Vibolroth Sambath

Vibolroth Sambath

Auto-generated profile, based on publicly available information

Vibolroth Sambath

Laboratoire Atmosphres, Milieux et Observations Spatiales (LATMOS), Universit de Versailles-Saint Quentin-en-Yvelines Paris-Saclay, Guyancourt, France

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 July 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Open access
NVNicolas Viltard
Nicolas Viltard
VSVibolroth Sambath
Vibolroth Sambath
PLPierre Lepetit
Pierre Lepetit
AMAudrey Martini
Audrey Martini
LBLaurent Barthès
Laurent Barthès
CMCécile Mallet
Cécile Mallet
Retrieval of rain from Passive Microwave radiometers data has been a challenge ever since the launch of the first Defense Meteorological Satellite Program in the late 1980s. Enormous progress has been made since the launch of the Tropical Rainfall Measuring Mission (TRMM) in 1997 but until recently the data were processed pixel-by-pixel or taking a few neighboring pixels into account. Deep learning has obtained remarkable improvement in the computer vision field, and offers a whole new way to tackle the rain retrieval problem. The Global Precipitation Measurement (GPM) Core satellite carries similarly to TRMM, a passive microwave radiometer and a radar that share part of their swath. The brightness temperatures measured in the 37 and 89 GHz channels are used like the RGB components of a regular image while rain rate from Dual Frequency radar provides the surface rain. A U-net is then trained on these data to develop a retrieval algorithm: Deep-learning RAIN (DRAIN). Using only the brightness temperatures from four channels as input and no other a priori information, DRAIN is offering similar or slightly better performances than GPROF, the GPM official algorithm, in most situations. These performances are assumed to be due to the fact that DRAIN works on an image basis instead of the classical pixel-by-pixel basis.

6 December 2022 in Environmental Data Science
Verified
Journal Article
Open access
PDF file
VSVibolroth Sambath
Vibolroth Sambath
NVNicolas Viltard
Nicolas Viltard
LBLaurent Barthès
Laurent Barthès
AMAudrey Martini
Audrey Martini
CMCécile Mallet
Cécile Mallet
Artificial intelligence has provided many breakthroughs in the field of computer vision. The fully convolutional networks U-Net in particular have provided very promising results in the problem of retrieving rain rates from space-borne observations, a challenge that has persisted over the past few decades. The rain intensity is estimated from the measurement of the brightness temperatures on different microwave channels. However, these channels are slightly different depending on the satellite. In the case where a retrieval model has been developed from a single satellite, it may be advantageous to use domain adaptation methods in order to make this model compatible with all the satellites of the constellation. In this proposed feasibility study, a Cycle Generative Adversarial Nets model is used for adapting one set of brightness temperature channels to another set. Results of a toy experiment show that this method is able to provide qualitatively good precipitation structure but still could be improved in terms of precision.

20 May 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
VSVibolroth Sambath
Vibolroth Sambath
NDNatanaël Dubois-Quilici
Natanaël Dubois-Quilici
NVNicolas Viltard
Nicolas Viltard
AMAudrey Martini
Audrey Martini
CMCécile Mallet
Cécile Mallet
A major issue limiting the successful deployment of deep-learning algorithms in geophysical applications is their inability to generalize to new contexts. Regarding the quantitative precipitation estimation (QPE) from the Global Precipitation Measurement (GPM) satellite constellation, the GPM microwave imager (GMI) contains enough co-located brightness temperatures (TBs) and rain rates data to train a deep-learning inverse model to retrieve precipitation intensity. However, the difference in instrumental configurations makes it impossible to directly apply this inverse operator to another space-borne radiometric imager. A domain adaptation is thus necessary to solve the domain shift problem encountered when applying the model trained on one satellite to another satellite. The present article tests a method to map the SSMI/S data to the GMI data. In the absence of sufficient paired images between the two satellites, we applied a Cycle Consistent Generative Adversarial Network (CycleGAN), which allows for an Unsupervised Domain Adaptation approach. Evaluating the quality of adapted images is a complex problem. This article employs two tactics: a brief evaluation of adapted radiometric images and a qualitative/quantitative evaluation of rain retrieval. Over several case studies, the results show that the domain adaptation step produces adapted SSMI/S images that retain the majority of the rain structure. Next, the rain detection score and intensity bias are then compared using 847 overpasses. The same analysis is carried out over mainland France by comparing the results with rainfall products supplied by Météo-France. In both comparisons, the adapted images allow the inverse operator to provide a better score in rain detection and intensity.

