temporal representations of satellite time series for large-scale crop mapping." Thesis, Université Gustave Eiffel, 2022. http://www.theses.fr/2022UEFL2006.
Full textAbstract:
L'analyse et le suivi de l'activité agricole d'un territoire nécessitent la production de cartes agricoles précises. Ces cartes identifient les bordures de chaque parcelle ainsi que le type de culture. Ces informations sont précieuses pour une variété d'acteurs et ont des applications allant de la prévision de la production alimentaire à l'allocation de subventions ou à la gestion environnementale. Alors que les premières cartes agricoles nécessitaient un travail de terrain fastidieux, l'essor de l'analyse automatisée des données de télédétection a ouvert la voie à des cartographies à grande échelle. Dans cette thèse nous nous intéressons à la cartographie agricole à partir de séries temporelles d'images satellites multi-spectrales. Dans la plupart des travaux de la dernière décennie ce problème est abordé à l'aide de modèles d'apprentissage automatique entraînés sur des descripteurs conçus par des experts. Cependant, dans la littérature de vision par ordinateur (VO) et du traitement automatique de la langue (TAL), l'entrainement de modèles d'apprentissage profond à apprendre des représentations à partir des données brutes a constitué un changement de paradigme menant à des performances sans précédent sur une variété de problèmes. De même, l'application de ces modèles d'apprentissage profond aux données de télédétection a considérablement amélioré l'état de l'art pour la cartographie agricole ainsi que d'autres tâches de télédétection.Dans cette thèse nous soutenons que les méthodes actuelles issues des littérature VO et TAL ignorent certaines des spécificités des données de télédétection et ne devraient pas être appliquées directement. Au contraire, nous pronons le développement de méthodes adaptées, exploitant les structures spatiales, spectrales et temporelles spécifiques des séries temporelles d'images satellites. Nous caractérisons la cartographie agricole successivement comme une classification à la parcelle, une segmentation sémantique et une segmentation panoptique. Pour chacune de ces tâches, nous développons une nouvelle architecture d'apprentissage profond adaptée aux particularités de la tâche et inspirée des avancées récentes de l'apprentissage profond. Nous montrons que nos méthodes établissent un nouvel état de l'art tout en étant plus efficaces que les approches concurrentes.Plus précisément, nous présentons (i) le Pixel-Set Encoder, un encodeur spatial efficace, (ii) le Temporal Attention Encoder (TAE), un encodeur temporel utilisant la self-attention, (iii) le U-net avec TAE, une variation du TAE pour les problèmes de segmentation, et (iv) Parcel-as-Point, un module de segmentation d'instance conçu pour la segmentation panoptique des parcelles.Nous étudions également comment exploiter des séries temporelles multimodales combinant des informations optiques et radar. Nous améliorons ainsi les performances de nos modèles ainsi que leur robustesse aux nuages. Enfin, nous considérons l'arbre hiérarchique qui décrit les relations sémantiques entre les types de culture. Nous présentons une méthode pour inclure cette structure dans le processus d'apprentissage. Sur la classification des cultures ainsi que d'autres problèmes de classification, notre méthode réduit le taux d'erreurs entre les classes sémantiquement éloignées. En plus de ces méthodes, nous introduisons PASTIS, le premier jeu de données en accès libre de séries temporelles d'images satellites multimodales avec des annotations panoptiques de parcelles agricoles. Nous espérons que ce jeu de données, ainsi que les résultats prometteurs présentés dans cette thèse encourageront d'autres travaux de recherche et aideront à produire des cartes agricoles toujours plus précisesUnderstanding and monitoring the agricultural activity of a territory requires the production of accurate crop type maps. Such maps identify the boundaries of each agricultural parcel along with the cultivated crop type. This information is valuable for a variety of stakeholders and has applications ranging from food supply prediction to subsidy allocation and environmental monitoring. While earlier crop type maps required tedious in situ data collection, the advent of automated analysis of remote sensing data enabled large-scale mapping efforts. In this dissertation, we consider the problem of crop type mapping from multispectral satellite image time series. In most of the literature of the past decade, this problem is typically addressed with traditional machine learning models trained on hand-engineered descriptors. Meanwhile, in the Computer Vision (CV) and Natural Language Processing (NLP) literature, the ability to train deep learning models to learn representations from raw data provoked a paradigm shift leading to unprecedented levels of performance on a variety of problems. Similarly, the application of deep learning models to remote sensing data significantly improved the state-of-the-art for crop type mapping as well as other tasks.In this thesis, we hold that current state-of-the-art methods from CV and NLP ignore some of the crucial specificities of remote sensing data and should not be applied directly. Instead, we argue for the design of bespoke methods exploiting the specific spatial, spectral, and temporal structures of satellite time series. We successively characterise crop type mapping as parcel-based classification, semantic segmentation, and panoptic segmentation. For each of these tasks, we develop a novel deep learning architecture adapted to the task's peculiarities and inspired by recent advances in the deep learning literature. We show that our methods set a new state-of-the-art while being more efficient than competing approaches.Specifically, we introduce (i) the Pixel-Set Encoder, an efficient spatial parcel-based encoder, (ii) the Temporal Attention Encoder (TAE), a self-attention temporal encoder, (iii) U-net with TAE, a variation of the TAE for segmentation problems, and (iv) Parcel-as-Point, a lightweight instance segmentation head designed for the panoptic segmentation of parcels.We also explore how these architectures can leverage multi-modal image time series combining optical and radar information through well-chosen fusion schemes. This approach improves the mapping performance as well as the robustness to cloud obstruction. Lastly, we focus on the hierarchical tree that encapsulates the semantic relationships between crop classes. We introduce a method to include such structure in the learning process. On crop classification as well as other classification problems, we show that our method reduces the rate of errors between semantically distant classes.Along with these methods, we introduce PASTIS, the first large-scale open-access dataset of multimodal satellite image time series with panoptic annotations of agricultural parcels. We hope that this dataset, along with the promising results presented in this dissertation, will encourage further research and help produce ever more accurate agricultural maps
24
Ratana, Piyachat. "Spatial and Temporal Amazon Vegetation Dynamics and Phenology Using Time Series Satellite Data." Diss., The University of Arizona, 2006. http://hdl.handle.net/10150/194427.
Full textAbstract:
Improved knowledge of landscape seasonal variations and phenology at the regional scale is needed for carbon and water flux studies, and biogeochemical, hydrological, and climate models. Amazon vegetation mechanisms and dynamics controlling biosphere-atmosphere interactions are not entirely understood. To better understand these processes, vegetation photosynthetic activity and canopy water and temperature dynamics were analyzed over various types of vegetation in Amazon using satellite data from the Terra-Moderate Resolution Imaging Spectroradiometer (MODIS). The objectives of this dissertation were to 1) assess the spatial and temporal variations of satellite data over the Amazon as a function of vegetation physiognomies for monitoring and discrimination, 2) investigate seasonal vegetation photosynthetic activity and phenology across the forest-cerrado ecotone and conversion areas, and 3) investigate seasonal variations of satellite-based canopy water and land surface temperature in relation to photosynthetic activity over the Amazon basin.The results of this study showed the highly diverse and complex cerrado biome and associated cerrado conversions could be monitored and analyzed with MODIS vegetation index (VI) time series data. The MODIS enhanced vegetation index (EVI) seasonal profiles were found useful in characterizing the spatial and temporal variability in landscape phenology across a climatic gradient of rainfall and sunlight conditions through the rainforest-cerrado ecotone. Significant trends in landscape phenology were observed across the different biomes with strong seasonal shifts resulting from differences in vegetation physiognomic responses to rainfall and sunlight. We also found unique seasonal and temporal patterns of the land surface water index (LSWI) and land surface temperature (LST), which in combination with the EVI provided improved information for monitoring the seasonal ecosystem dynamics of the Amazon rainforest, cerrado, ecotone, and conversion areas. In conclusion, satellite-based, regional scale studies were found to aid in understanding land surface processes and mechanisms at the ecosystem level, providing a "big picture" of landscape dynamics. Coupling this with ground, in-situ measurements, such as from flux towers, can greatly improve the estimation of carbon and water fluxes, and our understanding of the biogeochemistry and climate in very dynamic and changing landscapes.
25
Mondal, Tanmoy. "From Time series signal matching to word spotting in multilingual historical document images." Thesis, Tours, 2015. http://www.theses.fr/2015TOUR4045/document.
