Sentinel-1 Backscatter Assimilation Using Support Vector Regression or the Water Cloud Model at European Soil Moisture Sites

Dominik Rains; Hans Lievens; Gabrielle J. M. De Lannoy; Matthew McCabe; Richard A. M. de Jeu; Diego G. Miralles

doi:10.1109/lgrs.2021.3073484

Sentinel-1 Backscatter Assimilation Using Support Vector Regression or the Water Cloud Model at European Soil Moisture Sites

Dominik Rains, Hans Lievens, Gabrielle J. M. De Lannoy, Matthew McCabe, Richard A. M. de Jeu, Diego G. Miralles

Research output: Contribution to journal › Article › peer-review

15 Scopus citations

Abstract

Sentinel-1 backscatter observations were assimilated into the Global Land Evaporation Amsterdam Model (GLEAM) using an ensemble Kalman filter. As a forward operator, which is required to simulate backscatter from soil moisture and leaf area index (LAI), we evaluated both the traditional water cloud model (WCM) and the support vector regression (SVR). With SVR, a closer fit between backscatter observations and simulations was achieved. The impact on the correlation between modeled and in situ soil moisture measurements was similar when assimilating the Sentinel data using WCM (Δ R = +0.037) or SVR (Δ R = +0.025).

Original language	English (US)
Pages (from-to)	1-5
Number of pages	5
Journal	IEEE Geoscience and Remote Sensing Letters
DOIs	https://doi.org/10.1109/lgrs.2021.3073484
State	Published - 2021

ASJC Scopus subject areas

Geotechnical Engineering and Engineering Geology
Electrical and Electronic Engineering

Access to Document

10.1109/lgrs.2021.3073484

https://repository.kaust.edu.sa/bitstream/10754/669672/1/09451176.pdf

Cite this

@article{68fd9bc072b6457bab74c89cddf7dbd1,

title = "Sentinel-1 Backscatter Assimilation Using Support Vector Regression or the Water Cloud Model at European Soil Moisture Sites",

abstract = "Sentinel-1 backscatter observations were assimilated into the Global Land Evaporation Amsterdam Model (GLEAM) using an ensemble Kalman filter. As a forward operator, which is required to simulate backscatter from soil moisture and leaf area index (LAI), we evaluated both the traditional water cloud model (WCM) and the support vector regression (SVR). With SVR, a closer fit between backscatter observations and simulations was achieved. The impact on the correlation between modeled and in situ soil moisture measurements was similar when assimilating the Sentinel data using WCM (Δ R = +0.037) or SVR (Δ R = +0.025).",

author = "Dominik Rains and Hans Lievens and {De Lannoy}, {Gabrielle J. M.} and Matthew McCabe and {de Jeu}, {Richard A. M.} and Miralles, {Diego G.}",

note = "KAUST Repository Item: Exported on 2021-06-17 Acknowledgements: This work was supported by the Belgian Science Policy Office as part of the ET-Sense project within the STEREO III programme (contract SR/02/377).",

year = "2021",

doi = "10.1109/lgrs.2021.3073484",

language = "English (US)",

pages = "1--5",

journal = "IEEE Geoscience and Remote Sensing Letters",

issn = "1545-598X",

publisher = "Institute of Electrical and Electronics Engineers",

}

TY - JOUR

T1 - Sentinel-1 Backscatter Assimilation Using Support Vector Regression or the Water Cloud Model at European Soil Moisture Sites

AU - Rains, Dominik

AU - Lievens, Hans

AU - De Lannoy, Gabrielle J. M.

AU - McCabe, Matthew

AU - de Jeu, Richard A. M.

AU - Miralles, Diego G.

N1 - KAUST Repository Item: Exported on 2021-06-17 Acknowledgements: This work was supported by the Belgian Science Policy Office as part of the ET-Sense project within the STEREO III programme (contract SR/02/377).

PY - 2021

Y1 - 2021

N2 - Sentinel-1 backscatter observations were assimilated into the Global Land Evaporation Amsterdam Model (GLEAM) using an ensemble Kalman filter. As a forward operator, which is required to simulate backscatter from soil moisture and leaf area index (LAI), we evaluated both the traditional water cloud model (WCM) and the support vector regression (SVR). With SVR, a closer fit between backscatter observations and simulations was achieved. The impact on the correlation between modeled and in situ soil moisture measurements was similar when assimilating the Sentinel data using WCM (Δ R = +0.037) or SVR (Δ R = +0.025).

AB - Sentinel-1 backscatter observations were assimilated into the Global Land Evaporation Amsterdam Model (GLEAM) using an ensemble Kalman filter. As a forward operator, which is required to simulate backscatter from soil moisture and leaf area index (LAI), we evaluated both the traditional water cloud model (WCM) and the support vector regression (SVR). With SVR, a closer fit between backscatter observations and simulations was achieved. The impact on the correlation between modeled and in situ soil moisture measurements was similar when assimilating the Sentinel data using WCM (Δ R = +0.037) or SVR (Δ R = +0.025).

UR - http://hdl.handle.net/10754/669672

UR - https://ieeexplore.ieee.org/document/9451176/

U2 - 10.1109/lgrs.2021.3073484

DO - 10.1109/lgrs.2021.3073484

M3 - Article

SN - 1545-598X

SP - 1

EP - 5

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

ER -

Sentinel-1 Backscatter Assimilation Using Support Vector Regression or the Water Cloud Model at European Soil Moisture Sites

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this