To see the other types of publications on this topic, follow the link: Classification and spatiotemporal forecasting.
Journal articles on the topic 'Classification and spatiotemporal forecasting'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Classification and spatiotemporal forecasting.'
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 journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Wang, Guosong, Xidong Wang, Xinrong Wu, Kexiu Liu, Yiquan Qi, Chunjian Sun, and Hongli Fu. "A Hybrid Multivariate Deep Learning Network for Multistep Ahead Sea Level Anomaly Forecasting." Journal of Atmospheric and Oceanic Technology 39, no. 3 (March 2022): 285–301. http://dx.doi.org/10.1175/jtech-d-21-0043.1.
Full textAbstract:
Abstract The accumulated remote sensing data of altimeters and scatterometers have provided new opportunities for ocean state forecasting and have improved our knowledge of ocean–atmosphere exchanges. Studies on multivariate, multistep, spatiotemporal sequence forecasts of sea level anomalies (SLA) for different modalities, however, remain problematic. In this paper, we present a novel hybrid and multivariate deep neural network, named HMnet3, which can be used for SLA forecasting in the South China Sea (SCS). First, a spatiotemporal sequence forecasting network is trained by an improved convolutional long short-term memory (ConvLSTM) network using a channelwise attention mechanism and multivariate data from 1993 to 2015. Then a time series forecasting network is trained by an improved long short-term memory (LSTM) network, which is realized by ensemble empirical mode decomposition (EEMD). Finally, the two networks are combined by a successive correction method to produce SLA forecasts for lead times of up to 15 days, with a special focus on the open sea and coastal regions of the SCS. During the testing period of 2016–18, the performance of HMnet3 with sea surface temperature anomaly (SSTA), wind speed anomaly (SPDA), and SLA data is much better than those of state-of-the-art dynamic and statistical (ConvLSTM, persistence, and climatology) forecast models. Stricter testbeds for trial simulation experiments with real-time datasets are investigated, where the eddy classification metrics of HMnet3 are favorable for all properties, especially for those of small-scale eddies.
2
Plain, M. B., B. Minasny, A. B. McBratney, and R. W. Vervoort. "Spatially explicit seasonal forecasting using fuzzy spatiotemporal clustering of long-term daily rainfall and temperature data." Hydrology and Earth System Sciences Discussions 5, no. 3 (May 14, 2008): 1159–89. http://dx.doi.org/10.5194/hessd-5-1159-2008.
Full textAbstract:
Abstract. A major limitation of statistical forecasts for specific weather station sites is that they are not spatial in the true sense. And while spatial predictions have been studied, their results have indicated a lack of seasonality. Global Circulation Models (GCMs) are spatial, but their spatial resolution is rather coarse. Here we propose spatially explicit seasonal forecasting, based on the Fuzzy Classification of long-term (40 years) daily rainfall and temperature data to create climate memberships over time and location. Data were obtained from weather stations across south-east Australia, covering sub-tropical to arid climate zones. Class memberships were used to produce seasonal predictions using correlations with climate drivers and a regression rules approach. Therefore, this model includes both local climate feedback and the continental drivers. The developed seasonal forecasting model predicts rainfall and temperature reasonably accurately. The final 6-month forecast for average maximum temperature and rainfall produced relative errors of 0.89 and 0.56 and Pearson correlation coefficients of 0.83 and 0.82, respectively.
3
Jiang, Hongxun, Xiaotong Wang, and Caihong Sun. "Predicting PM2.5 in the Northeast China Heavy Industrial Zone: A Semi-Supervised Learning with Spatiotemporal Features." Atmosphere 13, no. 11 (October 23, 2022): 1744. http://dx.doi.org/10.3390/atmos13111744.
Full textAbstract:
Particulate matter PM2.5 pollution affects the Chinese population, particularly in cities such as Shenyang in northeastern China, which occupies a number of traditional heavy industries. This paper proposes a semi-supervised learning model used for predicting PM2.5 concentrations. The model incorporates rich data from the real world, including 11 air quality monitoring stations in Shenyang and nearby cities. There are three types of data: air monitoring, meteorological data, and spatiotemporal information (such as the spatiotemporal effects of PM2.5 emissions and diffusion across different geographical regions). The model consists of two classifiers: genetic programming (GP) to forecast PM2.5 concentrations and support vector classification (SVC) to predict trends. The experimental results show that the proposed model performs better than baseline models in accuracy, including 3% to 18% over a classic multivariate linear regression (MLR), 1% to 11% over a multi-layer perceptron neural network (MLP-ANN), and 21% to 68% over a support vector regression (SVR). Furthermore, the proposed GP approach provides an intuitive contribution analysis of factors for PM2.5 concentrations. The data of backtracking points adjacent to other monitoring stations are critical in forecasting shorter time intervals (1 h). Wind speeds are more important in longer intervals (6 and 24 h).
4
Yusro, Muhammad, and Isnaini Nurisusilawati. "Forecasting Approach to Investigate Dynamic Growth of Organoid within 3D Matrix for Distinct Perspective." Journal of Biomimetics, Biomaterials and Biomedical Engineering 59 (February 14, 2023): 107–17. http://dx.doi.org/10.4028/p-99od29.
Full textAbstract:
Organoid as a 3D structured model in vitro has difficulty in controlling its size. This issue becomes problematic when it is applied in a microfluidic source and sink-based because different dimension leads to different exposure to morphogen resulting in different cell fate. As a model used for biomedical purposes, this problem could lead to a discrepancy. This research is imposed to implement the forecasting method to study the dynamic of organoid growth profile. This approach could help a better understanding via spatiotemporal perspective complemented with a mathematical formula. The forecasting approach that clarifies the trend of this organoid growth by assessing whether the decided trend fits in every (or particular) stage (or not) has not been informed yet. Neural tube organoids have four different mechanical stiffness (0,5 kPa, 2 kPa, 4 kPa, 8kPa) which are documented in three days by time-lapse microscopy used in this experiment. These objects are mapped in a spatiotemporal fashion investigated in the profile and assessed by exponential trend. The actual phenomenon and forecasted result are evaluated by Mean Absolute Percentage Error (MAPE). Based on the result, the profile of organoid growth indicates that the organoid develops mostly following an exponential profile with the highest R2 value of 0,9868 and the lowest being 0,8734. Based on the MAPE value calculation it could be confirmed that the MAPE value on day 3 is the highest among the others indicating that the extended time of growth tends to have a different profile rather than the exponential trend after day 2. It should be noted that on the lowest stiffness (0,5 kPa) the mechanical properties do not significantly affect the organoid size during the development. Almost all (11 by 12 data or 91,6%) of the MAPE value is in excellent criteria (the value is less than 10%). Only one data does not belong to that classification which is in 8 kPa on day 3. Indicating that the higher stiffness the stronger effect on the system. From the axis development perspective, the organoid does not follow any specific pattern. This research could be a reference for a better understanding of the organoid growth profile in the 3D matrix environment which is nowadays become a hot topic in biomedical applications.
5
Akarsu, Osman Nuri. "A Bibliometric Review of Earthquake and Machine Learning Research." January 2024 5, no. 1 (April 1, 2024): 1–10. http://dx.doi.org/10.36937/cebel.2024.1908.
Full textAbstract:
This article presents a bibliometric review of earthquake research and its integration with machine learning techniques. Over the past two decades, there has been a growing interest in using machine learning to enhance earthquake prediction and research. The review collected 1172 scholarly articles from the Web of Science database, focusing on the keywords "earthquake" and "machine learning." Machine learning has shown promise in improving earthquake forecasting models and aiding decision-making in disaster management, infrastructure design, and emergency response. However, it is noted that the application of machine learning in earthquake engineering is still in its early stages and requires further exploration. Key findings of this review include the increasing importance of certain keywords in earthquake and machine learning research, such as "prediction," "neural network," "classification," "logistic regression," and "performance." These keywords highlight the central areas of research focus within this field. The review also identifies research trends and gaps, including the need for more exploration of large-scale, high-dimensional, nonlinear, non-stationary, and heterogeneous spatiotemporal data in earthquake engineering. It emphasizes the necessity for novel machine learning algorithms tailored specifically for earthquake prediction and analysis. Furthermore, it highlights the need for addressing uncertainty in earthquake research and improving forecasting models. The review underscores the growth in interest and collaboration in earthquake research and machine learning, evident in the increasing number of scholarly contributions over the years. In summary, this bibliometric review highlights the importance of accurate forecasting and the potential of machine learning techniques in advancing this field.