Full textAbstract:
Cette thèse traite dela mise en correspondance de séquences appliquée au word spotting (localisation de motsclés dans des images de documents sans en interpréter le contenu). De nombreux algorithmes existent mais très peu d’entre eux ont été évalués dans ce contexte. Nous commençons donc par une étude comparative de ces méthodes sur plusieurs bases d’images de documents historiques. Nous proposons ensuite un nouvel algorithme réunissant la plupart des possibilités offertes séparément dans les autres algorithmes. Ainsi, le FSM (Flexible Sequence Matching) permet de réaliser des correspondances multiples sans considérer des éléments bruités dans la séquence cible, qu’ils se situent au début, à la fin ou bien au coeur de la correspondance. Nous étendons ensuite ces possibilités à la séquence requête en définissant un nouvel algorithme (ESC : Examplary Sequence Cardinality). Finalement, nous proposons une méthode d’appariement alternative utilisant une mise en correspondance inexacte de chaines de codes (shape code) décrivant les motsThis thesis deals with sequence matching techniques, applied to word spotting (locating keywords in document images without interpreting the content). Several sequence matching techniques exist in the literature but very few of them have been evaluated in the context of word spotting. This thesis begins by a comparative study of these methods for word spotting on several datasets of historical images. After analyzing these approaches, we then propose a new algorithm, called as Flexible Sequence Matching (FSM) which combines most of the advantages offered separately by several other previously explored sequence matching algorithms. Thus, FSM is able to skip outliers from target sequence, which can be present at the beginning, at the end or in the middle of the target sequence. Moreover it can perform one-to-one, one-to-many and many-to-one correspondences between query and target sequence without considering noisy elements in the target sequence. We then also extend these characteristics to the query sequence by defining a new algorithm (ESC : Examplary Sequence Cardinality). Finally, we propose an alternative word matching technique by using an inexact chain codes (shape code), describing the words
26
Salmon, Brian Paxton. "Improved hyper-temporal feature extraction methods for land cover change detection in satellite time series." Thesis, University of Pretoria, 2012. http://hdl.handle.net/2263/28199.
Full textAbstract:
The growth in global population inevitably increases the consumption of natural resources. The need to provide basic services to these growing communities leads to an increase in anthropogenic changes to the natural environment. The resulting transformation of vegetation cover (e.g. deforestation, agricultural expansion, urbanisation) has significant impacts on hydrology, biodiversity, ecosystems and climate. Human settlement expansion is the most common driver of land cover change in South Africa, and is currently mapped on an irregular, ad hoc basis using visual interpretation of aerial photographs or satellite images. This thesis proposes several methods of detecting newly formed human settlements using hyper-temporal, multi-spectral, medium spatial resolution MODIS land surface reflectance satellite imagery. The hyper-temporal images are used to extract time series, which are analysed in an automated fashion using machine learning methods. A post-classification change detection framework was developed to analyse the time series using several feature extraction methods and classifiers. Two novel hyper-temporal feature extraction methods are proposed to characterise the seasonal pattern in the time series. The first feature extraction method extracts Seasonal Fourier features that exploits the difference in temporal spectra inherent to land cover classes. The second feature extraction method extracts state-space vectors derived using an extended Kalman filter. The extended Kalman filter is optimised using a novel criterion which exploits the information inherent in the spatio-temporal domain. The post-classification change detection framework was evaluated on different classifiers; both supervised and unsupervised methods were explored. A change detection accuracy of above 85% with false alarm rate below 10% was attained. The best performing methods were then applied at a provincial scale in the Gauteng and Limpopo provinces to produce regional change maps, indicating settlement expansion.Thesis (PhD(Eng))--University of Pretoria, 2012.
Electrical, Electronic and Computer Engineering
unrestricted
27
Denize, Julien. "Evaluation of time-series SAR and optical images for the study of winter land-use." Thesis, Rennes 1, 2019. http://www.theses.fr/2019REN1S062.
Full textAbstract:
L'étude de l'utilisation hivernale du sol représente un enjeu majeur afin de préserver et d'améliorer la qualité des sols et des eaux de surfaces. Cependant la connaissance des dynamiques spatio-temporelles associées à l'utilisation du sol en période hivernale demeure aujourd'hui encore un défi pour la communauté scientifique. C'est dans ce contexte que s'inscrivent ces travaux de thèse dont l'objectif est d'évaluer le potentiel de séries temporelles d'images optiques et RSO à haute résolution spatiale pour l'étude de l'utilisation des sols en période hivernale à une échelle locale et régionale. Pour se faire, une méthodologie a été établie afin : (i) de déterminer la méthode de classification la plus adaptée pour identifier l'usage des sols en hiver; (ii) de comparer des images RSO Sentinel-1 et optiques Sentinel-2; (iii) de définir la configuration RSO la plus adaptée en comparant trois séries temporelles d'images (Alos-2, Radarsat-2 et Sentinel-1).Les résultats ont tout d'abord mis en évidence l'intérêt de l'algorithme de classification Random Forest pour discriminer à une échelle fine les types d'usage des sols en hiver qui sont très variés. Dans un second temps, ils ont souligné l'intérêt des données Sentinel-2 pour cartographier l'utilisation hivernale des sols à une échelle locale et régionale. Enfin, ils ont permis de déterminer qu'une série temporelle dense d'images Sentinel-1 était la configuration RSO la plus adaptée afin d'identifier l'utilisation hivernale du sol. De manière générale, si cette thèse a permis de montrer que les données Sentinel-2 sont les plus adaptées pour étudier l'utilisation du sol en période hivernale, les images RSO ont tout leur intérêt dans les régions où le couvert nuageux est important, les séries temporelles denses Sentinel- 1 ayant été définies comme les plus performantesThe study of winter land-use is a major challenge in order to preserve and improve the quality of soils and surface water. However, knowledge of the spatio-temporal dynamics associated with winter land-use remains a challenge for the scientific community. In this context, the objective of this study is to evaluate the potential of time series of high spatial resolution optical and SAR images for the study of winter land-use at a local and regional scale. For that purpose, a methodology has been established to: (i) determine the most suitable classification method for identifying winter land-use ; (ii) compare Sentinel-1 SAR and Sentinel-2 optical images; (iii) define the most suitable SAR configuration by comparing three image time-series (Alos-2, Radarsat-2 and Sentinel-1).The results first of all highlighted the interest of the Random Forest classification algorithm to discriminate at a fine scale the different types of land use in winter. Secondly, they showed the value of Sentinel-2 data for mapping winter land-use at a local and regional scale. Finally, they determined that a dense time series of Sentinel-1 images was the most appropriate SAR configuration to identify winter land-use. In general, while this thesis has shown that Sentinel-2 data are best suited to studying land use in winter, SAR images are of great interest in regions with significant cloud cover, dense Sentinel-1 time-series having being defined as the most efficient
28
Manfron, G. "ANALYSIS OF AGRO-ECOSYSTEMS EXPLOITING OPTICAL SATELLITE DATA TIME SERIES: THE CASE STUDY OF CAMARGUE REGION, FRANCE." Doctoral thesis, Università degli Studi di Milano, 2016. http://hdl.handle.net/2434/347538.
Full textAbstract:
The research activities presented in this manuscript were conducted in the frame of the international project SCENARICE, whose aim is to demonstrate the contribution of different technical and scientific competences, to assess current characteristics of analyzed cropping systems and to define sustainable future agricultural scenarios. Dynamic simulation crop models are used to evaluate the efficiency of current cropping systems and to predict their performances as consequence of climate change scenarios. In this context, a lack of information regarding the intra- and inter-annual variability of crop practices was highlighted for crops such as winter wheat, for the study area of Camargue. Moreover, a description of possible future cropping systems adaptation strategies was needed to formulate short term scenario farming system assessment. To perform this analysis it is fundamental to identify the different farm typologies representing the study area.
Since it was required to take into account inter-annual variability of crop practices and farm diversities to build farm typologies, representative data of the study region in both time and space were needed.
To address this issue, in this work long term time series of satellite data (2003-2013) were exploited with the specific aims to: (i) provide winter wheat sowing dates estimations variability on a long term period (11 years) to contribute in base line scenario definition and (ii) reconstruct farms land use changes through the analysis of time series of satellite data to provide helpful information for farm typologies definition.
Two main research activities were carried out to address the defined objectives. Firstly a rule-based methodology was developed to automatically identify winter wheat cultivated areas in order to retrieve crop sowing occurrences in the satellite time series. Detection criteria were derived on the basis of agronomic expert knowledge and by interpretation of high confidence temporal signature. The distinction of winter wheat from other crops was based on the individuation of the crop heading and establishment periods and considering the length of the crop cycle. The detection of winter wheat cultivated areas showed that 56% of the target in the study area was correctly detected with low commissions (11%). Once winter wheat area was detected, additional rules were designed to identify sowing dates. The method was able to capture the seasonal variability of sowing dates with errors of ±8 and ±16 days in 45% and 65% of cases respectively. Extending the analysis to the 11 years period it was observed that in Camargue the most frequent sowing period was about October 31th (±4 days of uncertainty). The 2004 and 2006 seasons showed early sowings (late September) the 2003 and 2008 seasons were slightly delayed at the beginning of November. Sowing dates were not correlated to the seasonal rainfall events; this led us to formulate the hypothesis that sowing dates could be much more influenced by the harvest date of the preceding crop and soil moisture, which are related to rains but also to the date of last irrigations and to the wind.
