Mathieu Fauvel
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mathieu Fauvel has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Jordi Inglada
Univ Toulouse 3 Paul Sabatier, Univ Toulouse, CNES/IRD/CNRS/INRAe, CESBIO, Toulouse, France
3 shared publications - Nicolas Dobigeon
IRIT/INP-ENSEEIHT, University of Toulouse, Toulouse, France
3 shared publications - Stéphane May
Centre National d' Études Spatiales (CNES) Toulouse France
3 shared publications - Adrien Lagrange
University of Toulouse IRIT/INP-ENSEEIHT Toulouse BP 7122 31071 Cedex 7 Toulouse France
2 shared publications - Alexandre Constantin
Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, Grenoble, France
2 shared publications - Stéphane Girard
Univ. Grenoble Alpes Inria CNRS Grenoble INP LJK 38000 Grenoble France
2 shared publications
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23, 1
Whittaker smoother for long satellite image time series interpolation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23, 1
Whittaker smoother for long satellite image time series interpolation
- Open Access
- 31 October 2024
- Published by Elsevier in Remote Sensing of Environment
- Vol. 315
Nationwide operational mapping of grassland first mowing dates combining machine learning and Sentinel-2 time series
- 31 October 2024
- Published by Elsevier in Remote Sensing of Environment
- Vol. 315
Open AccessNationwide operational mapping of grassland first mowing dates combining machine learning and Sentinel-2 time series
- Open Access
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 2980-2994
End-to-End Learning for Land Cover Classification Using Irregular and Unaligned SITS by Combining Attention-Based Interpolation With Sparse Variational Gaussian Processes
In this article, we propose a method exploiting irregular and unaligned Sentinel-2 satellite image time series (SITS) for large-scale land cover pixel-based classification. We perform end-to-end learning by combining a time and space informed kernel interpolator with a Sparse Variational Gaussian Processes (SVGP) classifier. The interpolator embeds irregular and unaligned SITS onto a fixed and reduced size latent representation. The spatial information is taken into account by using a spatial positional encoding . The obtained latent representation is given to the SVGP classifier and all the parameters are jointly optimized w.r.t. the classification task. We run experiments with irregular and unaligned Sentinel-2 SITS of the full year 2018 over an area of 200 000 $\rm{km}^{2}$ (about two billion pixels) in the south of France (27 MGRS tiles). Such experimental condition exacerbates the irregular and unaligned issues of SITS. In terms of overall accuracy, with the learned latent representation instead of linearly interpolated SITS, the results of the SVGP classifier are improved by about 10 points. Moreover, with the learned latent representation, the SVGP classifier outperforms the main state-of-the-art methods from the literature at large scale (e.g., seven points for the Multi-layer Perceptron) and is robust to the available timestamps used for training and testing.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 2980-2994
Open AccessEnd-to-End Learning for Land Cover Classification Using Irregular and Unaligned SITS by Combining Attention-Based Interpolation With Sparse Variational Gaussian Processes
In this article, we propose a method exploiting irregular and unaligned Sentinel-2 satellite image time series (SITS) for large-scale land cover pixel-based classification. We perform end-to-end learning by combining a time and space informed kernel interpolator with a Sparse Variational Gaussian Processes (SVGP) classifier. The interpolator embeds irregular and unaligned SITS onto a fixed and reduced size latent representation. The spatial information is taken into account by using a spatial positional encoding . The obtained latent representation is given to the SVGP classifier and all the parameters are jointly optimized w.r.t. the classification task. We run experiments with irregular and unaligned Sentinel-2 SITS of the full year 2018 over an area of 200 000 $\rm{km}^{2}$ (about two billion pixels) in the south of France (27 MGRS tiles). Such experimental condition exacerbates the irregular and unaligned issues of SITS. In terms of overall accuracy, with the learned latent representation instead of linearly interpolated SITS, the results of the SVGP classifier are improved by about 10 points. Moreover, with the learned latent representation, the SVGP classifier outperforms the main state-of-the-art methods from the literature at large scale (e.g., seven points for the Multi-layer Perceptron) and is robust to the available timestamps used for training and testing.
- Open Access
End-to-end Learning for Land Cover Classification using Irregular and Unaligned SITS by Combining Attention-Based Interpolation with Sparse Variational Gaussian Processes
Are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
Open AccessEnd-to-end Learning for Land Cover Classification using Irregular and Unaligned SITS by Combining Attention-Based Interpolation with Sparse Variational Gaussian Processes
Are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.
- 5 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-21
Land Cover Classification With Gaussian Processes Using Spatio-Spectro-Temporal Features
In this article, we propose an approach based on Gaussian Processes (GP) for large scale land cover pixel-based classification 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 of the art results in the literature, but are not applied in operational systems), GP models are only one point below.
- 5 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-21
Land Cover Classification With Gaussian Processes Using Spatio-Spectro-Temporal Features
In this article, we propose an approach based on Gaussian Processes (GP) for large scale land cover pixel-based classification 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 of the art results in the literature, but are not applied in operational systems), GP models are only one point below.