6
Rotti, Sumanth, and Petrus C. Martens. "Analysis of SEP Events and Their Possible Precursors Based on the GSEP Catalog." Astrophysical Journal Supplement Series 267, no. 2 (August 1, 2023): 40. http://dx.doi.org/10.3847/1538-4365/acdace.
Full textAbstract:
Abstract Solar energetic particle (SEP) events are one of the most crucial aspects of space weather. Their prediction depends on various factors including the source solar eruptions such as flares and coronal mass ejections (CMEs). The Geostationary Solar Energetic Particle (GSEP) events catalog was developed as an extensive data set toward this effort for solar cycles 22, 23, and 24. In the present work, we review and extend the GSEP data set by (1) adding “weak” SEP events that have proton enhancements from 0.5 to 10 pfu in the E >10 MeV channel and (2) improving the associated solar source eruptions information. We analyze and discuss spatiotemporal properties such as flare magnitudes, locations, rise times, and speeds and widths of CMEs. We check for the correlation of these parameters with peak proton fluxes and event fluences. Our study also focuses on understanding feature importance toward the optimal performance of machine-learning (ML) models for SEP event forecasting. We implement random forest, extreme gradient boosting, logistic regression, and support vector machine classifiers in a binary classification schema. Based on the evaluation of our best models, we find both the flare and CME parameters are requisites to predict the occurrence of an SEP event. This work is a foundation for our further efforts on SEP event forecasting using robust ML methods.
7
Hushtan, Tetiana, and Anatoliy Kolodiychuk. "DEFINING CONDITIONS FOR INCREASING INNOVATION ACTIVITY IN THE INDUSTRIAL COMPLEX: ESSENCE, SYSTEMATIZATION, IDENTIFICATION." Baltic Journal of Economic Studies 7, no. 4 (September 27, 2021): 54–62. http://dx.doi.org/10.30525/2256-0742/2021-7-4-54-62.
Full textAbstract:
The subject of the study is to substantiate classifications of the factors of innovation development of the industry: according to the priority, traditional, barrier, according to the hierarchical level of innovation, the nature of supply demand for innovation, the peculiarity of the influence of factors on the market environment, the influence of factors on innovation localization, importance of innovations, the effect of innovation, nature of the impact, the power of influence, the type of competition, and other classifications of factors of innovation development of the industry. The need to intensify the development of Ukrainian industry in an innovative way requires the identification of the impact on these processes of various factors. To group these influences, the assessment of these factors should be done in the context of separate classes. For this purpose, it is necessary to develop a classification of innovative factors of industrial development. The purpose of the paper is to investigate and systematize the defining conditions for the activation of innovative development in the industrial sphere. The following methods were used in the work: dialectical method of scientific knowledge, analysis and synthesis, comparative, as well as the method of data generalization. It is proved that the complex non-use of these classifications for the substantiation of innovative development of the industry will improve the quality of planning and forecasting documentation and provisions of industrial policy. The applied meaning arising from the criteria for the classification of factors is based on their specific spatiotemporal and situational application, in particular, in conditions of imperfect competition. The classification of innovative factors of industrial development according to their priority is given. In this classification, the priority is determined by the importance and relevance of innovative industry development tasks on the basis of conclusions made as a result of the literature review. Summarizing the factors of innovation development in the barrier classification allows us to distinguish three aggregated groups of factors: socio-political and managerial, socio-economic, and financial. Our socio-economic analysis of innovative development factors of industry also allowed us to identify the following their classification attributes: the hierarchical level of innovation implementation, the character of demand for innovation, the nature of the impact on the market environment, the type of impact, the time horizon of action, impact on the area of innovation localization, the economic essence of innovation, the nature of the significance of innovation, innovation effect, the nature of effective impact, the power of influence, the type of competition.
8
Zhang, Yi, Fang Liu, Sheng Yue, Yuxuan Li, and Qianwei Dong. "Accident Detection and Flow Prediction for Connected and Automated Transport Systems." Journal of Advanced Transportation 2023 (April 17, 2023): 1–9. http://dx.doi.org/10.1155/2023/5041509.
Full textAbstract:
Effective accident detection and traffic flow forecasting are of great importance for quick respond, impact elimination and intelligent control of the traffic flow consisting of autonomous vehicles. This paper proposes a traffic accident detection method for connected and automated transport systems by conducting a grid-based parameter extracting and SVC-based traffic state classification. Allowing for the dynamic spread of traffic flow over time, from upstream to downstream and from accident lanes to other lanes, a spatiotemporal Markov model is established to predict the evolution of traffic flow after accident by introducing the grid as state detection unit and fitting the spatiotemporal evolution with the parameter space mean speed to match the need of both detection accuracy and monitoring scope. Compared with actual accident data, the validation results indicate that the proposed methods present a good performance in accident detection with the accident detection rate as 87.72% and a higher precision rate than both SVM (support vector machine) and ANN (artificial neural network) models in traffic flow prediction. With the active traffic accident identification and dynamic traffic flow prediction, it is beneficial to shorten detection time, reduce possible impacts of traffic accidents and carbon emissions from congestion. The methods can be implied to traffic state recognition and traffic flow prediction, which is one of the significant sections of connected and automated transport systems, and serve as references for accident handling and urban traffic management.
9
Khokhlov, V., О. Umanska, and I. Deriabina. "Objective classification of atmospheric processes for the East European region." Physical Geography and Geomorphology 90, no. 2 (2018): 84–90. http://dx.doi.org/10.17721/phgg.2018.2.10.
Full textAbstract:
The article describes the objective classification, involving the automated systems application to section the atmospheric processes by types. The objective of typing is to split a collection of objects of a certain sample according to the maximum-distance-separable groups. The basis for objective classification includes several methods: correlation, cluster analysis, nonlinear methods, neural network method, etc. One of the analysis methods for the characteristics of synoptic processes is typing, or the classification of synoptic processes by types, which allows finding common features of development of atmospheric processes in a large variety of synoptic situations. The objective of typing is to split a collection of objects of a certain sample by maximum-distance-separable groups. Since the beginning of the XIX century, when the classification of synoptic processes was introduced to the practice of weather forecasting, there were published a large number of works that differ in specific methodological approaches, in a number of selected types of weather, etc. Currently, only on the territory of Europe, according to various estimates, researchers allocate from 4 to 40 types of atmospheric processes and account for up to 209 subtypes, 84 % of which is obtained by analyzing the data of surface atmospheric pressure, geopotential heights and wind characteristics. On-scale data from 6 to 12 hours (9 %), daily (84 %) and monthly data(7 %) are used as an output information. The spatial range varies from mesoscale (5% of classifications), regional (3 %), on an individual nationwide scale (20 %), as part of the continent (22 %) and the continent as a whole (50 %) The second half of the XX century and the beginning of XXI century are characterized by high rates of changes in climatic and circulation conditions. An occurrence of rare weather extremums is a manifestation of the transition state of the atmosphere and its instability. Often regional changes have more significant variations than global. Therefore, progress, in the understanding of current trends of climate change, is impossible without taking into account spatiotemporal dynamics of atmospheric processes. The author considers the main principles of GWL classification and investigates regional characteristics of synoptic processes in the territory of Europe based on the characteristics of the surface baric field and displacement trajectories of the main baric systems. The purpose of this paper is to explore one of the most popular classifications for the European region and to establish the possibility of its further application to the territory of Ukraine. Research methods: a statistical description of the synoptic types for Europe for the period from September 1957 up to August 2002. Results of the study confirm the fact, that the addressed classification is aimed at creation of seasonal and interannual forecasts of synoptic processes and works better in the central, western and southern directions of Europe.
10
Fossa, Manuel, Bastien Dieppois, Nicolas Massei, Matthieu Fournier, Benoit Laignel, and Jean-Philippe Vidal. "Spatiotemporal and cross-scale interactions in hydroclimate variability: a case-study in France." Hydrology and Earth System Sciences 25, no. 11 (November 4, 2021): 5683–702. http://dx.doi.org/10.5194/hess-25-5683-2021.