15 May 2023
Verified
Conference Paper
Open access
VSVibolroth Sambath
Vibolroth Sambath
NVNicolas Viltard
Nicolas Viltard
LBLaurent Barthès
Laurent Barthès
AMAudrey Martini
Audrey Martini
CMCécile Mallet
Cécile Mallet
Due to climate change, understanding the changes in the water cycle has become a pressing issue. It is increasingly important to study prolonged periods of intense precipitation or dry spells to better manage water supply, infrastructure and agriculture. However, obtaining fine-scale precipitation data is challenging due to the intermittent nature of rain in time and space. Ground-based instruments could have mismatches between different regions due to spatial distribution, calibration, and complex topography. On the other hand, space-borne observations have uncertainties in their retrieval algorithms. This study proposes to deal directly with microwave images from space remote sensing, as this type of data makes it possible to study the evolution of the atmospheric water cycle on a global scale and with a temporal coverage of several decades by avoiding the uncertainties from retrieval methods. In recent years, convolutional neural networks have shown promising capabilities in identifying cyclones and weather fronts in large labelled climate datasets. However, these models required large labelled datasets for training and testing. The present study aims to test unsupervised segmentation approaches of microwave images, which are thus segmented into different classes. Instead of focusing only on one aspect, for example, precipitation, the obtained classes contain many physical properties. This is due to the fact that microwave brightness temperatures contain essential information relative to the atmospheric water cycle that can be used to derive many products such as rain intensity, water vapour, cloud fraction, and sea surface temperature. The unsupervised segmentation model consists of blocks of fully convolutional networks serving as feature extractors. Without labels, pseudo-targets from the feature extractors are used to train the model. The performance of the model in terms of intra-class and inter-class distances is compared with those of simpler models such as Kmeans. A major challenge in the unsupervised approach is validating and interpreting the resulting classes. Most of the obtained cluster patterns provide geographically coherent regions whose mode of variability of geophysical quantities can be highlighted. The presented study will then explore how the different classes computed by the unsupervised methods can be labelled and how the properties of the said classes change through time and space.

8 April 2026
Verified
Thesis
Closed access
VSVibolroth Sambath
Vibolroth Sambath
Apprentissage profond non-supervisé pour l’analyse de séries chronologiques d’observations spatiales : Application aux données GPM: Le cycle de l'eau joue un rôle essentiel pour toute vie sur Terre. L'observation et la quantification de ses divers composants sous la pression du changement climatique sont devenues de plus en plus importantes pour la société et la science. Les réponses de chaque composante du cycle de l'eau au réchauffement climatique diffèrent fortement d'une région à l'autre. Par exemple, certaines régions ont connu une augmentation des précipitations, tandis que d'autres ont connu une diminution. Il est donc nécessaire d'observer le cycle de l'eau à l'échelle globale. La télédétection a accumulé une grande quantité de données d'observation spatiale. Concernant les précipitations, la mission Global Precipitation Measurement (GPM) (2014-présent) offre une constellation de satellites équipés de radiomètres micro-ondes, ce qui permet d'obtenir une vaste base de données de température de brillance (TB). Les TB contiennent des informations implicites sur plusieurs variables géophysiques importantes, notamment l'intensité de la pluie, la vapeur d'eau, la température de surface de la mer (SST), la neige et le contenu en eau liquide et glacé dans les nuages. Notre présente étude utilise le radiomètre (GMI) du GPM Core Observatory, qui est le satellite de référence pour unifier les satellites de la constellation. En considérant les mesures de TB comme des images non conventionnelles, nous proposons une nouvelle méthode pour observer le cycle de l'eau à partir de ces mesures. La segmentation sémantique non-supervisée est appliquée aux données GMI pour extraire des informations sans l'aide d'une annotation ou de données auxiliaires. L'avantage d'une telle approche est qu'elle peut être appliquée à n'importe quel radiomètre de la constellation. Elle est également exempte des incertitudes liées aux données auxiliaires. Des modèles de segmentation non-supervisés de différentes complexité sont explorés. Nous avons testé des approches qui s'appuient sur des réseaux entièrement convolutifs (FCN) pour extraire des cartes de caractéristiques à partir de l'entrée. Dans cette optique, nous avons utilisé dans un premier temps un modèle FCN relativement simple composé de quelques couches de convolution 2D. Dans un second temps, afin d'augmenter la complexité du module d'extraction de caractéristiques, nous l'avons remplacé par un réseau de type U-Net. Un modèle FCN basé sur une architecture de type auto encodeur avec un mécanisme d'attention a également été développé. Enfin, une approche par pixel de type k-moyenne a été testée. Pour comparer les performances de ces différents modèles, nous proposons une évaluation externe où les variables géophysiques pertinentes sont utilisées pour le calcul des métriques de segmentation. D'abord, les classes sont attribuées aux variables géophysiques. Ensuite, en convertissant ces variables quantitatives (précipitation et SST) en catégories, elles peuvent être comparées à la segmentation à l'aide de déférentes métriques. Dans l'apprentissage non-supervisé, il est essentiel que chaque classe obtenue représente une variable géophysique ainsi que ses caractéristiques. Les classes de pluie identifiées montrent la variabilité intra-annuelles des précipitations régionales. La segmentation préserve également les structures de précipitations telles que les cyclones. À plus grande échelle, les classes de pluie montrent les zones de convergence intertropicale (ITCZ), tandis que les classes sur les océans peuvent représenter la saisonnalité de la SST. Ces résultats montrent que la segmentation non-supervisée est un outil potentiel pour extraire des informations sur le cycle de l'eau à partir des bases de données d'observation spatiales. Ainsi, l'évolution des classes de segmentation, sur des données multi-décennales, pourrait contenir des informations importantes sur les modifications du cycle de l'eau.