arXiv subjects

Claire Guilloteau

Publications and source records attributed to Claire Guilloteau.

6 recordsLinked to original sources

arXiv2026

A Latent Representation Learning Framework for Hyperspectral Image Emulation in Remote Sensing

Synthetic hyperspectral image (HSI) generation is essential for large-scale simulation, algorithm development, and mission design, yet traditional radiative transfer models remain computationally expensive and proposed emulation methods are often limited to spectrum-level outputs. In this work, we propose a latent representation-based framework for hyperspectral emulation that learns a probabilistic latent representation of hyperspectral data. The proposed approach supports both spectrum-level and spatial-spectral emulation and can be trained either in a direct one-step formulation or in a two-step strategy that couples variational autoencoder (VAE) pretraining with parameter-to-latent mapping. Experiments on PROSAIL-simulated vegetation data and Sentinel-3 OLCI imagery demonstrate that the method outperforms classical regression-based emulators in reconstruction accuracy, spectral fidelity, and robustness to real-world spatial variability. We further show that emulated HSIs preserve performance in downstream biophysical parameter retrieval, highlighting the practical relevance of emulated data for remote sensing applications.

cs.CV↗

arXiv2026

SVH-BD : Synthetic Vegetation Hyperspectral Benchmark Dataset for Emulation of Remote Sensing Images

This dataset provides a large collection of 10,915 synthetic hyperspectral image cubes paired with pixel-level vegetation trait maps, designed to support research in radiative transfer emulation, vegetation trait retrieval, and uncertainty quantification. Each hyperspectral cube contains 211 bands spanning 400--2500 nm at 10 nm resolution and a fixed spatial layout of 64 \times 64 pixels, offering continuous simulated surface reflectance spectra suitable for emulator development and machine-learning tasks requiring high spectral detail. Vegetation traits were derived by inverting Sentinel-2 Level-2A surface reflectance using a PROSAIL-based lookup-table approach, followed by forward PROSAIL simulations to generate hyperspectral reflectance under physically consistent canopy and illumination conditions. The dataset covers four ecologically diverse regions -- East Africa, Northern France, Eastern India, and Southern Spain -- and includes 5th and 95th percentile uncertainty maps as well as Sentinel-2 scene classification layers. This resource enables benchmarking of inversion methods, development of fast radiative transfer emulators, and studies of spectral--biophysical relationships under controlled yet realistic environmental variability.

cs.CV↗

arXiv2026

Fusion of JWST data: Demonstrating practical feasibility

Data fusion is a computational process widely used in Earth observation to generate high-resolution hyperspectral data cubes with two spatial and one spectral dimensions. It merges data from instruments with complementary characteristics: one with low spatial but high spectral resolutions, and another with high spatial but low spectral resolutions. In astronomy, the use of such instrumental combinations is becoming increasingly common, making data fusion a promising approach for enhancing observational data. Until now, however, its application to astronomical data has remained unsuccessful. We present the first successful astronomical data fusion using JWST integral field spectroscopy with NIRSpec and imaging across 29 filters with NIRCam. Applied to observations of the d203-506 protoplanetary disk in Orion and of Titan, our method produces fused hyperspectral cubes with NIRCam spatial and NIRSpec spectral resolutions. These results pave the way for extracting the physical properties from JWST data with unprecedented spatial resolution and showcase the transformative potential of data fusion in astronomy.

astro-ph.IM↗

arXiv2022

PDRs4All: A JWST Early Release Science Program on radiative feedback from massive stars

Massive stars disrupt their natal molecular cloud material through radiative and mechanical feedback processes. These processes have profound effects on the evolution of interstellar matter in our Galaxy and throughout the Universe, from the era of vigorous star formation at redshifts of 1-3 to the present day. The dominant feedback processes can be probed by observations of the Photo-Dissociation Regions (PDRs) where the far-ultraviolet photons of massive stars create warm regions of gas and dust in the neutral atomic and molecular gas. PDR emission provides a unique tool to study in detail the physical and chemical processes that are relevant for most of the mass in inter- and circumstellar media including diffuse clouds, proto-planetary disks and molecular cloud surfaces, globules, planetary nebulae, and star-forming regions. PDR emission dominates the infrared (IR) spectra of star-forming galaxies. Most of the Galactic and extragalactic observations obtained with the James Webb Space Telescope (JWST) will therefore arise in PDR emission. In this paper we present an Early Release Science program using the MIRI, NIRSpec, and NIRCam instruments dedicated to the observations of an emblematic and nearby PDR: the Orion Bar. These early JWST observations will provide template datasets designed to identify key PDR characteristics in JWST observations. These data will serve to benchmark PDR models and extend them into the JWST era. We also present the Science-Enabling products that we will provide to the community. These template datasets and Science-Enabling products will guide the preparation of future proposals on star-forming regions in our Galaxy and beyond and will facilitate data analysis and interpretation of forthcoming JWST observations.

astro-ph.GA↗

arXiv2020

Simulated JWST datasets for multispectral and hyperspectral image fusion

This paper aims at providing a comprehensive framework to generate an astrophysical scene and to simulate realistic hyperspectral and multispectral data acquired by two JWST instruments, namely NIRCam Imager and NIRSpec IFU. We want to show that this simulation framework can be resorted to assess the benefits of fusing these images to recover an image of high spatial and spectral resolutions. To do so, we create a synthetic scene associated with a canonical infrared source, the Orion Bar. This scene combines pre-existing modelled spectra provided by the JWST Early Release Science Program 1288 and real high resolution spatial maps from the Hubble space and ALMA telescopes. We develop forward models including corresponding noises for the two JWST instruments based on their technical designs and physical features. JWST observations are then simulated by applying the forward models to the aforementioned synthetic scene. We test a dedicated fusion algorithm we developed on these simulated observations. We show the fusion process reconstructs the high spatio-spectral resolution scene with a good accuracy on most areas, and we identify some limitations of the method to be tackled in future works. The synthetic scene and observations presented in the paper are made publicly available and can be used for instance to evaluate instrument models (aboard the JWST or on the ground), pipelines, or more sophisticated algorithms dedicated to JWST data analysis. Besides, fusion methods such as the one presented in this paper are shown to be promising tools to fully exploit the unprecedented capabilities of the JWST.

astro-ph.IM↗

arXiv2019

Hyperspectral and multispectral image fusion under spectrally varying spatial blurs -- Application to high dimensional infrared astronomical imaging

Hyperspectral imaging has become a significant source of valuable data for astronomers over the past decades. Current instrumental and observing time constraints allow direct acquisition of multispectral images, with high spatial but low spectral resolution, and hyperspectral images, with low spatial but high spectral resolution. To enhance scientific interpretation of the data, we propose a data fusion method which combines the benefits of each image to recover a high spatio-spectral resolution datacube. The proposed inverse problem accounts for the specificities of astronomical instruments, such as spectrally variant blurs. We provide a fast implementation by solving the problem in the frequency domain and in a low-dimensional subspace to efficiently handle the convolution operators as well as the high dimensionality of the data. We conduct experiments on a realistic synthetic dataset of simulated observation of the upcoming James Webb Space Telescope, and we show that our fusion algorithm outperforms state-of-the-art methods commonly used in remote sensing for Earth observation.

cs.CV↗