Full textAbstract:
Abstract. Understanding how water resources vary in response to climate at different temporal and spatial scales is crucial to inform long-term management. Climate change impacts and induced trends may indeed be substantially modulated by low-frequency (multi-year) variations, whose strength varies in time and space, with large consequences for risk forecasting systems. In this study, we present a spatial classification of precipitation, temperature, and discharge variability in France, based on a fuzzy clustering and wavelet spectra of 152 near-natural watersheds between 1958 and 2008. We also explore phase–phase and phase–amplitude causal interactions between timescales of each homogeneous region. A total of three significant timescales of variability are found in precipitation, temperature, and discharge, i.e., 1, 2–4, and 5–8 years. The magnitude of these timescales of variability is, however, not constant over the different regions. For instance, southern regions are markedly different from other regions, with much lower (5–8 years) variability and much larger (2–4 years) variability. Several temporal changes in precipitation, temperature, and discharge variability are identified during the 1980s and 1990s. Notably, in the southern regions of France, we note a decrease in annual temperature variability in the mid 1990s. Investigating cross-scale interactions, our study reveals causal and bi-directional relationships between higher- and lower-frequency variability, which may feature interactions within the coupled land–ocean–atmosphere systems. Interestingly, however, even though time frequency patterns (occurrence and timing of timescales of variability) were similar between regions, cross-scale interactions are far much complex, differ between regions, and are not systematically transferred from climate (precipitation and temperature) to hydrological variability (discharge). Phase–amplitude interactions are indeed absent in discharge variability, although significant phase–amplitude interactions are found in precipitation and temperature. This suggests that watershed characteristics cancel the negative feedback systems found in precipitation and temperature. This study allows for a multi-timescale representation of hydroclimate variability in France and provides unique insight into the complex nonlinear dynamics of this variability and its predictability.
11
Zhang, Tuantuan, Zhongmin Liang, Wentao Li, Jun Wang, Yiming Hu, and Binquan Li. "Statistical post-processing of precipitation forecasts using circulation classifications and spatiotemporal deep neural networks." Hydrology and Earth System Sciences 27, no. 10 (May 22, 2023): 1945–60. http://dx.doi.org/10.5194/hess-27-1945-2023.
Full textAbstract:
Abstract. Statistical post-processing techniques are widely used to reduce systematic biases and quantify forecast uncertainty in numerical weather prediction (NWP). In this study, we propose a method to correct the raw daily forecast precipitation by combining large-scale circulation patterns with local spatiotemporal information such as topography and meteorological factors. Particularly, we first use the self-organizing map (SOM) model to classify large-scale circulation patterns for each season, then we build the convolutional neural network (CNN) model to extract spatial information (e.g., elevation, specific humidity, and mean sea level pressure) and the long short-term memory network (LSTM) model to extract time series (e.g., t, t−1, t−2), and we finally correct local precipitation for each circulation pattern separately. Furthermore, the proposed method (SOM-CNN-LSTM) is compared with other benchmark methods (i.e., CNN, LSTM, and CNN-LSTM) in the Huaihe River basin with a lead time of 15 d from 2007 to 2021. The results show that the proposed SOM-CNN-LSTM post-processing method outperforms other benchmark methods for all lead times and each season with the largest correlation coefficient improvement (32.30 %) and root mean square error reduction (26.58 %). Moreover, the proposed method can effectively capture the westward and northward movement of the western Pacific subtropical high (WPSH), which impacts the basin's summer rain. The results illustrate that incorporating large-scale circulation patterns with local spatiotemporal information is a feasible and effective post-processing method to improve forecasting skills, which would benefit hydrological forecasts and other applications.
12
Abdulrazzaq, Zaidoon T., Raghad H. Hasan, and Nadia A. Aziz. "Integrated TRMM Data and Standardized Precipitation Index to Monitor the Meteorological Drought." Civil Engineering Journal 5, no. 7 (July 21, 2019): 1590–98. http://dx.doi.org/10.28991/cej-2019-03091355.
Full textAbstract:
Droughts are a major problem in Iraq especially in the Arid and Semi-Arid Lands where they are frequent and causes a great deal of suffering and loss. Drought monitoring and forecasting requires extensive climate and meteorological data which is usually largely missing in developing countries or not available in the required spatial and temporal resolutions. In this study, the drought categories were defined for the years 2000, 2005, 2010, 2015 and 2017 using the TRMM data to map the spatiotemporal meteorological drought, and the Standardized Precipitation Index (SPI) to analyze the meteorological drought at 11 stations located in Western Iraq. The SPI analyses were performed on 12-month datasets for five years. The results showed that the northeast region has the higher rainfall indices and the southwest region has the lowest rainfall. An analysis of the drought and rain conditions showed that the quantity of extreme drought events was higher than that expected in the study area, especially in the south and southwest areas. Therefore, an alternate classification is proposed to describe the drought, which spatially classifies the drought type as mild, moderate, severe and extreme. In conclusion, the integration between TRMM data SPI data proved to be an effective tool to map the spatial distribution and drought assessment in the study area.
13
Gel, Yulia R. "Comparative Analysis of the Local Observation-Based (LOB) Method and the Nonparametric Regression-Based Method for Gridded Bias Correction in Mesoscale Weather Forecasting." Weather and Forecasting 22, no. 6 (December 1, 2007): 1243–56. http://dx.doi.org/10.1175/2007waf2006046.1.
Full textAbstract:
Abstract The comparative analysis of three methods for objective grid-based bias removal in mesoscale numerical weather prediction models is considered. The first technique is the local observation-based (LOB) method that extends further the approaches of several recent studies and is focused on utilizing the information obtained from meteorological stations or neighbor grid points in the proximity of a site of interest. The bias at a site of interest might then be considered as a spatiotemporal function of the weighted information on the past biases observed in the cluster of neighbors during a certain time window. The second method is an extension of model output statistics (MOS), combining several modern multiple regression techniques such as the classification and regression trees (CARTs) and the alternative conditional expectation (ACE) and, therefore, is named the CART–ACE method. The CART–ACE method allows representing possible nonlinear aspects of the bias in a parsimonious linearized statistical model. Finally, the third considered method is a natural combination of the LOB and CART–ACE methods in which the information provided by the LOB method is interpreted as an extra predictor in the regression model of the CART–ACE method. The proposed methods are illustrated by a case study of an observation-based verification and bias correction of fifth-generation Pennsylvania State University–National Center for Atmospheric Research Mesoscale Model (MM5) 48-h surface temperature, that is, 2-m temperature, forecasts over the Pacific Northwest.
14
Lima, Carlos H. R., Amir AghaKouchak, and Upmanu Lall. "Classification of mechanisms, climatic context, areal scaling, and synchronization of floods: the hydroclimatology of floods in the Upper Paraná River basin, Brazil." Earth System Dynamics 8, no. 4 (December 1, 2017): 1071–91. http://dx.doi.org/10.5194/esd-8-1071-2017.
Full textAbstract:
Abstract. Floods are the main natural disaster in Brazil, causing substantial economic damage and loss of life. Studies suggest that some extreme floods result from a causal climate chain. Exceptional rain and floods are determined by large-scale anomalies and persistent patterns in the atmospheric and oceanic circulations, which influence the magnitude, extent, and duration of these extremes. Moreover, floods can result from different generating mechanisms. These factors contradict the assumptions of homogeneity, and often stationarity, in flood frequency analysis. Here we outline a methodological framework based on clustering using self-organizing maps (SOMs) that allows the linkage of large-scale processes to local-scale observations. The methodology is applied to flood data from several sites in the flood-prone Upper Paraná River basin (UPRB) in southern Brazil. The SOM clustering approach is employed to classify the 6-day rainfall field over the UPRB into four categories, which are then used to classify floods into four types based on the spatiotemporal dynamics of the rainfall field prior to the observed flood events. An analysis of the vertically integrated moisture fluxes, vorticity, and high-level atmospheric circulation revealed that these four clusters are related to known tropical and extratropical processes, including the South American low-level jet (SALLJ); extratropical cyclones; and the South Atlantic Convergence Zone (SACZ). Persistent anomalies in the sea surface temperature fields in the Pacific and Atlantic oceans are also found to be associated with these processes. Floods associated with each cluster present different patterns in terms of frequency, magnitude, spatial variability, scaling, and synchronization of events across the sites and subbasins. These insights suggest new directions for flood risk assessment, forecasting, and management.