The second activity was related to define farm typologies. Temporal trajectories of winter and summer crops cultivated areas were estimated at farm scale level based on satellite data time series in the 2003-2013 periods. The validation demonstrated that the method was able to produce maps with high overall accuracy (OA 92%) and very low commission errors (3% for summer crops and 7% for winter crops). Omission errors were very low for summer crops (3%) and higher but within an acceptable level for winter crops (31%). Temporal trajectories of annual winter and summer crop land use at farm level were assumed as indicators of farm management (e.g. intensive monoculture farm or diversified crop producer). Trajectories were analysed through a hierarchical clustering procedure to identify farm management typologies. We were able to identify six typologies out of 140 farm samples, covering 75% of the arable land in the study area. A semantic interpretation of the farm types, allowed formulating hypothesis to describe farming systems. The size of the farms seemed to be an explanatory variable of the intensive or extensive farm management.
The two main activities presented in this thesis highlighted the importance of time series spatial and temporal resolution for crop monitoring purposes. Currently, only heterogeneous remotely sensed data in terms of spatial and temporal resolutions are available for agricultural monitoring. Forthcoming sensors (i.e. ESA Sentinel-II A/B) will offer the chance to exploit coexisting high spatial and temporal resolutions for the first time.
A preliminary application of an innovative methodology for the fusion of heterogeneous spatio-temporal resolution remotely sensed datasets was provided in the final section of the thesis with the aim to (i) produce high spatio-temporal resolution time series and (ii) verify the quality and the usefulness of the generated time series for monitoring the main European cultivated crops. The experiment positively demonstrated the contribution of data fusion techniques for the production of time series at high space-time resolution for crop monitoring purposes. The application of data fusion techniques in the main methodologies presented in this work appears to be beneficial.
To conclude this thesis framework, satellite remotely sensed data properly analyzed has shown to be a reliable tool to study large-scale crop cultivations and to retrieve spatially and temporally distributed information of cropping systems. Remote sensing time series analyses lead to highlight patterns of intra- and inter-annual dynamics of agro-practices and were also useful to define farm typologies based on multi-temporal land use trajectories. Results contribute in enriching the studies and the characterization of the Camargue study area, in particular providing information such as sowing dates that are not available at present for the considered study area and represent a step forward in respect to the actual (static) available crop calendar informations. Moreover, the achieved results provide supplementary information layers for summarize and classify the diversity of the farm in the study area and to characterize farming systems.
29
Khwarahm, Nabaz. "Modelling and mapping the birch and grass pollen seasons using satellite sensor time-series in the United Kingdom." Thesis, University of Southampton, 2014. https://eprints.soton.ac.uk/372695/.
Full text
30
BECCATI, Alan. "Multi-sensor Evolution Analysis: an advanced GIS for interactive time series analysis and modelling based on satellite data." Doctoral thesis, Università degli studi di Ferrara, 2011. http://hdl.handle.net/11392/2388733.
Full textAbstract:
Archives of Earth remote sensing data, acquired from orbiting satellites, contain large amounts of information that can be used both for research activities and decision support. Thematic categorization is one method to extract from satellite data meaningful information that humans can directly comprehend. An interactive system that permits to analyse geo-referenced thematic data and its evolution over time is proposed as a tool to efficiently exploit such vast and growing amount of data. This thesis describes the approach used in building the system, the data processing methodology, details architectural elements and graphical interfaces. Finally, this thesis provides an evaluation of potential uses of the features provided, performance levels and usability of an implementation hosting an archive of 15 years moderate resolution (1 Km, from the ATSR instrument) thematic data.
31
Liu, Zhao. "Exploration and application of MISR high resolution Rahman Pinty-Verstraete time series." Thesis, Cape Peninsula University of Technology, 2017. http://hdl.handle.net/20.500.11838/2711.
Full textAbstract:
Thesis (Doctor of Engineering in Electrical Engineering)--Cape Peninsula University of Technology, 2017.Remote sensing provides a way of frequently observing broad land surfaces. The availability of various earth observation data and their potential exploitation in a wide range of socioeconomic applications stimulated the rapid development of remote sensing technology. Much of the research and most of the publications dealing with remote sensing in the solar spectral domain focus on analysing and interpreting the spectral, spatial and temporal signatures of the observed areas. However, the angular signatures of the reflectance field, known as surface anisotropy, also merit attention. The current research took an exploratory approach to the land surface anisotropy described by the RPV model parameters derived from the MISR-HR processing system (denoted as MISR-HR anisotropy data or MISR-HR RPV data), over a period of 14+ years, for three typical terrestrial surfaces in the Western Cape Province of South Africa: a semi-desert area, a wheat field and a vineyard area. The objectives of this study were to explore (1) to what extent spectral and directional signatures of the MISR-HR RPV data may vary in time and space over the different targets (landscapes), and (2) whether the observed variations in anisotropy might be useful in classifying different land surfaces or as a supplementary method to the traditional land cover classification method. The objectives were achieved by exploring the statistics of the MISR-HR RPV data in each spectral band over the different land surfaces, as well as seasonality and trend in these data. The MISR-HR RPV products were affected by outliers and missing values, both of which influenced the statistics, seasonality and trend of the examined time series. This research proposes a new outlier detection method, based on the cost function derived from the RPV model inversion process. Removed outliers and missing values leave gaps in a MISR-HR RPV time series; to avoid introducing extra biases in the statistics of the anisotropy data, this research kept the gaps and relied on gap-resilient trend and seasonality detection methods, such as the Mann-Kendal trend detection and Lomb-Scargle periodogram methods. The exploration of the statistics of the anisotropy data showed that RPV parameter rho exhibited distinctive over the different study sites; NIR band parameter k exhibits prominent high values for the vineyard area; red band parameter Theta data are not that distinctive over different study sites; variance is important in describing all three RPV parameters. The explorations on trends also demonstrated interesting findings: the downward trend in green band parameter rho data for the semi-desert and vineyard areas; and the upward trend in blue band parameters k and Theta data for all the three study sites. The investigation on seasonality showed that all the RPV parameters had seasonal variations which differed over spectral bands and land covers; the results confirmed expectations in previous literature that parameter varies regularly along the observation time, and also revealed seasonal variations in the parameter rho and Theta data. The explorations on the statistics and seasonality of the MISR-HR anisotropy data show that these data are potentially useful for classifying different landscapes. Finally, the classification results demonstrated that both red band parameter rho data and NIR band parameter k data could successfully separate the three different land surfaces in this research, which fulfilled the second primary objective of this study. This research also demonstrated a classification method using multiple RPV parameters as the classification signatures to discriminate different terrestrial surfaces; significant separation results were obtained by this method.
32
Tran, Thi Phuong Thao. "Interpretable time series kernel analytics by pre-image estimation." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM035.
Full textAbstract:
Les méthodes à noyaux sont connues pour être efficaces pour l’analyse d’objets complexes en les plongeant implicitement dans un espace de caractéristiques (feature-space). Pour interpréter et analyser les résultats obtenus, il est souvent nécessaire de restaurer dans l’espace d’entrée les résultats obtenus dans l’espace des caractéristiques à l’aide de méthodes d’estimation de la pré-image. Ce travail propose une méthode d’estimation de la pré-image pour rendre interprétable les méthodes d’analyse de séries temporelles à base de noyaux. Dans la première étape, une fonction de déformation temporelle, supervisée par des contraintes de distances, est définie pour plonger les séries dans un espace métrique où des analyses pratiques peuvent être menées. Dans la deuxième étape, l’estimation de la pré-image des séries temporelles est obtenue par l’apprentissage d’une transformation linéaire (ou non linéaire) assurant une isométrie locale entre le nouvel espace métrique des séries et l’espace des caractéristiques. La méthode proposée est comparée aux méthodes de l’état de l’art au travers de trois tâches principales requérant l’estimation de la pré-image: 1) le centrage des séries temporelles, 2) la reconstruction et le débruitage des séries temporelles et 3) l’apprentissage de représentations pour des séries temporellesKernel methods are known to be effective to analyse complex objects by implicitly embedding them into some feature space. To interpret and analyse the obtained results, it is often required to restore in the input space the results obtained in the feature space by using pre-image estimation methods. This work proposes a pre-image estimation method for time series kernel analytics that consists of two steps. In the first step, a time warp function, driven by distance constraints in the feature space, is defined to embed time series in a metric space where analytics can be performed conveniently. In the second step, the time series pre-image estimation is cast as learning a linear (or a nonlinear) transformation that ensures a local isometry between the time series embedding space and the feature space. The proposed method is compared to state of the art through three major tasks that require pre-image estimation: 1) time series averaging, 2) time series reconstruction and denoising, and 3) time series representation learning. The extensive experiments conducted son 33 publicly-available datasets show the benefits of the pre-image estimation for time series kernel analytics
33
Bergamasco, Luca. "Advanced Deep-Learning Methods For Automatic Change Detection and Classification of Multitemporal Remote-Sensing Images." Doctoral thesis, Università degli studi di Trento, 2022. http://hdl.handle.net/11572/342100.