- 19 September 2022
- Published by Springer Nature in Statistics and Computing
- Vol. 32 (5) , 1-20
Mixture of multivariate Gaussian processes for classification of irregularly sampled satellite image time-series
- 19 September 2022
- Published by Springer Nature in Statistics and Computing
- Vol. 32 (5) , 1-20
Mixture of multivariate Gaussian processes for classification of irregularly sampled satellite image time-series
- Open Access
- 26 October 2021
- Published by Elsevier in Pattern Recognition Letters
- Vol. 152, 320-326
Fast estimation for robust supervised classification with mixture models
- 26 October 2021
- Published by Elsevier in Pattern Recognition Letters
- Vol. 152, 320-326
Open AccessFast estimation for robust supervised classification with mixture models
- 11 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-13
Joint Supervised Classification and Reconstruction of Irregularly Sampled Satellite Image Times Series
Recent satellite missions have led to a huge amount of Earth observation data, most of them being freely available. In such a context, satellite image time series have been used to study land use and land cover information. However, optical time series, such as Sentinel-2 or Landsat ones, are provided with an irregular time sampling for different spatial locations, and images may contain clouds and shadows. Thus, preprocessing techniques are usually required to properly classify such data. The proposed approach is able to deal with irregular temporal sampling and missing data directly in the classification process. It is based on Gaussian processes and allows to perform jointly the classification of the pixel labels as well as the reconstruction of the pixel time series. The method complexity scales linearly with the number of pixels, making it amenable in large-scale scenarios. Experimental classification and reconstruction results show that the method does not compete yet with state-of-the-art classifiers but yields reconstructions that are robust with respect to the presence of undetected clouds or shadows and does not require any temporal preprocessing.
- 11 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-13
Joint Supervised Classification and Reconstruction of Irregularly Sampled Satellite Image Times Series
Recent satellite missions have led to a huge amount of Earth observation data, most of them being freely available. In such a context, satellite image time series have been used to study land use and land cover information. However, optical time series, such as Sentinel-2 or Landsat ones, are provided with an irregular time sampling for different spatial locations, and images may contain clouds and shadows. Thus, preprocessing techniques are usually required to properly classify such data. The proposed approach is able to deal with irregular temporal sampling and missing data directly in the classification process. It is based on Gaussian processes and allows to perform jointly the classification of the pixel labels as well as the reconstruction of the pixel time series. The method complexity scales linearly with the number of pixels, making it amenable in large-scale scenarios. Experimental classification and reconstruction results show that the method does not compete yet with state-of-the-art classifiers but yields reconstructions that are robust with respect to the presence of undetected clouds or shadows and does not require any temporal preprocessing.
- Open Access
- 20 July 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (14) , 2326
Hierarchical Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing with Spectral Variability
Accounting for endmember variability is a challenging issue when unmixing hyperspectral data. This paper models the variability that is associated with each endmember as a conical hull defined by extremal pixels from the data set. These extremal pixels are considered as so-called prototypal endmember spectra that have meaningful physical interpretation. Capitalizing on this data-driven modeling, the pixels of the hyperspectral image are then described as combinations of these prototypal endmember spectra weighted by bundling coefficients and spatial abundances. The proposed unmixing model not only extracts and clusters the prototypal endmember spectra, but also estimates the abundances of each endmember. The performance of the approach is illustrated thanks to experiments conducted on simulated and real hyperspectral data and it outperforms state-of-the-art methods.
- 20 July 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (14) , 2326
Open AccessHierarchical Sparse Nonnegative Matrix Factorization for Hyperspectral Unmixing with Spectral Variability
Accounting for endmember variability is a challenging issue when unmixing hyperspectral data. This paper models the variability that is associated with each endmember as a conical hull defined by extremal pixels from the data set. These extremal pixels are considered as so-called prototypal endmember spectra that have meaningful physical interpretation. Capitalizing on this data-driven modeling, the pixels of the hyperspectral image are then described as combinations of these prototypal endmember spectra weighted by bundling coefficients and spatial abundances. The proposed unmixing model not only extracts and clusters the prototypal endmember spectra, but also estimates the abundances of each endmember. The performance of the approach is illustrated thanks to experiments conducted on simulated and real hyperspectral data and it outperforms state-of-the-art methods.
- Open Access
Matrix cofactorization for joint spatial-spectral unmixing of hyperspectral images
Hyperspectral unmixing aims at identifying a set of elementary spectra and the corresponding mixture coefficients for each pixel of an image. As the elementary spectra correspond to the reflectance spectra of real materials, they are often very correlated yielding an ill-conditioned problem. To enrich the model and to reduce ambiguity due to the high correlation, it is common to introduce spatial information to complement the spectral information. The most common way to introduce spatial information is to rely on a spatial regularization of the abundance maps. In this paper, instead of considering a simple but limited regularization process, spatial information is directly incorporated through the newly proposed context of spatial unmixing. Contextual features are extracted for each pixel and this additional set of observations is decomposed according to a linear model. Finally the spatial and spectral observations are unmixed jointly through a cofactorization model. In particular, this model introduces a coupling term used to identify clusters of shared spatial and spectral signatures. An evaluation of the proposed method is conducted on synthetic and real data and shows that results are accurate and also very meaningful since they describe both spatially and spectrally the various areas of the scene.
Open AccessMatrix cofactorization for joint spatial-spectral unmixing of hyperspectral images
Hyperspectral unmixing aims at identifying a set of elementary spectra and the corresponding mixture coefficients for each pixel of an image. As the elementary spectra correspond to the reflectance spectra of real materials, they are often very correlated yielding an ill-conditioned problem. To enrich the model and to reduce ambiguity due to the high correlation, it is common to introduce spatial information to complement the spectral information. The most common way to introduce spatial information is to rely on a spatial regularization of the abundance maps. In this paper, instead of considering a simple but limited regularization process, spatial information is directly incorporated through the newly proposed context of spatial unmixing. Contextual features are extracted for each pixel and this additional set of observations is decomposed according to a linear model. Finally the spatial and spectral observations are unmixed jointly through a cofactorization model. In particular, this model introduces a coupling term used to identify clusters of shared spatial and spectral signatures. An evaluation of the proposed method is conducted on synthetic and real data and shows that results are accurate and also very meaningful since they describe both spatially and spectrally the various areas of the scene.