Добірка наукової літератури з теми "Modélisation ensembliste"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Modélisation ensembliste".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Статті в журналах з теми "Modélisation ensembliste"
Drocourt, Cyril, Laurent Delahoche, Eric Brassart, and Cyril Cauchois. "Localisation et modélisation ensembliste de l'environnement d'un robot." Journal Européen des Systèmes Automatisés 37, no. 9 (November 30, 2003): 1075–93. http://dx.doi.org/10.3166/jesa.37.1075-1093.
Повний текст джерелаДисертації з теми "Modélisation ensembliste"
Khemane, Firas. "Estimation fréquentielle par modèle non entier et approche ensembliste : application à la modélisation de la dynamique du conducteur." Thesis, Bordeaux 1, 2011. http://www.theses.fr/2010BOR14282/document.
Повний текст джерелаThis thesis deals with system identification and modeling of fractional transfer functions using bounded and uncertain frequency responses. Therefor, both of fractional differentiation and integration definitions are extended into intervals. Set membership approaches are then applied to estimate coefficients and derivative orders as intervals. These methods are applied to estimate certain Linear Time Invariant systems (LTI), uncertain LTI systems and Linear Parameter Varying systems (LPV). They are notably adopted to model driver's dynamics, since most of studies on one or several individuals shave shown that the collected reactions are not identical and are varying from an experiment to another
Destouches, Mayeul. "Prise en compte des hydrométéores dans un schéma d'assimilation variationnel ensembliste appliqué au modèle de prévision AROME." Thesis, Toulouse 3, 2020. http://www.theses.fr/2020TOU30268.
Повний текст джерелаInitialization of hydrometeor variables is a major challenge in convective-scale numerical weather prediction. This PhD thesis aims at analyzing these hydrometeors in the ensemble variational data assimilation scheme (3DEnVar) recently implemented for the prediction model AROME. This scheme uses an ensemble of forecasts to sample background error covariances. To filter these covariances, optimal localization has been diagnosed using an objective method based on the ensemble statistics only. Heterogeneity and discontinuities of hydrometeor fields have been tackled to perform these diagnoses. Optimal localization depends on model variable, model level and weather situation; a specific localization is advocated for hydrometeor variables. Cycled data assimilation experiments were then performed over a three-month summer period to assess the impact of proposed changes. Precipitation, cloud cover and surface pressure forecasts are significantly improved when hydrometeor are added to the control variables. A new variable-dependent localization scheme is tested, but show neutral impact. Better results were obtained with scale-dependent localization
Heim, Bruno. "Approche ensembliste et par logique floue pour le diagnostic causal de procédés de raffinage : application à un pilote de FCC." Phd thesis, Grenoble INPG, 2003. http://tel.archives-ouvertes.fr/tel-00197531.
Повний текст джерелаNarinc, Olivier. "Variabilité interannuelle de l'eau modale à dix-huit degrés de l'Atlantique nord : contributions apportées par une simulation océanique ensembliste réaliste." Electronic Thesis or Diss., Université Grenoble Alpes, 2024. http://www.theses.fr/2024GRALU022.
Повний текст джерелаThe Eighteen Degree Water (EDW) is a mode water located in the western NorthAtlantic subtropical gyre, south of the Gulf Stream. It is typically described asformed in the winter mixed layer through air-sea exchanges, before being sub-ducted and partly eroded over the rest of the year. The EDW plays a signif-icant role in the air-sea exchanges of the North Atlantic basin, and interactswith the Atlantic meridional overturning circulation (AMOC). Previous stud-ies have shown that in eddy-permitting simulations (resolution of 1/4° or finer),a significant part of the interannual variability of the subtropical gyre and ofthe AMOC is intrinsic to the ocean, meaning that it is independent from atmo-spheric variability and is driven by oceanic processes. The present study usesa realistically forced 20 year, 1/4°, 50-member regional ocean/sea-ice ensemblesimulation with identical air-sea fluxes for all ensemble members. By employingestablished methods that take advantage of the ensemble dimension we are ableto characterise the relative roles of intrinsic and atmospherically forced variabil-ity in the interannual variability of the EDW. Our simulation is shown to be ingood agreement with an observation-based 1/4°, 3-dimensional gridded analy-sis. Investigating average properties of the EDW, we show that while nearly allEDW variability is atmospherically forced at annual and subannual timescales,the intrinsic variability becomes significant at interannual timescales. Resultsobtained in the ensemble simulation are shown to be compatible with observedvariability, suggesting that EDW observations are affected by a significant anddifficult to quantify intrinsic variability. By separating the EDW volume intoa ventilated volume (below the area where EDW is in contact with the atmop-shere) and a subducted volume (the rest of the total volume), we were also ableto describe the yearly cycle of EDW volume change. We found that on averageover the 20 years of the simulation and over the 50 ensemble members, EDW for-mation is in near equilibrium with EDW destruction, and that forced variabilityis dominant in both processes although intrinsic variability plays a greater rolein EDW destruction. In addition, a 12-year timescale is apparent in the intrin-sic variability of EDW volume. The subducted volume carries this 12-year modeof intrinsic variability, modulated by the yearly addition of new EDW volumethrough ventilation. Overall, the results presented in this thesis show that thetypical description of EDW variability as atmospherically-driven is incomplete,and that intrinsic variability is also significant at interannual timescales, moreimportantly in the destruction of EDW
Raharjo, Agus Budi. "Reliability in ensemble learning and learning from crowds." Electronic Thesis or Diss., Aix-Marseille, 2019. http://www.theses.fr/2019AIXM0606.