Full textAbstract:
Deep-Learning (DL) methods have been widely used for Remote Sensing (RS) applications in the last few years, and they allow improving the analysis of the temporal information in bi-temporal and multi-temporal RS images. DL methods use RS data to classify geographical areas or find changes occurring over time. DL methods exploit multi-sensor or multi-temporal data to retrieve results more accurately than single-source or single-date processing. However, the State-of-the-Art DL methods exploit the heterogeneous information provided by these data by focusing the analysis either on the spatial information of multi-sensor multi-resolution images using multi-scale approaches or on the time component of the image time series. Most of the DL RS methods are supervised, so they require a large number of labeled data that is challenging to gather. Nowadays, we have access to many unlabeled RS data, so the creation of long image time series is feasible. However, supervised methods require labeled data that are expensive to gather over image time series. Hence multi-temporal RS methods usually follow unsupervised approaches. In this thesis, we propose DL methodologies that handle these open issues. We propose unsupervised DL methods that exploit multi-resolution deep feature maps derived by a Convolutional Autoencoder (CAE). These DL models automatically learn spatial features from the input during the training phase without any labeled data. We then exploit the high temporal resolution of image time series with the high spatial information of Very-High-Resolution (VHR) images to perform a multi-temporal and multi-scale analysis of the scene. We merge the information provided by the geometrical details of VHR images with the temporal information of the image time series to improve the RS application tasks. We tested the proposed methods to detect changes over bi-temporal RS images acquired by various sensors, such as Landsat-5, Landsat-8, and Sentinel-2, representing burned and deforested areas, and kinds of pasture impurities using VHR orthophotos and Sentinel-2 image time series. The results proved the effectiveness of the proposed methods.
34
Podsiadło, Iwona Katarzyna. "Methods for the analysis of time series of multispectral remote sensing images and application to climate change variable estimations." Doctoral thesis, Università degli studi di Trento, 2021. http://hdl.handle.net/11572/322351.
Full textAbstract:
In the last decades, the increasing number of new generation satellite images characterized by a better spectral, spatial and temporal resolution with respect to the past has provided unprecedented source of information for monitoring climate changes.To exploit this wealth of data, powerful and automatic methods to analyze remote sensing images need to be implemented. Accordingly, the objective of this thesis is to develop advanced methods for the analysis of multitemporal multispectral remote sensing images to support climate change applications. The thesis is divided into two main parts and provides four novel contributions to the state-of-the-art. In the first part of the thesis, we exploit multitemporal and multispectral remote sensing data for accurately monitoring two essential climate variables. The first contribution presents a method to improve the estimation of the glacier mass balance provided by physically-based models. Unlike most of the literature approaches, this method integrates together physically-based models, remote sensing data and in-situ measurements to achieve an accurate and comprehensive glacier mass balance estimation. The second contribution addresses the land cover mapping for monitoring climate change at high spatial resolution. Within this work, we developed two processing chains: one for the production of a recent (2019) static high resolution (10 m) land cover map at subcontinental scale, and the other for the production of a long-term record of regional high resolution (30 m) land cover maps. The second part of this thesis addresses the common challenges faced while performing the analysis of multitemporal multispectral remote sensing data. In this context, the third contribution deals with the multispectral images cloud occlusions problem. Differently from the literature, instead of performing computationally expensive cloud restoration techniques, we study the robustness of deep learning architectures such as Long Short Term Memory classifier to cloud cover. Finally, we address the problem of the large scale training set definition for multispectral data classification. To this aim, we propose an approach that leverages on available low resolution land cover maps and domain adaptation techniques to provide representative training sets at large scale. The proposed methods have been tested on Sentinel-2 and Landsat 5, 7, 8 multispectral images. Qualitative and quantitative experimental results confirm the effectiveness of the methods proposed in this thesis.
35
Taillade, Thibault. "A new strategy for change detection in SAR time-series : application to target detection." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPAST050.
Full textAbstract:
La détection de cibles telles que des navires ou des véhicules dans les images SAR (Synthetic Aperture radar) est un défi important pour la surveillance et la sécurité. Dans certains environnements tels que les zones urbaines, portuaires ou les forêts observées à basses fréquences radar, la détection de ces objets devient difficile en raison des propriétés de rétrodiffusion élevées de l'environnement. Pour résoudre ce problème, la détection de changement (CD) entre différentes images SAR permet de supprimer l'effet de l'environnement et ainsi une meilleur détection des cibles. Cependant, dans différents environnements à forte fréquentation, un chevauchement temporel des cibles peut se produire et génère une erreur d'interprétation possible car l'issue de la détection de changement repose sur une différence relative entre des objets de tailles ou de propriétés différentes. C'est un problème critique lorsque le but est de visualiser et d'obtenir le nombre d'objets à une acquisition donnée, dans les zones à fortes fréquentations comme les ports ou les zones urbaines. Idéalement, cette détection de changement devrait se réaliser entre une image constituée seulement de l'environnement et une image contenant les cibles d’intérêts. Grâce à l'accessibilité actuelle aux séries temporelles d'images SAR, nous proposons de générer une scène de référence (Frozen Background Image - FBR) qui n'est constituée que de l'environnement temporellement statique. La détection de changement entre une image SAR et cette image FBR vise donc a obtenir une map de détection des cibles éphémères présentes. Cette stratégie a été mise en œuvre pour la détection des navires en milieu portuaire et dans le contexte de véhicules cachés sous couvert forestierThe detection of targets such as ships or vehicles in SAR (Synthetic Aperture Radar) images is an essential challenge for surveillance and security purpose. In some environments such as urban areas, harbor areas or forest observed at low radar frequencies, detecting these objects becomes difficult due to the high backscattering properties of the surrounding background. To overcome this issue, change detection (CD) between SAR images enables to cancel the background and highlight successfully targets present within the scene. However, in several environments, a temporal overlapping of targets may occur and generates possible misinterpretation because the outcome relies on the relative change between objects of different sizes or properties. This is a critical issue when the purpose is to visualize and obtain the number of targets at a specific day in high attendance areas such as harbors or urban environments. Ideally, this change detection should occur between a target-free image and onewith possible objects of interest. With the current accessibility to SAR time-series, we propose to compute a frozen background reference (FBR) image that will consists only in the temporally static background. Performing change detection from this FBR image and any SAR image aim to highlight the presence of ephemeral targets. This strategy has been implemented for ship detection in harbor environment and in the context of vehicles hidden under foliage
36
Yang, Bo. "Spatio-temporal Analysis of Urban Heat Island and Heat Wave Evolution using Time-series Remote Sensing Images: Method and Applications." University of Cincinnati / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1552398782461458.
Full text
37
HAO, YONGPING. "AN ANALYSIS OF THE SPATIAL SCALE EFFECTS ON LANDSCAPE PATTERN METRICS IN A DEFORESTED AREA OF RONDONIA, BRAZIL." University of Cincinnati / OhioLINK, 2003. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1070488160.
Full text
38
Hiriart, Thomas. "Two studies in statistical data analysis for the space industry: cyclicality in the industry, and comparative satellite reliability analysis." Thesis, Georgia Institute of Technology, 2009. http://hdl.handle.net/1853/36533.
Full textAbstract:
This thesis brings statistical analyses techniques to bear on data derived from an extensive database of satellite launches and on-orbit anomalies and failures. The data collected is analyzed from two different perspectives and addresses, in two separate studies, two research objectives.
The first study proposes to identify trends and cyclical patterns in the space industry, and to forecast the volume of launches for the next few years. Satellites have been rightfully described as the lifeblood of the entire space industry and the number of satellites ordered or launched per year is an important defining metric of the industry's level of activity. The structure of the space industry, its financial health and its workforce retention and development is dependent on the volume of satellites contracted. As such, trends and variability in this volume have significant strategic impact on the space industry. Over the past 40+ years, hundreds of satellites have been launched every year. Thus, an important data set is available for time series analysis and identification of trends and cycles in the various markets of the space industry. For the purpose of this first study, we collected data for over 6,000 satellites launched since 1960 on a yearly basis. We separated the satellites into three broad segments: 1) defense and intelligence satellites, 2) science satellites, and 3) commercial satellites. Several techniques are available for the analysis of time series data, both in the time domain and in the frequency domain. In this first study, we conducted spectral analysis of the time series for each of the three satellite populations and identified cycles contained in the data. In addition, once harmonic models were derived and fitted to the data, we built forecasting models of satellite launch volumes in the different market segments for the next few years. The potential implications of the results are discussed as a number of strategic matters for the space industry are contingent on the predictions or forecast of the volume of satellites contracted (the example of the U.S. auto industry is a solemn reminder of such possible strategic issues).