15
Liu, Qian, Yun Li, Manzhu Yu, Long S. Chiu, Xianjun Hao, Daniel Q. Duffy, and Chaowei Yang. "Daytime Rainy Cloud Detection and Convective Precipitation Delineation Based on a Deep Neural Network Method Using GOES-16 ABI Images." Remote Sensing 11, no. 21 (October 30, 2019): 2555. http://dx.doi.org/10.3390/rs11212555.
Full textAbstract:
Precipitation, especially convective precipitation, is highly associated with hydrological disasters (e.g., floods and drought) that have negative impacts on agricultural productivity, society, and the environment. To mitigate these negative impacts, it is crucial to monitor the precipitation status in real time. The new Advanced Baseline Imager (ABI) onboard the GOES-16 satellite provides such a precipitation product in higher spatiotemporal and spectral resolutions, especially during the daytime. This research proposes a deep neural network (DNN) method to classify rainy and non-rainy clouds based on the brightness temperature differences (BTDs) and reflectances (Ref) derived from ABI. Convective and stratiform rain clouds are also separated using similar spectral parameters expressing the characteristics of cloud properties. The precipitation events used for training and validation are obtained from the IMERG V05B data, covering the southeastern coast of the U.S. during the 2018 rainy season. The performance of the proposed method is compared with traditional machine learning methods, including support vector machines (SVMs) and random forest (RF). For rainy area detection, the DNN method outperformed the other methods, with a critical success index (CSI) of 0.71 and a probability of detection (POD) of 0.86. For convective precipitation delineation, the DNN models also show a better performance, with a CSI of 0.58 and POD of 0.72. This automatic cloud classification system could be deployed for extreme rainfall event detection, real-time forecasting, and decision-making support in rainfall-related disasters.
16
Dillon, James, Christopher Donahue, Evan Schehrer, Karl Birkeland, and Kevin Hammonds. "Mapping surface hoar from near-infrared texture in a laboratory." Cryosphere 18, no. 5 (May 24, 2024): 2557–82. http://dx.doi.org/10.5194/tc-18-2557-2024.
Full textAbstract:
Abstract. Surface hoar crystals are snow grains that form when water vapor deposits on the snow surface. Once buried, surface hoar creates a weak layer in the snowpack that can later cause large avalanches to occur. The formation and persistence of surface hoar are highly spatiotemporally variable, making its detection difficult. Remote-sensing technology capable of detecting the presence and spatial distribution of surface hoar would be beneficial for avalanche forecasting, but this capability has yet to be developed. Here, we hypothesize that near-infrared (NIR) texture, defined as the spatial variability of reflectance magnitude, may produce an optical signature unique to surface hoar due to the distinct shape and orientation of the grains. We tested this hypothesis by performing reflectance experiments in a controlled cold laboratory environment to evaluate the potential and accuracy of surface hoar mapping from NIR texture using a near-infrared hyperspectral imager (NIR-HSI) and a lidar operating at 1064 nm. We analyzed 41 snow samples, three of which were surface hoar and 38 of which consisted of other grain morphologies. When using NIR-HSI under direct and diffuse illumination, we found that surface hoar displayed higher NIR texture relative to all other grain shapes across numerous spectral bands and a wide range of spatial resolutions (0.5–50 mm). Due to the large number of spectral- and spatial-resolution combinations, we conducted a detailed samplewise case study at 1324 nm spectral and 10 mm spatial resolution. The case study resulted in the median texture of surface hoar being 1.3 to 8.6 times greater than that of the 38 other samples under direct and diffuse illumination (p < 0.05 in all cases). Using lidar, surface hoar also exhibited significantly increased NIR texture in 30 out of 38 samples, but only at select (5–25 mm) spatial resolutions. Leveraging these results, we propose a simple binary classification algorithm to map the extent of surface hoar on a pixelwise basis using both the NIR-HSI and lidar instruments. The NIR-HSI under direct and diffuse illumination performed best, with a median accuracy of 96.91 % and 97.37 %, respectively. Conversely, the median classification accuracy achieved with lidar was only 66.99 %. Further, to assess the repeatability of our method and demonstrate its mapping capacity, we ran the algorithm on a new sample with mixed microstructures, with an accuracy of 99.61 % and 96.15 % achieved using NIR-HSI under direct and diffuse illumination, respectively. As NIR-HSI detectors become increasingly available, our findings demonstrate the potential of a new tool for avalanche forecasters to remotely assess the spatiotemporal variability of surface hoar, which would improve avalanche forecasts and potentially save lives.
17
Bogner, Konrad, Annie Y. Y. Chang, Luzi Bernhard, Massimiliano Zappa, Samuel Monhart, and Christoph Spirig. "Tercile Forecasts for Extending the Horizon of Skillful Hydrological Predictions." Journal of Hydrometeorology 23, no. 4 (April 2022): 521–39. http://dx.doi.org/10.1175/jhm-d-21-0020.1.
Full textAbstract:
Abstract Medium to subseasonal hydrological forecasts contain more information relevant to water and environmental management tasks than climatological forecasts. However, extracting this information at the most appropriate level of accuracy and spatiotemporal resolution remains a difficulty. Many studies show that the skill of the extended range forecasts with daily resolution tends toward zero after 7–14 days for small mountainous catchments. Beyond that forecast horizon the application of highly sophisticated pre- and postprocessing methods generally produce limited gains. Consequently, current forecasting techniques cannot effectively represent forecast extremes at extended ranges such as anomalously high and low runoff or soil moisture. To tackle these deficiencies, this study analyzes the value of tercile forecasts for weekly aggregates of runoff and soil moisture forecasts available at a daily resolution for Switzerland. The forecasts are classified into three categories: below, above, and normal conditions, which are derived from long-term simulations and correspond approximately to climatological conditions. To achieve improved reliability and skill of the predicted tercile probabilities, a nonparametric probabilistic classification method has been tested. It is based on Gaussian process (GP), which is attractive in machine learning (ML) applications because of its ability to estimate the predictive uncertainty. The outcome of these postprocessed forecasts was compared to preprocessing methods where the meteorological predictions are statistically corrected before passing to the hydrological model. Our results indicate that tercile forecasts of weekly aggregates produce a suitable skill up to 3 weeks lead time using the preprocessed input and up to 4 weeks lead time using the GP method.
18
Regasa, Motuma Shiferaw, Michael Nones, and Dereje Adeba. "A Review on Land Use and Land Cover Change in Ethiopian Basins." Land 10, no. 6 (June 1, 2021): 585. http://dx.doi.org/10.3390/land10060585.
Full textAbstract:
Land Use Land Cover (LULC) changes analysis is one of the most useful methodologies to understand how the land was used in the past years, what types of detections are to be expected in the future, as well as the driving forces and processes behind these changes. In Ethiopia, Africa, the rapid variations of LULC observed in the last decades are mainly due to population pressure, resettlement programs, climate change, and other human- and nature-induced driving forces. Anthropogenic activities are the most significant factors adversely changing the natural status of the landscape and resources, which exerts unfavourable and adverse impacts on the environment and livelihood. The main goal of the present work is to review previous studies, discussing the spatiotemporal LULC changes in Ethiopian basins, to find out common points and gaps that exist in the current literature, to be eventually addressed in the future. A total of 25 articles, published from 2011 to 2020, were selected and reviewed, focusing on LULC classification using ArcGIS and ERDAS imagine software by unsupervised and maximum likelihood supervised classification methods. Key informant interview, focal group discussions, and collection of ground truth information using ground positioning systems for data validation were the major approaches applied in most of the studies. All the analysed research showed that, during the last decades, Ethiopian lands changed from natural to agricultural land use, waterbody, commercial farmland, and built-up/settlement. Some parts of forest land, grazing land, swamp/wetland, shrubland, rangeland, and bare/ rock out cropland cover class changed to other LULC class types, mainly as a consequence of the increasing anthropogenic pressure. In summary, these articles confirmed that LULC changes are a direct result of both natural and human influences, with anthropogenic pressure due to globalisation as the main driver. However, most of the studies provided details of LULC for the past decades within a specific spatial location, while they did not address the challenge of forecasting future LULC changes at the watershed scale, therefore reducing the opportunity to develop adequate basin-wide management strategies for the next years.
19
Foroushani, Mansour A., Christian Opp, Michael Groll, and Amirhossein Nikfal. "Evaluation of WRF-Chem Predictions for Dust Deposition in Southwestern Iran." Atmosphere 11, no. 7 (July 17, 2020): 757. http://dx.doi.org/10.3390/atmos11070757.