Повний текст джерелаThe combination of several human expert labels is generally used to make reliable decisions. However, using humans or learning systems to improve the overall decision is a crucial problem. Indeed, several human experts or machine learning have not necessarily the same performance. Hence, a great effort is made to deal with this performance problem in the presence of several actors, i.e., humans or classifiers. In this thesis, we present the combination of reliable classifiers in ensemble learning and learning from crowds. The first contribution is a method, based on weighted voting, which allows selecting a reliable combination of classifications. Our algorithm RelMV transforms confidence scores, obtained during the training phase, into reliable scores. By using these scores, it determines a set of reliable candidates through both static and dynamic selection process. When it is hard to find expert labels as ground truth, we propose an approach based on Bayesian and expectation-maximization (EM) as our second contribution. The aim is to evaluate the reliability degree of each annotator and to aggregate the appropriate labels carefully. We optimize the computation time of the algorithm in order to adapt a large number of data collected from crowds. The obtained outcomes show better accuracy, stability, and computation time compared to the previous methods. Also, we conduct an experiment considering the melanoma diagnosis problem using a real-world medical dataset consisting of a set of skin lesions images, which is annotated by multiple dermatologists
Safadi, El Abed El. "Contribution à l'évaluation des risques liés au TMD (transport de matières dangereuses) en prenant en compte les incertitudes." Thesis, Université Grenoble Alpes (ComUE), 2015. http://www.theses.fr/2015GREAT059/document.
Повний текст джерелаWhen an accidental event is occurring, the process of technological risk assessment, in particular the one related to Dangerous Goods Transportation (DGT), allows assessing the level of potential risk of impacted areas in order to provide and quickly take prevention and protection actions (containment, evacuation ...). The objective is to reduce and control its effects on people and environment. The first issue of this work is to evaluate the risk level for areas subjected to dangerous goods transportation. The quantification of the intensity of the occurring events needed to do this evaluation is based on effect models (analytical or computer code). Regarding the problem of dispersion of toxic products, these models mainly contain inputs linked to different databases, like the exposure data and meteorological data. The second problematic is related to the uncertainties affecting some model inputs. To determine the geographical danger zone where the estimated risk level is not acceptable, it is necessary to identify and take in consideration the uncertainties on the inputs in aim to propagate them in the effect model and thus to have a reliable evaluation of the risk level. The first phase of this work is to evaluate and propagate the uncertainty on the gas concentration induced by uncertain model inputs during its evaluation by dispersion models. Two approaches are used to model and propagate the uncertainties. The first one is the set-membership approach based on interval calculus for analytical models. The second one is the probabilistic approach (Monte Carlo), which is more classical and used more frequently when the dispersion model is described by an analytic expression or is is defined by a computer code. The objective is to compare the two approaches to define their advantages and disadvantages in terms of precision and computation time to solve the proposed problem. To determine the danger zones, two dispersion models (Gaussian and SLAB) are used to evaluate the risk intensity in the contaminated area. The risk mapping is achieved by using two methods: a probabilistic method (Monte Carlo) which consists in solving an inverse problem on the effect model and a set-membership generic method that defines the problem as a constraint satisfaction problem (CSP) and to resolve it with an set-membership inversion method. The second phase consists in establishing a general methodology to realize the risk mapping and to improve performance in terms of computation time and precision. This methodology is based on three steps: - Firstly the analysis of the used effect model. - Secondly the proposal of a new method for the uncertainty propagationbased on a mix between the probabilistic and set-membership approaches that takes advantage of both approaches and that is suited to any type of spatial and static effect model. -Finally the realization of risk mapping by inversing the effect models. The sensitivity analysis present in the first step is typically addressed to probabilistic models. The validity of using Sobol indices for interval models is discussed and a new interval sensitivity indiceis proposed
Peng, Tao. "Analyse de données loT en flux." Electronic Thesis or Diss., Aix-Marseille, 2021. http://www.theses.fr/2021AIXM0649.