The second study uses the previously collected launch data, confined to Earth-orbiting satellites launched between 1990 and 2008, and expanded with the failure information and retirement of each satellite to conduct a comparative analysis of satellite reliability in GEO, LEO, and MEO orbits. Reliability has long been recognized as an essential consideration in the design of space systems. However, there is limited statistical analysis of satellite reliability based on actual flight data. The objective of this second study is to conduct nonparametric satellite reliability analysis, with orbit type as a covariate, and to explore appropriate parametric fits (Weibull, lognormal, and mixture distributions). The results indicate for example that differences exist between the failure behaviors of satellites in different orbits, or that satellite infant mortality exists or dominates more clearly in a particular orbit type. The findings can be useful to satellite manufacturers as they would provide an empirical basis for reviewing and adjusting satellite testing and burn-in procedures.
39
Bouraoui, Seyfallah. "Time series analysis of SAR images using persistent scatterer (PS), small baseline (SB) and merged approaches in regions with small surface deformation." Phd thesis, Université de Strasbourg, 2013. http://tel.archives-ouvertes.fr/tel-01019429.
Full textAbstract:
This thesis aims at the study of small to large surface deformation that can be detected using the remote sensing interferometric synthetic aperture radar (InSAR) methods. The new developments of InSAR processing techniques allow the monitoring of surface deformation with millimeter surface change accuracy. Conventional InSAR use a pair of SAR images ("Master" and "Slave" images) in order to measure the phase difference between the two images taken at different times. The uncertainties in measurements using the conventional InSAR due to the atmospheric delay, the topographic changes and the orbital artifacts are the handicaps of this method. The idea of InSAR method is to measure the phase difference between tow SAR acquisitions. These measure refere to the ground movment according to the satellite position. In interferogram the red to blue colors refere to the pixel movement to or far from the satellite position in Line-Of-Sight (LOS) direction. In 2000's, Radar spacecraft have seen a large number of launching mission, SAR quisitions and InSAR applicability have seen explosion in differents geophysical studies due to the important SAR datas and facility of data accessibity. This SAR-mining needs other type and generation of InSAR processing.In 2001, Ferretti and others introduce a new method called Permanent Scatterer InSAR (PS) that is based on the use of more than one Slave image in InSAR processing with the same Master image. This method allows enhancing the LOS signal for each pixel (PS) by using the best time and/or space-correlated signal (from amplitude and/or from phase) for each pixel over the acquisitions. A large number of algorithms were developed for this purpose using thesame principle (variantes). In 2002, Berardino et al developed new algorithm for monitoring surface deformation based on the combination of stack of InSAR results from SAR couples respecting small baseline (SB) distance. Nowadays, these two methods represent the existing time series (TS) analysis of SAR images approaches. In addition, StaMPS software introduced by Hooper and others, in 2008 is able to combine these two methods in order to take advantages from both of this TS approaches in term of best signal correlation and reducing the signal noise errors. In this thesis, the time series studies of surface changes associate to differents geophysical phenomena will have two interest: the first is to highlight the PS and SBAS results and discuss the fiability of obtained InSAR signal with comparation with the previous studies of the same geophysical case or observations in the field and in the second time, the combined method will also validate the results obtained separately with differents TS techniques. The validation of obtained signal is assured by these two steeps: Both of PS and SBAS methods should give relatively the same interferograms and LOSdisplacement signal (in term of sign and values), in addition these results will be compared with the previous studies results or with observations on the field.In this thesis, the InSAR techniques are applied to different case-studies of small surface deformation [...]
40
Coladello, Leandro Fernandes. "Integration of heterogeneous data in time series : a study of the evolution of aquatic macrophytes in eutrophic reservoirs based on multispectral images and meteorological data /." Presidente Prudente, 2020. http://hdl.handle.net/11449/192672.
Full textAbstract:
Orientador: Maria de Lourdes Bueno Trindade GaloResumo: O represamento de rios para a produção de energia elétrica usualmente provoca atividades antrópicas que impactam um ecossistema aquático fortemente. Uma das consequências de se instalar pequenos reservatórios em regiões sujeitas à intensos processos de urbanização e industrialização é a abundância de macrófitas, resultante do despejo de nutrientes em grandes concentrações no ecossistema aquático. Recentemente, o grande volume de images multitemporais de sensoriamento remoto disponíveis em bancos de dados gratuitos, bem como a alta performance computacional que permite a mineração de grandes volumes de dados, fazem com que o monitoramento de fenômenos ambientais seja um objeto de estudo recorrente. O propósito desse estudo é desenvolver uma metodologia baseada na integração de dados heterogêneos, fornecidos por séries temporais de coleções de imagens multiespectrais e multitemporais Landsat e coleções de dados climáticos históricos, para investigar a evolução e comportamento espacial de macrófitas aquáticas em lagos e reservatórios eutrofizados. A extensa coleção temporal de imagens de superfície de reflectância Landsat disponível e também dados de variáveis ambientais permitiram a construção e análise de séries temporais para investigar a recorrente abundância de macrófitas no reservatório de Salto Grande, localizado na região metropolitana de Campinas, São Paulo, Brasil. Inicialmente, foi encontrado que as imagens Landsat possuem a qualidade radiométrica necessária para se r... (Resumo completo, clicar acesso eletrônico abaixo)
Abstract: River damming for electric power production usually triggers anthropic activities that strongly impact on aquatic ecosystem. One of the consequences of installing small reservoirs in regions subject to an intense process of urbanization and industrialization is the overabundance of macrophytes, resulting from the input of nutrients in high concentration into the aquatic ecosystem. Currently, the large volume of multitemporal remote sensing images available in open data sources, as well as the high computational performance that allow the mining of large volumes of data has made the monitoring of environmental phenomena a recurrent object of analysis. The aim of this study is to develop a methodology based on the integration of heterogeneous data, provided by time series of multispectral and multitemporal Landsat images and collections of historical climatic data, to investigate the evolution and spatial behavior of aquatic macrophytes in lakes and eutrophic reservoirs. So, the extensive temporal collection of the Landsat surface reflectance images made available as well as environmental variables data permitted the construction and analysis of time series to investigate the recurrent over-abundance of macrophytes in Salto Grande reservoir, located in the metropolitan region of Campinas, São Paulo, Brazil. Initially, it was found that the the Landsat images have the necessary radiometric quality to perform the time series analyses, through an assessment based on information ab... (Complete abstract click electronic access below)
Doutor
41
Lambert, Jonas. "Évaluation des baisses de vitalité des peuplements forestiers à partir de séries temporelles d’images satellitaires : application aux résineux du sud du Massif central et à la sapinière pyrénéenne." Thesis, Toulouse, INPT, 2014. http://www.theses.fr/2014INPT0141/document.