Full textAbstract:
The relationships between monthly recorded ground deposition rates (GDRs) and the spatiotemporal characteristics of dust concentrations in southwest Iran were investigated. A simulation by the Weather Research and Forecasting Model coupled with the Chemistry modeling system (WRF-Chem) was conducted for dust deposition during 2014–2015. The monthly dust deposition values observed at 10 different gauge sites (G01–G10) were mapped to show the seasonal and spatial variations in dust episodes at each location. An analysis of the dust deposition samples, however, confirmed that the region along the deposition sites is exposed to the highest monthly dust load, which has a mean value of 2.4 mg cm−2. In addition, the study area is subjected to seasonally varying deposition, which follows the trend: spring > summer > winter > fall. The modeling results further demonstrate that the increase in dust emissions is followed by a windward convergence over the region (particularly in the spring and summer). Based on the maximum likelihood classification of land use land cover, the modeling results are consistent with observation data at gauge sites for three scenarios [S.I, S.II, and S.III]. The WRF model, in contrast with the corresponding observation data, reveals that the rate factor decreases from the southern [S.III—G08, G09, and G10] through [S.II—G04, G05, G06, and G07] to the northern points [S.I—G01, G02, and G03]. A narrower gap between the modeling results and GDRs is indicated if there is an increase in the number of dust particles moving to lower altitudes or an increase in the dust resident time at high altitudes. The quality of the model forecast is altered by the deposition rate and is sensitive to land surface properties and interactions among land and climate patterns.
20
Rios Gaona, M. F., A. Overeem, H. Leijnse, and R. Uijlenhoet. "Sources of uncertainty in rainfall maps from cellular communication networks." Hydrology and Earth System Sciences Discussions 12, no. 3 (March 25, 2015): 3289–317. http://dx.doi.org/10.5194/hessd-12-3289-2015.
Full textAbstract:
Abstract. Accurate measurements of rainfall are important in many hydrological and meteorological applications, for instance, flash-flood early-warning systems, hydraulic structures design, irrigation, weather forecasting, and climate modelling. Whenever possible, link networks measure and store the received power of the electromagnetic signal at regular intervals. The decrease in power can be converted to rainfall intensity, and is largely due to the attenuation by raindrops along the link paths. Such alternative technique fulfills the continuous strive for measurements of rainfall in time and space at higher resolutions, especially in places where traditional rain gauge networks are scarce or poorly maintained. Rainfall maps from microwave link networks have recently been introduced at country-wide scales. Despite their potential in rainfall estimation at high spatiotemporal resolutions, the uncertainties present in rainfall maps from link networks are not yet fully comprehended. The aim of this work is to identify and quantify the sources of uncertainty present in interpolated rainfall maps from link rainfall depths. In order to disentangle these sources of uncertainty, we classified them into two categories: (1) those associated with the individual microwave link measurements, i.e., the errors involved in single-link rainfall retrievals such as wet antenna attenuation, sampling interval of measurements, wet/dry period classification, quantization of the received power, drop size distribution (DSD), and multi-path propagation; (2) those associated with mapping, i.e., the combined effect of the interpolation methodology and the spatial density of link measurements. We computed ~3500 rainfall maps from real and simulated link rainfall depths for 12 days for the land surface of the Netherlands. Simulated link rainfall depths were obtained from radar data. These rainfall maps were compared against quality-controlled gauge-adjusted radar rainfall fields (assumed to be the ground truth). Thus, we were able to not only identify and quantify the sources of uncertainty in such rainfall maps, but also to test the actual and optimal performance of one commercial microwave network from one of the cellular providers in the Netherlands.
21
Rios Gaona, M. F., A. Overeem, H. Leijnse, and R. Uijlenhoet. "Measurement and interpolation uncertainties in rainfall maps from cellular communication networks." Hydrology and Earth System Sciences 19, no. 8 (August 14, 2015): 3571–84. http://dx.doi.org/10.5194/hess-19-3571-2015.
Full textAbstract:
Abstract. Accurate measurements of rainfall are important in many hydrological and meteorological applications, for instance, flash-flood early-warning systems, hydraulic structures design, irrigation, weather forecasting, and climate modelling. Whenever possible, link networks measure and store the received power of the electromagnetic signal at regular intervals. The decrease in power can be converted to rainfall intensity, and is largely due to the attenuation by raindrops along the link paths. Such an alternative technique fulfils the continuous effort to obtain measurements of rainfall in time and space at higher resolutions, especially in places where traditional rain gauge networks are scarce or poorly maintained. Rainfall maps from microwave link networks have recently been introduced at country-wide scales. Despite their potential in rainfall estimation at high spatiotemporal resolutions, the uncertainties present in rainfall maps from link networks are not yet fully comprehended. The aim of this work is to identify and quantify the sources of uncertainty present in interpolated rainfall maps from link rainfall depths. In order to disentangle these sources of uncertainty, we classified them into two categories: (1) those associated with the individual microwave link measurements, i.e. the errors involved in link rainfall retrievals, such as wet antenna attenuation, sampling interval of measurements, wet/dry period classification, dry weather baseline attenuation, quantization of the received power, drop size distribution (DSD), and multi-path propagation; and (2) those associated with mapping, i.e. the combined effect of the interpolation methodology and the spatial density of link measurements. We computed ~ 3500 rainfall maps from real and simulated link rainfall depths for 12 days for the land surface of the Netherlands. Simulated link rainfall depths refer to path-averaged rainfall depths obtained from radar data. The ~ 3500 real and simulated rainfall maps were compared against quality-controlled gauge-adjusted radar rainfall fields (assumed to be the ground truth). Thus, we were able to not only identify and quantify the sources of uncertainty in such rainfall maps, but also test the actual and optimal performance of one commercial microwave network from one of the cellular providers in the Netherlands. Errors in microwave link measurements were found to be the source that contributes most to the overall uncertainty.
22
Li, Cheng, Weimin Zheng, and Peng Ge. "Tourism demand forecasting with spatiotemporal features." Annals of Tourism Research 94 (May 2022): 103384. http://dx.doi.org/10.1016/j.annals.2022.103384.
Full text
23
Murr, Georges, and Saliya Coulibaly. "Machine Learning-assisted spatiotemporal chaos forecasting." EPJ Web of Conferences 287 (2023): 13002. http://dx.doi.org/10.1051/epjconf/202328713002.
Full textAbstract:
Long-term forecasting of extreme events such as oceanic rogue waves, heat waves, floods, earthquakes, has always been a challenge due to their highly complex dynamics. Recently, machine learning methods have been used for model-free forecasting of physical systems. In this work, we investigated the ability of these methods to forecast the emergence of extreme events in a spatiotemporal chaotic passive ring cavity by detecting the precursors of high intensity pulses. To this end, we have implemented supervised sequence (precursors) to sequence (pulses) machine learning algorithms, corresponding to a local forecasting of when and where extreme events will appear.
24
Lin, Xu, Hongyue Wang, Qingqing Zhang, Chaolong Yao, Changxin Chen, Lin Cheng, and Zhaoxiong Li. "A Spatiotemporal Network Model for Global Ionospheric TEC Forecasting." Remote Sensing 14, no. 7 (April 2, 2022): 1717. http://dx.doi.org/10.3390/rs14071717.
Full textAbstract:
In the Global Navigation Satellite System, ionospheric delay is a significant source of error. The magnitude of the ionosphere total electron content (TEC) directly impacts the magnitude of the ionospheric delay. Correcting the ionospheric delay and improving the accuracy of satellite navigation positioning can both benefit from the accurate modeling and forecasting of ionospheric TEC. The majority of current ionospheric TEC forecasting research only considers the temporal or spatial dimensions, ignoring the ionospheric TEC’s spatial and temporal autocorrelation. Therefore, we constructed a spatiotemporal network model with two modules: (i) global spatiotemporal characteristics extraction via forwarding spatiotemporal characteristics transfer and (ii) regional spatiotemporal characteristics correction via reverse spatiotemporal characteristics transfer. This model can realize the complementarity of TEC global spatiotemporal characteristics and regional spatiotemporal characteristics. It also ensures that the global spatiotemporal characteristics of the global ionospheric TEC are transferred to each other in both temporal and spatial domains at the same time. The spatiotemporal network model thus achieves a spatiotemporal prediction of global ionospheric TEC. The Huber loss function is also used to suppress the gross error and noise in the ionospheric TEC data to improve the forecasting accuracy of global ionospheric TEC. We compare the results of the spatiotemporal network model with the Center for Orbit Determination in Europe (CODE), the convolutional Long Short-Term Memory (convLSTM) model and the Predictive Recurrent Neural Network (PredRNN) model for one-day forecasts of global ionospheric TEC under different conditions of time and solar activity, respectively. With internal data validation, the average root mean square error (RMSE) of our proposed algorithm increased by 21.19, 15.75, and 9.67%, respectively, during the maximum solar activity period. During the minimum solar activity period, the RMSE improved by 38.69, 38.02, and 13.54%, respectively. This algorithm can effectively be applied to ionospheric delay error correction and can improve the accuracy of satellite navigation and positioning.