Повний текст джерелаSince the advent of the IoT (Internet of Things), we have witnessed an unprecedented growth in the amount of data generated by sensors. To exploit this data, we first need to model it, and then we need to develop analytical algorithms to process it. For the imputation of missing data from a sensor f, we propose ISTM (Incremental Space-Time Model), an incremental multiple linear regression model adapted to non-stationary data streams. ISTM updates its model by selecting: 1) data from sensors located in the neighborhood of f, and 2) the near-past most recent data gathered from f. To evaluate data trustworthiness, we propose DTOM (Data Trustworthiness Online Model), a prediction model that relies on online regression ensemble methods such as AddExp (Additive Expert) and BNNRW (Bagging NNRW) for assigning a trust score in real time. DTOM consists: 1) an initialization phase, 2) an estimation phase, and 3) a heuristic update phase. Finally, we are interested predicting multiple outputs STS in presence of imbalanced data, i.e. when there are more instances in one value interval than in another. We propose MORSTS, an online regression ensemble method, with specific features: 1) the sub-models are multiple output, 2) adoption of a cost sensitive strategy i.e. the incorrectly predicted instance has a higher weight, and 3) management of over-fitting by means of k-fold cross-validation. Experimentation with with real data has been conducted and the results were compared with reknown techniques
Devers, Alexandre. "Vers une réanalyse hydrométéorologique à l'échelle de la France sur les 150 dernières années par assimilation de données dans des reconstructions ensemblistes." Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAU029.
Повний текст джерелаClimate and hydrology have a strong impact on our society, and adaptating to climate change requires a better knowledge of the historical evolution of hydrometeorological variables. In France, the low density of meteorological and hydrometric observations before the 1970s made it difficult to have a clear vision of their long-term evolution. To fill this gap, various modeling chains have recently been developed to create hydrometeorological reconstructions that are independent of the available historical observations. This thesis work combines these two sources of information - observations and reconstructions - and their respective uncertainties through data assimilation methods, in order to better understand the evolution of climate and hydrology in France from the late nineteenth century onwards.This work is based on the SCOPE Climate high-resolution reconstructions, obtained from the 20CR global reanalysis through an analogue downscaling method and covering the period 1871-2012. These reconstructions are used as a background for assimilating historical precipitation and temperature observations using an ensemble Kalman filter approach. The assimilation method applied is an offline ensemble Kalman filter, that allows taking advantages of the different sources of information without necessarily resorting to a numerical model, and leading to a low computational cost. The assimilation is carried out at both daily and annual time steps to capture the day-to-day variations and extremes as well as the multidecadal climate variability. Applying the method over the period 1871-2012 led to FYRE Climate (French hYdrometeorological Reanalysis Climate), a daily meteorological reanalysis composed of 25 members on an 8 km grid covering the whole of France.FYRE Climate is then used as forcings to a conceptual hydrological model to reconstruct streamflow time series from 1871 onwards over 661 near-natural catchments. In particular, these reconstructions take into account the uncertainties on the input and hydrometric observations during the model calibration, but also the model uncertainty through a post-processing approach. The few hydrometric observations available over the 20th century also made it possible to constrain these hydrological reconstructions using an offline deterministic Kalman filter. This approach led to the FYRE Hydro daily streamflow reanalysis, also composed of 25-member ensemble time series for each of the 661 catchments.Applying an ensemble Kalman filter at a local scale, with a daily time step and on non-Gaussian variables - such as precipitation and discharge - is particularly innovative in the context of a long-term hydroclimatic reanalysis. It required implementing an anamorphosis transformation and an anisotropic localization approach. It also required to carefully define the errors on observations, on the climate background, and on the hydrological background, but also on the hydrological modeling itself. Beyond the reduction of uncertainty induced by the integration of additional information, the multidecadal variability is well reproduced in both FYRE Climate and FYRE Hydro. These two reanalyses also allow analyzing local extreme events over the whole 20th century, thanks to the integration of in-situ meteorological and hydrometric information. Several high-quality data sets - the FYRE Climate and FYRE Hydro reanalyses, but also hydrological reconstructions with additional variables like the snow water equivalent - are made available for studying the climatic and hydrological evolution over the 1871-2012 period
Частини книг з теми "Modélisation ensembliste"
BATO, Mary Grace, Virginie PINEL, and Yajing YAN. "Assimilation de données ensembliste en volcanologie." In Inversion et assimilation de données de télédétection, 133–67. ISTE Group, 2023. http://dx.doi.org/10.51926/iste.9142.ch4.
Повний текст джерела