Full textAbstract:
Une tendance à l’augmentation des dépérissements forestiers est observée et risque de s’accentuer dans le contexte actuel de changement climatique. La télédétection peut proposer des méthodes innovantes pour l’évaluation de l’état et du devenir des écosystèmes forestiers. Ce travail de thèse vise à proposer, valider et interpréter des mesures de baisse d’activité des résineux du Sud du Massif-Central et de la sapinière pyrénéenne. Le premier objectif est, par l’utilisation de séries temporelles d’images à moyenne résolution spatiale (images NDVI-MODIS), d’identifier les méthodes permettant de mesurer des baisses d’activité, et de vérifier qu’elles correspondent à des baisses de vitalité, dans des peuplements où se manifestent des phénomènes de dépérissement. La détection de changement d’activité, que l’on peut assimiler à des perturbations, repose sur deux approches : la première mesure des écarts ou des tendances de paramètres de phénologie de surface et la deuxième utilise une procédure de décomposition de la série temporelle. Les mesures de changement ont été réalisées sur la période 2000-2011. La détection des ruptures négatives et de forte amplitude dans la réponse de NDVI de 2003 à 2011 confirme l’influence de la sècheresse de 2003, qui se traduit à la fois par les baisses d’activité liées à l’état des arbres mais également par des coupes de dépérissement qui se sont succédées les années suivantes. Un travail préliminaire à l’étape de validation des baisses de vitalité détectées, a consisté à proposer et appliquer un modèle de détection des coupes afin d’éliminer ces situations des zones d’observation. Une procédure de validation des baisses de vitalité a été mise en place dans le cas de la sapinière des Pyrénées. Pour cela, deux approches ont été utilisées : (1) la confrontation à des données indirectes de l’état des peuplements mais spatialement exhaustives, à travers les inventaires des coupes de dépérissement sur la période 2000-2012 et une cartographie du dépérissement datant de 2001 et (2) la confrontation à des données d’observations directes de l’état des Sapins dans le Pays de Sault (Est des Pyrénées), en utilisant une méthode de diagnostic basée sur l’architecture des arbres (méthode ARCHI), avec un échantillonnage adapté à l’échelle des pixels MODIS (Lambert et al. 2013). Des relations ont été mises en évidence, permettant de valider les méthodes utilisées, mais aussi d’en ressortir des limites d’interprétation. Enfin, pour donner des éléments d’interprétation des phénomènes observés, les variations d’activité observées par télédétection ont été confrontées à des données climatiques et édaphiques spatialisées, adaptées à l’étude des milieux forestiers. Les résultats montrent que les baisses de vitalité constatées dans les peuplements de Sapins du Pays de Sault sont significativement corrélées au facteur climatique température et dans une moindre mesure, aux précipitations. Dans les Pyrénées Centrales, où les facteurs de causalité semblent être multiples, l’influence des conditions de sècheresse hydrique et édaphique n’a pas pu être démontréeAn increasing trend of forest decline is observed and is likely to increase in the current context of climate change. Remote sensing can provide innovative methods for the forest ecosystems status assessment. This thesis aims at proposing, validating and interpreting activity measurements of some Southern Massif Central and Pyrenees mountains coniferous stands. The first objective is, using of time series of medium spatial resolution (MODIS-NDVI) images, to identify methods to measure decreases of activity, and to verify if they correspond to vitality decreases in stands in which has been observed forest decline. Change detection of activity, which can be considered as disturbances, is based on two approaches: the first allows to measure differences or trends of phenology surface parameters, and the second uses a method based on the time series decomposition. Changes that occur during the 2000-2011 times-period were measured. The detection of high magnitude negative breakpoints in NDVI time series from 2003 to 2011 confirms the influence of the 2003 summer drought, which both led to decreases in activity related to trees heath status and also to clear-cuts during the following years. Before the validation process, a clear-cut detection method was proposed in order to eliminate these situations in the study areas. A validation procedure was implemented on Pyrenean fir stands. For this step, two approaches were implemented: (1) the use of spatially extensive state stands proxies, through cuts inventory inventories during the 2000-2012 times-period and a 2001 forest decline map, and (2) the use of data from direct tree heath’s observations in the fir stands of Pays de Sault region (Eastern Pyrenees) using a diagnostic method based on the observation of tree architecture (ARCHI method). For this second approach, an appropriate sampling was assessed to deal with the MODIS pixels scale (Lambert et al. 2013). Relationships have been identified, allowing to validate the used methods, but also to highlight theirs interpretation’s limits. Finally, to provide an interpretation of the observed phenomena, the remote sensing activity variations were compared to climatic and soil spatial data which are adapted to the study of forest environments. The results show that vitality declines in Pays de Sault fir stands are significantly correlated with climatic factors, temperature and to a lesser degree to precipitations. In the Central Pyrenees, where the causal factors appear to be numerous, the influence of water and soil drought conditions has not been demonstrated
42
Behling, Robert [Verfasser], Birgit [Akademischer Betreuer] Kleinschmit, Birgit [Gutachter] Kleinschmit, Herrmann [Gutachter] Kaufmann, and Luis [Gutachter] Guanter. "Derivation of spatiotemporal landslide activity for large areas using long-term multi-sensor satellite time series data / Robert Behling ; Gutachter: Birgit Kleinschmit, Herrmann Kaufmann, Luis Guanter ; Betreuer: Birgit Kleinschmit." Berlin : Technische Universität Berlin, 2016. http://d-nb.info/1156271037/34.
Full text
43
Sharif, Abbass. "Visual Data Mining Techniques for Functional Actigraphy Data: An Object-Oriented Approach in R." DigitalCommons@USU, 2012. https://digitalcommons.usu.edu/etd/1394.
Full textAbstract:
Actigraphy, a technology for measuring a subject's overall activity level almost continuously over time, has gained a lot of momentum over the last few years. An actigraph, a watch-like device that can be attached to the wrist or ankle of a subject, uses an accelerometer to measure human movement every minute or even every 15 seconds. Actigraphy data is often treated as functional data. In this dissertation, we discuss what has been done regarding the visualization of actigraphy data, and then we will explain the three main goals we achieved: (i) develop new multivariate visualization techniques for actigraphy data; (ii) integrate the new and current visualization tools into an R package using object-oriented model design; and (iii) develop an adaptive user-friendly web interface for actigraphy software.
44
Kandasamy, Sivasathivel. "Leaf Area Index (LAI) monitoring at global scale : improved definition, continuity and consistency of LAI estimates from kilometric satellite observations." Phd thesis, Université d'Avignon, 2013. http://tel.archives-ouvertes.fr/tel-00967319.
Full textAbstract:
Monitoring biophysical variables at a global scale over long time periods is vital to address the climatechange and food security challenges. Leaf Area Index (LAI) is a structure variable giving a measure of the canopysurface for radiation interception and canopy-atmosphere interactions. LAI is an important variable in manyecosystem models and it has been recognized as an Essential Climate Variable. This thesis aims to provide globaland continuous estimates of LAI from satellite observations in near-real time according to user requirements to beused for diagnostic and prognostic evaluations of vegetation state and functioning. There are already someavailable LAI products which show however some important discrepancies in terms of magnitude and somelimitations in terms of continuity and consistency. This thesis addresses these important issues. First, the nature ofthe LAI estimated from these satellite observations was investigated to address the existing differences in thedefinition of products. Then, different temporal smoothing and gap filling methods were analyzed to reduce noiseand discontinuities in the time series mainly due to cloud cover. Finally, different methods for near real timeestimation of LAI were evaluated. Such comparison assessment as a function of the level of noise and gaps werelacking for LAI.Results achieved within the first part of the thesis show that the effective LAI is more accurately retrievedfrom satellite data than the actual LAI due to leaf clumping in the canopies. Further, the study has demonstratedthat multi-view observations provide only marginal improvements on LAI retrieval. The study also found that foroptimal retrievals the size of the uncertainty envelope over a set of possible solutions to be approximately equal tothat in the reflectance measurements. The results achieved in the second part of the thesis found the method withlocally adaptive temporal window, depending on amount of available observations and Climatology as backgroundestimation to be more robust to noise and missing data for smoothing, gap-filling and near real time estimationswith satellite time series.
45
Gong, Xing. "Analyse de séries temporelles d’images à moyenne résolution spatiale : reconstruction de profils de LAI, démélangeage : application pour le suivi de la végétation sur des images MODIS." Thesis, Rennes 2, 2015. http://www.theses.fr/2015REN20021/document.
Full textAbstract:
Cette thèse s’intéresse à l’analyse de séries temporelles d’images satellites à moyenne résolution spatiale. L’intérêt principal de telles données est leur haute répétitivité qui autorise des analyses de l’usage des sols. Cependant, deux problèmes principaux subsistent avec de telles données. En premier lieu, en raison de la couverture nuageuse, des mauvaises conditions d’acquisition, ..., ces données sont souvent très bruitées. Deuxièmement, les pixels associés à la moyenne résolution spatiale sont souvent “mixtes” dans la mesure où leur réponse spectrale est une combinaison de la réponse de plusieurs éléments “purs”. Ces deux problèmes sont abordés dans cette thèse. Premièrement, nous proposons une technique d’assimilation de données capable de recouvrer des séries temporelles cohérentes de LAI (Leaf Area Index) à partir de séquences d’images MODIS bruitées. Pour cela, le modèle de croissance de plantes GreenLab estutilisé. En second lieu, nous proposons une technique originale de démélangeage, qui s’appuie notamment sur des noyaux “élastiques” capables de gérer les spécificités des séries temporelles (séries de taille différentes, décalées dans le temps, ...)Les résultats expérimentaux, sur des données synthétiques et réelles, montrent de bonnes performances des méthodologies proposéesThis PhD dissertation is concerned with time series analysis for medium spatial resolution (MSR) remote sensing images. The main advantage of MSR data is their high temporal rate which allows to monitor land use. However, two main problems arise with such data. First, because of cloud coverage and bad acquisition conditions, the resulting time series are often corrupted and not directly exploitable. Secondly, pixels in medium spatial resolution images are often “mixed” in the sense that the spectral response is a combination of the response of “pure” elements.These two problems are addressed in this PhD. First, we propose a data assimilation technique able to recover consistent time series of Leaf Area Index from corrupted MODIS sequences. To this end, a plant growth model, namely GreenLab, is used as a dynamical constraint. Second, we propose a new and efficient unmixing technique for time series. It is in particular based on the use of “elastic” kernels able to properly compare time series shifted in time or of various lengths.Experimental results are shown both on synthetic and real data and demonstrate the efficiency of the proposed methodologies
46
Gapper, Justin J. "Bias Reduction in Machine Learning Classifiers for Spatiotemporal Analysis of Coral Reefs using Remote Sensing Images." Chapman University Digital Commons, 2019. https://digitalcommons.chapman.edu/cads_dissertations/2.