25
Oliveira, Mariana, Luís Torgo, and Vítor Santos Costa. "Evaluation Procedures for Forecasting with Spatiotemporal Data." Mathematics 9, no. 6 (March 23, 2021): 691. http://dx.doi.org/10.3390/math9060691.
Full textAbstract:
The increasing use of sensor networks has led to an ever larger number of available spatiotemporal datasets. Forecasting applications using this type of data are frequently motivated by important domains such as environmental monitoring. Being able to properly assess the performance of different forecasting approaches is fundamental to achieve progress. However, traditional performance estimation procedures, such as cross-validation, face challenges due to the implicit dependence between observations in spatiotemporal datasets. In this paper, we empirically compare several variants of cross-validation (CV) and out-of-sample (OOS) performance estimation procedures, using both artificially generated and real-world spatiotemporal datasets. Our results show both CV and OOS reporting useful estimates, but they suggest that blocking data in space and/or in time may be useful in mitigating CV’s bias to underestimate error. Overall, our study shows the importance of considering data dependencies when estimating the performance of spatiotemporal forecasting models.
26
Pavlyuk, Dmitry. "Temporal Aggregation Effects in Spatiotemporal Traffic Modelling." Sensors 20, no. 23 (December 4, 2020): 6931. http://dx.doi.org/10.3390/s20236931.
Full textAbstract:
Spatiotemporal models are a popular tool for urban traffic forecasting, and their correct specification is a challenging task. Temporal aggregation of traffic sensor data series is a critical component of model specification, which determines the spatial structure and affects models’ forecasting accuracy. Through extensive experiments with real-world data, we investigated the effects of the selected temporal aggregation level for forecasting performance of different spatiotemporal model specifications. A set of analysed models include travel-time-based and correlation-based spatially restricted vector autoregressive models, compared to classical univariate and multivariate time series models. Research experiments are executed in several dimensions: temporal aggregation levels, forecasting horizons (one-step and multi-step forecasts), spatial complexity (sequential and complex spatial structures), the spatial restriction approach (unrestricted, travel-time-based and correlation-based), and series transformation (original and detrended traffic volumes). The obtained results demonstrate the crucial role of the temporal aggregation level for identification of the spatiotemporal traffic flow structure and selection of the best model specification. We conclude that the common research practice of an arbitrary selection of the temporal aggregation level could lead to incorrect conclusions on optimal model specification. Thus, we recommend extending the traffic forecasting methodology by validation of existing and newly developed model specifications for different temporal aggregation levels. Additionally, we provide empirical results on the selection of the optimal temporal aggregation level for the discussed spatiotemporal models for different forecasting horizons.
27
Muñoz-Organero, Mario, and Paula Queipo-Álvarez. "Deep Spatiotemporal Model for COVID-19 Forecasting." Sensors 22, no. 9 (May 5, 2022): 3519. http://dx.doi.org/10.3390/s22093519.
Full textAbstract:
COVID-19 has caused millions of infections and deaths over the last 2 years. Machine learning models have been proposed as an alternative to conventional epidemiologic models in an effort to optimize short- and medium-term forecasts that will help health authorities to optimize the use of policies and resources to tackle the spread of the SARS-CoV-2 virus. Although previous machine learning models based on time pattern analysis for COVID-19 sensed data have shown promising results, the spread of the virus has both spatial and temporal components. This manuscript proposes a new deep learning model that combines a time pattern extraction based on the use of a Long-Short Term Memory (LSTM) Recurrent Neural Network (RNN) over a preceding spatial analysis based on a Convolutional Neural Network (CNN) applied to a sequence of COVID-19 incidence images. The model has been validated with data from the 286 health primary care centers in the Comunidad de Madrid (Madrid region, Spain). The results show improved scores in terms of both root mean square error (RMSE) and explained variance (EV) when compared with previous models that have mainly focused on the temporal patterns and dependencies.
28
., V. Nourani, A. A. Moghaddam ., A. O. Nadiri ., and V. P. Singh . "Forecasting Spatiotemporal Water Levels of Tabriz Aquifer." Trends in Applied Sciences Research 3, no. 4 (April 1, 2008): 319–29. http://dx.doi.org/10.3923/tasr.2008.319.329.
Full text
29
López, Cristóbal, Alberto Álvarez, and Emilio Hernández-García. "Forecasting Confined Spatiotemporal Chaos with Genetic Algorithms." Physical Review Letters 85, no. 11 (September 11, 2000): 2300–2303. http://dx.doi.org/10.1103/physrevlett.85.2300.
Full text
30
Ermagun, Alireza, and David Levinson. "Spatiotemporal traffic forecasting: review and proposed directions." Transport Reviews 38, no. 6 (March 6, 2018): 786–814. http://dx.doi.org/10.1080/01441647.2018.1442887.
Full text
31
Li, Zhenxin, Yong Han, Zhenyu Xu, Zhihao Zhang, Zhixian Sun, and Ge Chen. "PMGCN: Progressive Multi-Graph Convolutional Network for Traffic Forecasting." ISPRS International Journal of Geo-Information 12, no. 6 (June 16, 2023): 241. http://dx.doi.org/10.3390/ijgi12060241.
Full textAbstract:
Traffic forecasting has always been an important part of intelligent transportation systems. At present, spatiotemporal graph neural networks are widely used to capture spatiotemporal dependencies. However, most spatiotemporal graph neural networks use a single predefined matrix or a single self-generated matrix. It is difficult to obtain deeper spatial information by only relying on a single adjacency matrix. In this paper, we present a progressive multi-graph convolutional network (PMGCN), which includes spatiotemporal attention, multi-graph convolution, and multi-scale convolution modules. Specifically, we use a new spatiotemporal attention multi-graph convolution that can extract extensive and comprehensive dynamic spatial dependence between nodes, in which multiple graph convolutions adopt progressive connections and spatiotemporal attention dynamically adjusts each item of the Chebyshev polynomial in graph convolutions. In addition, multi-scale time convolution was added to obtain an extensive and comprehensive dynamic time dependence from multiple receptive field features. We used real datasets to predict traffic speed and traffic flow, and the results were compared with a variety of typical prediction models. PMGCN has the smallest Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) results under different horizons (H = 15 min, 30 min, 60 min), which shows the superiority of the proposed model.
32
Rapantzikos, Konstantinos, Nicolas Tsapatsoulis, Yannis Avrithis, and Stefanos Kollias. "Spatiotemporal saliency for video classification." Signal Processing: Image Communication 24, no. 7 (August 2009): 557–71. http://dx.doi.org/10.1016/j.image.2009.03.002.
Full text
33
Liu, Gang, Silu He, Xing Han, Qinyao Luo, Ronghua Du, Xinsha Fu, and Ling Zhao. "Self-Supervised Spatiotemporal Masking Strategy-Based Models for Traffic Flow Forecasting." Symmetry 15, no. 11 (October 31, 2023): 2002. http://dx.doi.org/10.3390/sym15112002.
