Search

Your search keyword '"Sparse Variational Gaussian Processes"' showing total 2 results
Start Over Descriptor "Sparse Variational Gaussian Processes" Topic earth observation (eo)
2 results on '"Sparse Variational Gaussian Processes"'

1. End-to-end Learning for Land Cover Classification using Irregular and Unaligned SITS by Combining Attention-Based Interpolation with Sparse Variational Gaussian Processes

Author

Bellet, Valentine, Fauvel, Mathieu, Inglada, Jordi, Michel, Julien, Centre d'études spatiales de la biosphère (CESBIO), Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Université de Toulouse (UT), and ANR-19-P3IA-0004,ANITI,Artificial and Natural Intelligence Toulouse Institute(2019)

Subjects
[SHS.STAT]Humanities and Social Sciences/Methods and statistics, Satellite Image Time Series SITS, [SDE.IE]Environmental Sciences/Environmental Engineering, Land Cover Map, Sparse Variational Gaussian Processes, Classification, Earth Observation (EO), Irregular Sampling, Large Scale, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Remote Sensing, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Sentinel-2, [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
Published
2023

2. Land Cover Classification with Gaussian Processes using spatio-spectro-temporal features

Author

Valentine Bellet, Mathieu Fauvel, Jordi Inglada, Centre d'études spatiales de la biosphère (CESBIO), Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Centre National d'Études Spatiales [Toulouse] (CNES), Centre National d’Etudes Spatiales (CNES), ANR-19-P3IA-0004,ANITI,Artificial and Natural Intelligence Toulouse Institute(2019), Bellet, Valentine, Artificial and Natural Intelligence Toulouse Institute - - ANITI2019 - ANR-19-P3IA-0004 - P3IA - VALID, Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), and Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National d'Études Spatiales [Toulouse] (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France -Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)

Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Satellite Image Time-Series (SITS), Land Cover Map, Land Cover Pixel-Based Classification, Sparse Variational Gaussian Processes, [MATH] Mathematics [math], Classification, Earth Observation (EO), [SDU.ENVI] Sciences of the Universe [physics]/Continental interfaces, environment, Large Scale, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Remote Sensing, Pixel-Based, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], General Earth and Planetary Sciences, Sentinel- 2, Electrical and Electronic Engineering, [MATH]Mathematics [math], [SDU.ENVI]Sciences of the Universe [physics]/Continental interfaces, environment, [MATH.MATH-ST] Mathematics [math]/Statistics [math.ST]
Abstract

In this article, we propose an approach based on Gaussian Processes (GP) for large scale land cover pixel-basedclassification with Sentinel-2 satellite image time-series (SITS). We used a sparse approximation of the posterior combined with variational inference to learn the GP’s parameters. We applied stochastic gradient descent and GPU computing to optimize our GP models on massive data sets. The proposed GP model can be trained with hundreds of thousands of samples, compared to few thousands for traditional GP methods. Moreover, we included the spatial information by adding the geographic coordinates into the GP’s covariance function to efficiently exploit the spatio-spectro-temporal structure of the SITS. We ran experiments with Sentinel-2 SITS of the full year 2018 over an area of 200 000 km 2 (about 2 billion pixels) in the south of France, which is representative of an operational setting. Adding the spatial information significantly improved the results in terms of classification accuracy. With spatial information, GP models have an overall accuracy of 79.8. They are more than three points above Random Forest (the method used for current operational systems) and more than one point above a multi-layer perceptron. Compared to a Transformer-based model (which provides state ofthe art results in the literature, but are not applied in operational systems), GP models are only one point below.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results