Full textAbstract:
This dissertation is an evaluation of the generalization characteristics of machine learning classifiers as applied to the detection of coral reefs using remote sensing images. Three scientific studies have been conducted as part of this research: 1) Evaluation of Spatial Generalization Characteristics of a Robust Classifier as Applied to Coral Reef Habitats in Remote Islands of the Pacific Ocean 2) Coral Reef Change Detection in Remote Pacific Islands using Support Vector Machine Classifiers 3) A Generalized Machine Learning Classifier for Spatiotemporal Analysis of Coral Reefs in the Red Sea. The aim of this dissertation is to propose and evaluate a methodology for developing a robust machine learning classifier that can effectively be deployed to accurately detect coral reefs at scale. The hypothesis is that Landsat data can be used to train a classifier to detect coral reefs in remote sensing imagery and that this classifier can be trained to generalize across multiple sites. Another objective is to identify how well different classifiers perform under the generalized conditions and how unique the spectral signature of coral is as environmental conditions vary across observation sites. A methodology for validating the generalization performance of a classifier to unseen locations is proposed and implemented (Controlled Parameter Cross-Validation,). Analysis is performed using satellite imagery from nine different locations with known coral reefs (six Pacific Ocean sites and three Red Sea sites). Ground truth observations for four of the Pacific Ocean sites and two of the Red Sea sites were used to validate the proposed methodology. Within the Pacific Ocean sites, the consolidated classifier (trained on data from all sites) yielded an accuracy of 75.5% (0.778 AUC). Within the Red Sea sites, the consolidated classifier yielded an accuracy of 71.0% (0.7754 AUC). Finally, long-term change detection analysis is conducted for each of the sites evaluated. In total, over 16,700 km2 was analyzed for benthic cover type and cover change detection analysis. Within the Pacific Ocean sites, decreases in coral cover ranged from 25.3% reduction (Kingman Reef) to 42.7% reduction (Kiritimati Island). Within the Red Sea sites, decrease in coral cover ranged from 3.4% (Umluj) to 13.6% (Al Wajh).
47
Cano, Emmanuelle. "Cartographie des formations végétales naturelles à l’échelle régionale par classification de séries temporelles d’images satellitaires." Thesis, Rennes 2, 2016. http://www.theses.fr/2016REN20024/document.
Full textAbstract:
La cartographie du couvert végétal est un outil essentiel au suivi et à la gestion et des milieux « naturels ». Des cartes caractérisant les essences forestières à l'échelle régionale sont nécessaires pour la gestion des milieux forestiers. Les séries temporelles d'images satellitaires optiques à moyenne résolution spatiale, peuvent permettre de satisfaire ce besoin. L'objectif de cette thèse est d'améliorer la classification supervisée d'une série temporelle afin de produire des cartes à l'échelle régionale détaillant la composition en essences de la végétation forestière. Nous avons d'abord évalué l'apport de la stratification du site d'étude pour améliorer les résultats de la classification d'une série temporelle d'images MODIS. Le recours à une stratification à partir d'une segmentation orientée objet améliore la classification supervisée, avec une augmentation de la valeur de Kappa et du taux de rejet des pixels à classer. Un seuil minimal et un seuil maximal de la surface de végétation à classer ont été identifiés, correspondant respectivement à un taux de rejet trop élevé et à une absence d'effet de la stratification. Nous avons ensuite évalué l'influence de l'organisation de la série temporelle d'images à moyenne résolution spatiale et du choix de l'algorithme de classification. Cette évaluation a été effectuée pour trois algorithmes (maximum de vraisemblance, Support Vector Machine, Random Forest) en faisant varier les caractéristiques de la série temporelle. On observe un effet de la temporalité et de la radiométrie sur la précision de la classification particulièrement significatif et la supériorité de l'algorithme Random Forest. Sur le plan thématique, des confusions subsistent et certains mélanges d'essences sont mal distingués. Nous avons alors cherché à évaluer l'apport du changement de résolution spatiale des images composant la série temporelle pour améliorer les résultats de classification. Les conclusions effectuées précédemment avec les données MODIS sont confortées, ce qui permet de conclure qu'elles sont indépendantes des données d'entrée et de leur résolution spatiale. Une amélioration significative est apportée par le changement de résolution spatiale, avec une augmentation de l'indice de Kappa de 0,60 à 0,72 obtenue grâce à la diminution de la proportion de pixels mixtes. Quelle que soit la résolution spatiale des images utilisées, les résultats obtenus montrent que la définition d'une procédure optimale améliore sensiblement les résultats de la classificationForest cover mapping is an essential tool for forest management. Detailed maps, characterizing forest types at a régional scale, are needed. This need can be fulfilled by médium spatial resolution optical satellite images time sériés. This thesis aims at improving the supervised classification procédure applied to a time sériés, to produce maps detailing forest types at a régional scale. To meet this goal, the improvement of the results obtained by the classification of a MODIS time sériés, performed with a stratification of the study area, was assessed. An improvement of classification accuracy due to stratification built by object-based image analysis was observed, with an increase of the Kappa index value and an increase of the reject fraction rate. These two phenomena are correlated to the classified végétation area. A minimal and a maximal value were identified, respectively related to a too high reject fraction rate and a neutral stratification impact.We carried out a second study, aiming at assessing the influence of the médium spatial resolution time sériés organization and of the algorithm on classification quality. Three distinct classification algorithms (maximum likelihood, Support Vector Machine, Random Forest) and several time sériés were studied. A significant improvement due to temporal and radiométrie effects and the superiority of Random Forest were highlighted by the results. Thematic confusions and low user's and producer's accuracies were still observed for several classes. We finally studied the improvement brought by a spatial resolution change for the images composing the time sériés to discriminate classes of mixed forest species. The conclusions of the former study (MODIS images) were confirmed with DEIMOS images. We can conclude that these effects are independent from input data and their spatial resolution. A significant improvement was also observed with an increase of the Kappa index value from 0,60 with MODIS data to 0,72 with DEIMOS data, due to a decrease of the mixed pixels rate
48
Wandeto, John Mwangi. "Self-organizing map quantization error approach for detecting temporal variations in image sets." Thesis, Strasbourg, 2018. http://www.theses.fr/2018STRAD025/document.