Full textAbstract:
Traffic flow forecasting is an important function of intelligent transportation systems. With the rise of deep learning, building traffic flow prediction models based on deep neural networks has become a current research hotspot. Most of the current traffic flow prediction methods are designed from the perspective of model architectures, using only the traffic features of future moments as supervision signals to guide the models to learn the spatiotemporal dependence in traffic flow. However, traffic flow data themselves contain rich spatiotemporal features, and it is feasible to obtain additional self-supervised signals from the data to assist the model to further explore the underlying spatiotemporal dependence. Therefore, we propose a self-supervised traffic flow prediction method based on a spatiotemporal masking strategy. A framework consisting of symmetric backbone models with asymmetric task heads were applied to learn both prediction and spatiotemporal context features. Specifically, a spatiotemporal context mask reconstruction task was designed to force the model to reconstruct the masked features via spatiotemporal context information, so as to assist the model to better understand the spatiotemporal contextual associations in the data. In order to avoid the model simply making inferences based on the local smoothness in the data without truly learning the spatiotemporal dependence, we performed a temporal shift operation on the features to be reconstructed. The experimental results showed that the model based on the spatiotemporal context masking strategy achieved an average prediction performance improvement of 1.56% and a maximum of 7.72% for longer prediction horizons of more than 30 min compared with the backbone models.
34
Cheng, Yong, Haifeng Qu, Jun Wang, Kun Qian, Wei Li, Ling Yang, Xiaodong Han, and Min Liu. "A Radar Echo Extrapolation Model Based on a Dual-Branch Encoder–Decoder and Spatiotemporal GRU." Atmosphere 15, no. 1 (January 14, 2024): 104. http://dx.doi.org/10.3390/atmos15010104.
Full textAbstract:
Precipitation forecasting is an immensely significant aspect of meteorological prediction. Accurate weather predictions facilitate services in sectors such as transportation, agriculture, and tourism. In recent years, deep learning-based radar echo extrapolation techniques have found effective applications in precipitation forecasting. However, the ability of existing methods to extract and characterize complex spatiotemporal features from radar echo images remains insufficient, resulting in suboptimal forecasting accuracy. This paper proposes a novel extrapolation algorithm based on a dual-branch encoder–decoder and spatiotemporal Gated Recurrent Unit. In this model, the dual-branch encoder–decoder structure independently encodes radar echo images in the temporal and spatial domains, thereby avoiding interference between spatiotemporal information. Additionally, we introduce a Multi-Scale Channel Attention Module (MSCAM) to learn global and local feature information from each encoder layer, thereby enhancing focus on radar image details. Furthermore, we propose a Spatiotemporal Attention Gated Recurrent Unit (STAGRU) that integrates attention mechanisms to handle temporal evolution and spatial relationships within radar data, enabling the extraction of spatiotemporal information from a broader receptive field. Experimental results demonstrate the model’s ability to accurately predict morphological changes and motion trajectories of radar images on real radar datasets, exhibiting superior performance compared to existing models in terms of various evaluation metrics. This study effectively improves the accuracy of precipitation forecasting in radar echo images, provides technical support for the short-range forecasting of precipitation, and has good application prospects.
35
Sajan, Bhartendu, Varun Narayan Mishra, Shruti Kanga, Gowhar Meraj, Suraj Kumar Singh, and Pankaj Kumar. "Cellular Automata-Based Artificial Neural Network Model for Assessing Past, Present, and Future Land Use/Land Cover Dynamics." Agronomy 12, no. 11 (November 7, 2022): 2772. http://dx.doi.org/10.3390/agronomy12112772.
Full textAbstract:
Land use and land cover change (LULCC) is among the most apparent natural landscape processes impacted by anthropogenic activities, particularly in fast-growing regions. In India, at present, due to the impacts of anthropogenic climate change, supplemented by the fast pace of developmental activities, the areas providing the highest agricultural yields are facing the threat of either extinction or change in land use. This study assesses the LULCC in the fastest-changing landscape region of the Indian state of Bihar, District Muzaffarpur. This district is known for its litchi cultivation, which, over the last few years, has been observed to be increasing in acreage at the behest of a decrease in natural vegetation. In this study, we aim to assess the past, present and future changes in LULC of the Muzaffarpur district using support vector classification and CA-ANN (cellular automata-artificial neural network) algorithms. For assessing the present and past LULC of the study area, we used Landsat Satellite data for 1990, 2000, 2010, and 2020. It was observed that between 1990 and 2020, the area under vegetation, wetlands, water body, and fallow land decreased by 44.28%, 34.82%, 25.56%, and 5.63%, respectively. At the same time, the area under built-up, litchi plantation, and cropland increased by 1451.30%, 181.91%, and 5.66%, respectively. Extensive ground truthing was carried out to assess the accuracy of the LULC for 2020, whereas historical google earth images were used for 1990, 2000, and 2010, through the use of overall accuracy and kappa coefficient indices. The kappa coefficients for the final LULC for the years 1990, 2000, 2010, and 2020 were 0.79, 0.75, 0.87, and 0.85, respectively. For forecasting the future LULC, first, the LULC of 1990 and 2010 were used to predict the landscape for 2020 using the CA-ANN model. After calibrating and validating the CA-ANN outputs, LULC for 2030 and 2050 were generated. The generated future LULC scenarios were validated using kappa index statistics by comparing the forecast outcomes with the original LULC data for 2020. It was observed that in both 2030 and 2050, built-up and vegetation would be the major transitioning LULC. In 2030 and 2050, built-up will increase by 13.15% and 108.69%, respectively, compared to its area in 2020; whereas vegetation is expected to decrease by 14.30% in 2030 and 32.84% in 2050 compared to its area in 2020. Overall, this study depicted a decline in the natural landscape and a sudden increase in the built-up and cash-crop area. If such trends continue, the future scenario of LULC will also demonstrate the same pattern. This study will help formulate better land use management policy in the study area, and the overall state of Bihar, which is considered to be the poorest state of India and the most vulnerable to natural calamities. It also demonstrates the ability of the CA-ANN model to forecast future events and comprehend spatiotemporal LULC dynamics.
36
Heinecke, G., A. A. Syntetos, and W. Wang. "Forecasting-based SKU classification." International Journal of Production Economics 143, no. 2 (June 2013): 455–62. http://dx.doi.org/10.1016/j.ijpe.2011.11.020.
Full text
37
Pavlyuk. "Transfer Learning: Video Prediction and Spatiotemporal Urban Traffic Forecasting." Algorithms 13, no. 2 (February 13, 2020): 39. http://dx.doi.org/10.3390/a13020039.
Full textAbstract:
Transfer learning is a modern concept that focuses on the application of ideas, models, and algorithms, developed in one applied area, for solving a similar problem in another area. In this paper, we identify links between methodologies in two fields: video prediction and spatiotemporal traffic forecasting. The similarities of the video stream and citywide traffic data structures are discovered and analogues between historical development and modern states of the methodologies are presented and discussed. The idea of transferring video prediction models to the urban traffic forecasting domain is validated using a large real-world traffic data set. The list of transferred techniques includes spatial filtering by predefined kernels in combination with time series models and spectral graph convolutional artificial neural networks. The obtained models’ forecasting performance is compared to the baseline traffic forecasting models: non-spatial time series models and spatially regularized vector autoregression models. We conclude that the application of video prediction models and algorithms for urban traffic forecasting is effective both in terms of observed forecasting accuracy and development, and training efforts. Finally, we discuss problems and obstacles of transferring methodologies and present potential directions for further research.
38
Kolidakis, Stylianos Z., Kornilia Maria A. Kotoula, and George N. Botzoris. "School Mode Choice Classification Model Exploitation Though Artificial Intelligence Classification Application." Mathematical Modelling of Engineering Problems 9, no. 6 (December 31, 2022): 1441–50. http://dx.doi.org/10.18280/mmep.090601.
Full textAbstract:
Human behavior pattern recognition exploited using Artificial Neural Networks (ANN) is at the core of Artificial Intelligence (AI) classification applications. School trip transport forecasting mode selection based upon ANN forecasting ability provided an easy-to-use scientific toolkit for sustainable urban policies designing and implementation. The paper capitalized acknowledged forecasting ability of ANN to recognize and classify behavior patterns leading to parental decisions of school mode choice. Main stages of this research included the conduction of an extended questionnaire survey in 512 parents of school students in Thessaloniki (northern Greece) and the investigation whether ANN forecasting model could classify school mode choice. Research provided promising results (forecasting ability ranging from 76% to 93%) on school mode parental selection forecasting models based on ANN classifier, providing a solid proof of concept for further investigation.
39
Xiong, Liyan, Weihua Ding, Xiaohui Huang, and Weichun Huang. "CLSTAN: ConvLSTM-Based Spatiotemporal Attention Network for Traffic Flow Forecasting." Mathematical Problems in Engineering 2022 (July 11, 2022): 1–13. http://dx.doi.org/10.1155/2022/1604727.