Full textAbstract:
Une nouvelle approche du traitement de l'image, appelée SOM-QE, qui exploite quantization error (QE) des self-organizing maps (SOM) est proposée dans cette thèse. Les SOM produisent des représentations discrètes de faible dimension des données d'entrée de haute dimension. QE est déterminée à partir des résultats du processus d'apprentissage non supervisé du SOM et des données d'entrée. SOM-QE d'une série chronologique d'images peut être utilisé comme indicateur de changements dans la série chronologique. Pour configurer SOM, on détermine la taille de la carte, la distance du voisinage, le rythme d'apprentissage et le nombre d'itérations dans le processus d'apprentissage. La combinaison de ces paramètres, qui donne la valeur la plus faible de QE, est considérée comme le jeu de paramètres optimal et est utilisée pour transformer l'ensemble de données. C'est l'utilisation de l'assouplissement quantitatif. La nouveauté de la technique SOM-QE est quadruple : d'abord dans l'usage. SOM-QE utilise un SOM pour déterminer la QE de différentes images - typiquement, dans un ensemble de données de séries temporelles - contrairement à l'utilisation traditionnelle où différents SOMs sont appliqués sur un ensemble de données. Deuxièmement, la valeur SOM-QE est introduite pour mesurer l'uniformité de l'image. Troisièmement, la valeur SOM-QE devient une étiquette spéciale et unique pour l'image dans l'ensemble de données et quatrièmement, cette étiquette est utilisée pour suivre les changements qui se produisent dans les images suivantes de la même scène. Ainsi, SOM-QE fournit une mesure des variations à l'intérieur de l'image à une instance dans le temps, et lorsqu'il est comparé aux valeurs des images subséquentes de la même scène, il révèle une visualisation transitoire des changements dans la scène à l'étude. Dans cette recherche, l'approche a été appliquée à l'imagerie artificielle, médicale et géographique pour démontrer sa performance. Les scientifiques et les ingénieurs s'intéressent aux changements qui se produisent dans les scènes géographiques d'intérêt, comme la construction de nouveaux bâtiments dans une ville ou le recul des lésions dans les images médicales. La technique SOM-QE offre un nouveau moyen de détection automatique de la croissance dans les espaces urbains ou de la progression des maladies, fournissant des informations opportunes pour une planification ou un traitement approprié. Dans ce travail, il est démontré que SOM-QE peut capturer de très petits changements dans les images. Les résultats confirment également qu'il est rapide et moins coûteux de faire la distinction entre le contenu modifié et le contenu inchangé dans les grands ensembles de données d'images. La corrélation de Pearson a confirmé qu'il y avait des corrélations statistiquement significatives entre les valeurs SOM-QE et les données réelles de vérité de terrain. Sur le plan de l'évaluation, cette technique a donné de meilleurs résultats que les autres approches existantes. Ce travail est important car il introduit une nouvelle façon d'envisager la détection rapide et automatique des changements, même lorsqu'il s'agit de petits changements locaux dans les images. Il introduit également une nouvelle méthode de détermination de QE, et les données qu'il génère peuvent être utilisées pour prédire les changements dans un ensemble de données de séries chronologiquesA new approach for image processing, dubbed SOM-QE, that exploits the quantization error (QE) from self-organizing maps (SOM) is proposed in this thesis. SOM produce low-dimensional discrete representations of high-dimensional input data. QE is determined from the results of the unsupervised learning process of SOM and the input data. SOM-QE from a time-series of images can be used as an indicator of changes in the time series. To set-up SOM, a map size, the neighbourhood distance, the learning rate and the number of iterations in the learning process are determined. The combination of these parameters that gives the lowest value of QE, is taken to be the optimal parameter set and it is used to transform the dataset. This has been the use of QE. The novelty in SOM-QE technique is fourfold: first, in the usage. SOM-QE employs a SOM to determine QE for different images - typically, in a time series dataset - unlike the traditional usage where different SOMs are applied on one dataset. Secondly, the SOM-QE value is introduced as a measure of uniformity within the image. Thirdly, the SOM-QE value becomes a special, unique label for the image within the dataset and fourthly, this label is used to track changes that occur in subsequent images of the same scene. Thus, SOM-QE provides a measure of variations within the image at an instance in time, and when compared with the values from subsequent images of the same scene, it reveals a transient visualization of changes in the scene of study. In this research the approach was applied to artificial, medical and geographic imagery to demonstrate its performance. Changes that occur in geographic scenes of interest, such as new buildings being put up in a city or lesions receding in medical images are of interest to scientists and engineers. The SOM-QE technique provides a new way for automatic detection of growth in urban spaces or the progressions of diseases, giving timely information for appropriate planning or treatment. In this work, it is demonstrated that SOM-QE can capture very small changes in images. Results also confirm it to be fast and less computationally expensive in discriminating between changed and unchanged contents in large image datasets. Pearson's correlation confirmed that there was statistically significant correlations between SOM-QE values and the actual ground truth data. On evaluation, this technique performed better compared to other existing approaches. This work is important as it introduces a new way of looking at fast, automatic change detection even when dealing with small local changes within images. It also introduces a new method of determining QE, and the data it generates can be used to predict changes in a time series dataset
49
Cechim, Júnior Clóvis. "Mapeamento e estimativa de área de cana-de-açúcar no estado do Paraná." Universidade Estadual do Oeste do Parana, 2016. http://tede.unioeste.br:8080/tede/handle/tede/263.
Full textAbstract:
Made available in DSpace on 2017-05-12T14:47:35Z (GMT). No. of bitstreams: 1
Clovis_Cechim_MC.pdf: 6987482 bytes, checksum: c33db297dd7ec8aaf8bfde9e1e56c2cc (MD5)
Previous issue date: 2016-02-04Sugarcane has been cropped and produced in Brazil for a long time, so, it deserves mention because it makes the country as the largest producer, with also representativeness in sugar and ethanol production. The knowledge of reliable estimates concerning their cropped areas is essential for Brazilian agribusiness, as they help in determining prices to producers by power plants as well as allow establishing logistics flow of production. The cropped areas estimates are made by official agencies. Therefore, in order to reduce this subjectivity, geotechnology use comes as an alternative since it has been widely used in mappings agricultural crops. Thus, this study aimed at developing a methodology for mapping sugarcane crop in Paraná State with satellite images as LANDSAT, IRS and spectrum-temporal series of vegetation indexes from MODIS sensor, for 2010/2011 to 2014/2015 harvesting season. The carried out mappings indicated a strong positive correlation concerning Canasat and official IBGE. The developed method was based on Fuzzy ARTMAP classification and was efficient to map and estimate the sugarcane cropped area using vegetation index in Paraná State.
A cana-de-açúcar como cultura cultivada e produzida no Brasil merece destaque, pois torna o País o maior produtor mundial, com representatividade também na produção de açúcar e etanol. O conhecimento de estimativas confiáveis de suas áreas cultivadas é imprescindível para o agronegócio brasileiro, por auxiliar na determinação dos preços aos produtores pelas usinas e permitir estabelecer a logística de escoamento da produção. As estimativas de área cultivada são realizadas de forma subjetiva pelos órgãos oficiais. Com a finalidade de diminuir tal subjetividade, surge como alternativa o uso de geotecnologias, as quais têm sido muito utilizadas em mapeamentos de culturas agrícolas. Diante disto, o objetivo deste trabalho foi o desenvolvimento de uma metodologia para o mapeamento da cultura de cana-de-açúcar para o Estado do Paraná usando imagens dos satélites LANDSAT, IRS e de séries espectro-temporais de índices de vegetação, provenientes do sensor MODIS, para as safras de 2010/2011 a 2014/2015. O mapeamento da cultura foi realizado a partir do modelo de classificação supervisionada Fuzzy ARTMAP, tendo como variáveis de entrada, termos harmônicos de amplitude e fase e as métricas fenológicas da cultura. Os mapeamentos realizados indicaram forte correlação positiva com relação aos dados do Canasat e oficiais IBGE. O método desenvolvido com base na classificação Fuzzy ARTMAP demonstrou ser eficiente para mapear e estimar a área cultivada da cultura de cana-de-açúcar utilizando índices de vegetação no Estado do Paraná.
50
Salami, Yunus. "Risk Management in Reservoir Operations in the Context of Undefined Competitive Consumption." Doctoral diss., University of Central Florida, 2012. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/5478.
Full textAbstract:
Dams and reservoirs with multiple purposes require effective management to fully realize their purposes and maximize efficiency. For instance, a reservoir intended mainly for the purposes of flood control and hydropower generation may result in a system with primary objectives that conflict with each other. This is because higher hydraulic heads are required to achieve the hydropower generation objective while relatively lower reservoir levels are required to fulfill flood control objectives. Protracted imbalances between these two could increase the susceptibility of the system to risks of water shortage or flood, depending on inflow volumes and operational policy effectiveness. The magnitudes of these risks can become even more pronounced when upstream use of the river is unregulated and uncoordinated so that upstream consumptions and releases are arbitrary. As a result, safe operational practices and risk management alternatives must be structured after an improved understanding of historical and anticipated inflows, actual and speculative upstream uses, and the overall hydrology of catchments upstream of the reservoir. One of such systems with an almost yearly occurrence of floods and shortages due to both natural and anthropogenic factors is the dual reservoir system of Kainji and Jebba in Nigeria. To analyze and manage these risks, a methodology that combines a stochastic and deterministic approach was employed. Using methods outlined by Box and Jenkins (1976), autoregressive integrated moving average (ARIMA) models were developed for forecasting Niger river inflows at Kainji reservoir based on twenty-seven-year-long historical inflow data (1970-1996). These were then validated using seven-year inflow records (1997-2003). The model with the best correlation was a seasonal multiplicative ARIMA (2,1,1)x(2,1,2)12 model. Supplementary validation of this model was done with discharge rating curves developed for the inlet of the reservoir using in situ inflows and satellite altimetry data. By comparing net inflow volumes with storage deficit, flood and shortage risk factors at the reservoir were determined based on (a) actual inflows, (b) forecasted inflows (up to 2015), and (c) simulated scenarios depicting undefined competitive upstream consumption. Calculated high-risk years matched actual flood years again suggesting the reliability of the model. Monte Carlo simulations were then used to prescribe safe outflows and storage allocations in order to reduce futuristic risk factors. The theoretical safety levels achieved indicated risk factors below threshold values and showed that this methodology is a powerful tool for estimating and managing flood and shortage risks in reservoirs with undefined competitive upstream consumption.Ph.D.
Doctorate
Civil, Environmental, and Construction Engineering
Engineering and Computer Science
Civil Engineering