Full textAbstract:
Traffic flow forecasting is the essential part of intelligent transportation sSystem (ITS), which can fully protect traffic safety and improve traffic system management capability. Nevertheless, it is still a challenging problem, which is influenced by many complex factors, including regional distribution and external factors (e.g., holidays and weather). To combine various factors to forecast traffic flow, we presented a novel neural network structure called ConvLSTM-based Spatiotemporal Attention Network (CLSTAN). Specifically, our proposed model is composed of four modules: a preliminary feature extraction module, a spatial attention module, a temporal attention module, and an information fusion module. The spatiotemporal attention module can efficiently learn the complex spatiotemporal patterns of traffic flow through the attention mechanism. The spatial attention module uses a series of initial traffic flow maps as input and obtains the weights of the various regions through a ConvLSTM. The temporal attention module uses the spatially weighted traffic flow map as input and acquires the complex spatiotemporal patterns of traffic flow by a ConvLSTM that introduces an attention mechanism. Finally, the information fusion module integrates spatiotemporal information from multiple time dimensions to forecast future traffic flow. Moreover, to confirm the validity of our method, our experiments were conducted extensively on the TaxiBJ and BikeNYC datasets, and ultimately, CLSTAN performed better than other baseline experiments.
40
Pavlyuk, Dmitry. "Spatiotemporal cross-validation of urban traffic forecasting models." Transportation Research Procedia 52 (2021): 179–86. http://dx.doi.org/10.1016/j.trpro.2021.01.020.
Full text
41
Kaboudan, M. A. "SPATIOTEMPORAL FORECASTING OF HOME PRICES: A GIS APPLICATION." IFAC Proceedings Volumes 38, no. 1 (2005): 95–99. http://dx.doi.org/10.3182/20050703-6-cz-1902.02251.
Full text
42
Director, Hannah M., Adrian E. Raftery, and Cecilia M. Bitz. "Improved Sea Ice Forecasting through Spatiotemporal Bias Correction." Journal of Climate 30, no. 23 (December 2017): 9493–510. http://dx.doi.org/10.1175/jcli-d-17-0185.1.
Full textAbstract:
A new method, called contour shifting, is proposed for correcting the bias in forecasts of contours such as sea ice concentration above certain thresholds. Retrospective comparisons of observations and dynamical model forecasts are used to build a statistical spatiotemporal model of how predicted contours typically differ from observed contours. Forecasted contours from a dynamical model are then adjusted to correct for expected errors in their location. The statistical model changes over time to reflect the changing error patterns that result from reducing sea ice cover in the satellite era in both models and observations. For an evaluation period from 2001 to 2013, these bias-corrected forecasts are on average more accurate than the unadjusted dynamical model forecasts for all forecast months in the year at four different lead times. The total area, which is incorrectly categorized as containing sea ice or not, is reduced by 3.3 × 105 km2 (or 21.3%) on average. The root-mean-square error of forecasts of total sea ice area is also reduced for all lead times.
43
Prestemon, Jeffrey P., María L. Chas-Amil, Julia M. Touza, and Scott L. Goodrick. "Forecasting intentional wildfires using temporal and spatiotemporal autocorrelations." International Journal of Wildland Fire 21, no. 6 (2012): 743. http://dx.doi.org/10.1071/wf11049.
Full textAbstract:
We report daily time series models containing both temporal and spatiotemporal lags, which are applied to forecasting intentional wildfires in Galicia, Spain. Models are estimated independently for each of the 19 forest districts in Galicia using a 1999–2003 training dataset and evaluated out-of-sample with a 2004–06 dataset. Poisson autoregressive models of order P – PAR(P) models – significantly out-perform competing alternative models over both in-sample and out-of-sample datasets, reducing out-of-sample root-mean-squared errors by an average of 15%. PAR(P) and static Poisson models included covariates deriving from crime theory, including the temporal and spatiotemporal autoregressive time series components. Estimates indicate highly significant autoregressive components, lasting up to 3 days, and spatiotemporal autoregression, lasting up to 2 days. Models also applied to predict the effect of increased arrest rates for illegal intentional firesetting indicate that the direct long-run effect of an additional firesetting arrest, summed across forest districts in Galicia, is –139.6 intentional wildfires, equivalent to a long-run elasticity of –0.94.
44
Chai, Songjian, Zhao Xu, Youwei Jia, and Wai Kin Wong. "A Robust Spatiotemporal Forecasting Framework for Photovoltaic Generation." IEEE Transactions on Smart Grid 11, no. 6 (November 2020): 5370–82. http://dx.doi.org/10.1109/tsg.2020.3006085.
Full text
45
Lenzi, Amanda, and Marc G. Genton. "Spatiotemporal probabilistic wind vector forecasting over Saudi Arabia." Annals of Applied Statistics 14, no. 3 (September 2020): 1359–78. http://dx.doi.org/10.1214/20-aoas1347.
Full text
46
You, Yujie, Le Zhang, Peng Tao, Suran Liu, and Luonan Chen. "Spatiotemporal Transformer Neural Network for Time-Series Forecasting." Entropy 24, no. 11 (November 14, 2022): 1651. http://dx.doi.org/10.3390/e24111651.
Full textAbstract:
Predicting high-dimensional short-term time-series is a difficult task due to the lack of sufficient information and the curse of dimensionality. To overcome these problems, this study proposes a novel spatiotemporal transformer neural network (STNN) for efficient prediction of short-term time-series with three major features. Firstly, the STNN can accurately and robustly predict a high-dimensional short-term time-series in a multi-step-ahead manner by exploiting high-dimensional/spatial information based on the spatiotemporal information (STI) transformation equation. Secondly, the continuous attention mechanism makes the prediction results more accurate than those of previous studies. Thirdly, we developed continuous spatial self-attention, temporal self-attention, and transformation attention mechanisms to create a bridge between effective spatial information and future temporal evolution information. Fourthly, we show that the STNN model can reconstruct the phase space of the dynamical system, which is explored in the time-series prediction. The experimental results demonstrate that the STNN significantly outperforms the existing methods on various benchmarks and real-world systems in the multi-step-ahead prediction of a short-term time-series.
47
Jiao, Xiaoying, Gang Li, and Jason Li Chen. "Forecasting international tourism demand: a local spatiotemporal model." Annals of Tourism Research 83 (July 2020): 102937. http://dx.doi.org/10.1016/j.annals.2020.102937.
Full text
48
Abirami, S., and P. Chitra. "Regional air quality forecasting using spatiotemporal deep learning." Journal of Cleaner Production 283 (February 2021): 125341. http://dx.doi.org/10.1016/j.jclepro.2020.125341.
Full text
49
Li, Yung-Chen, Hsiao-Yun Huang, Nan-Ping Yang, and Yi-Hung Kung. "Stock Market Forecasting Based on Spatiotemporal Deep Learning." Entropy 25, no. 9 (September 12, 2023): 1326. http://dx.doi.org/10.3390/e25091326.
Full textAbstract:
This study introduces the Spacetimeformer model, a novel approach for predicting stock prices, leveraging the Transformer architecture with a time–space mechanism to capture both spatial and temporal interactions among stocks. Traditional Long–Short Term Memory (LSTM) and recent Transformer models lack the ability to directly incorporate spatial information, making the Spacetimeformer model a valuable addition to stock price prediction. This article uses the ten minute stock prices of the constituent stocks of the Taiwan 50 Index and the intraday data of individual stock on the Taiwan Stock Exchange. By training the Timespaceformer model with multi-time-step stock price data, we can predict the stock prices at every ten minute interval within the next hour. Finally, we also compare the prediction results with LSTM and Transformer models that only consider temporal relationships. The research demonstrates that the Spacetimeformer model consistently captures essential trend changes and provides stable predictions in stock price forecasting. This article proposes a Spacetimeformer model combined with daily moving windows. This method has superior performance in stock price prediction and also demonstrates the significance and value of the space–time mechanism for prediction. We recommend that people who want to predict stock prices or other financial instruments try our proposed method to obtain a better return on investment.
50
Yue, Aming, and Wenhua Wu. "STGWN: Enhanced spatiotemporal wave forecasting using multiscale features." Applied Ocean Research 145 (April 2024): 103923. http://dx.doi.org/10.1016/j.apor.2024.103923.
Full text