Hybrid Methodology Using Sentinel-1/Sentinel-2 for Soil Moisture Estimation
Soil moisture is an essential parameter for a better understanding of water processes in the soil–vegetation–atmosphere continuum. Satellite synthetic aperture radar (SAR) is well suited for monitoring water content at fine spatial resolutions on the order of 1 km or higher. Several methodologies ar...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-05-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/14/10/2434 |
_version_ | 1797495907337371648 |
---|---|
author | Simon Nativel Emna Ayari Nemesio Rodriguez-Fernandez Nicolas Baghdadi Remi Madelon Clement Albergel Mehrez Zribi |
author_facet | Simon Nativel Emna Ayari Nemesio Rodriguez-Fernandez Nicolas Baghdadi Remi Madelon Clement Albergel Mehrez Zribi |
author_sort | Simon Nativel |
collection | DOAJ |
description | Soil moisture is an essential parameter for a better understanding of water processes in the soil–vegetation–atmosphere continuum. Satellite synthetic aperture radar (SAR) is well suited for monitoring water content at fine spatial resolutions on the order of 1 km or higher. Several methodologies are often considered in the inversion of SAR signals: machine learning techniques, such as neural networks, empirical models and change detection methods. In this study, we propose two hybrid methodologies by improving a change detection approach with vegetation consideration or by combining a change detection approach together with a neural network algorithm. The methodology is based on Sentinel-1 and Sentinel-2 data with the use of numerous metrics, including vertical–vertical (VV) and vertical–horizontal (VH) polarization radar signals, the classical change detection surface soil moisture (SSM) index <inline-formula><math display="inline"><semantics><mrow><msub><mi>I</mi><mrow><mi mathvariant="italic">SSM</mi></mrow></msub></mrow></semantics></math></inline-formula>, radar incidence angle, normalized difference vegetation index (<i>NDVI</i>) optical index, and the VH/VV ratio. Those approaches are tested using in situ data from the ISMN (International Soil Moisture Network) with observations covering different climatic contexts. The results show an improvement in soil moisture estimations using the hybrid algorithms, in particular the change detection with the neural network one, for which the correlation increases by 54% and 33% with respect to that of the neural network or change detection alone, respectively. |
first_indexed | 2024-03-10T01:56:19Z |
format | Article |
id | doaj.art-c226e117e3dc4d5fac7719db3ef49d55 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T01:56:19Z |
publishDate | 2022-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-c226e117e3dc4d5fac7719db3ef49d552023-11-23T12:56:14ZengMDPI AGRemote Sensing2072-42922022-05-011410243410.3390/rs14102434Hybrid Methodology Using Sentinel-1/Sentinel-2 for Soil Moisture EstimationSimon Nativel0Emna Ayari1Nemesio Rodriguez-Fernandez2Nicolas Baghdadi3Remi Madelon4Clement Albergel5Mehrez Zribi6CESBIO, CNES/CNRS/INRAE/IRD/UPS, Université de Toulouse, 18 Av. Edouard Belin, Bpi 2801, CEDEX 9, 31401 Toulouse, FranceCESBIO, CNES/CNRS/INRAE/IRD/UPS, Université de Toulouse, 18 Av. Edouard Belin, Bpi 2801, CEDEX 9, 31401 Toulouse, FranceCESBIO, CNES/CNRS/INRAE/IRD/UPS, Université de Toulouse, 18 Av. Edouard Belin, Bpi 2801, CEDEX 9, 31401 Toulouse, FranceCIRAD, CNRS, INRAE, TETIS, University of Montpellier, AgroParisTech, CEDEX 5, 34093 Montpellier, FranceCESBIO, CNES/CNRS/INRAE/IRD/UPS, Université de Toulouse, 18 Av. Edouard Belin, Bpi 2801, CEDEX 9, 31401 Toulouse, FranceEuropean Space Agency Climate Office, ECSAT, Harwell Campus, Oxforshire, Didcot OX11 0FD, UKCESBIO, CNES/CNRS/INRAE/IRD/UPS, Université de Toulouse, 18 Av. Edouard Belin, Bpi 2801, CEDEX 9, 31401 Toulouse, FranceSoil moisture is an essential parameter for a better understanding of water processes in the soil–vegetation–atmosphere continuum. Satellite synthetic aperture radar (SAR) is well suited for monitoring water content at fine spatial resolutions on the order of 1 km or higher. Several methodologies are often considered in the inversion of SAR signals: machine learning techniques, such as neural networks, empirical models and change detection methods. In this study, we propose two hybrid methodologies by improving a change detection approach with vegetation consideration or by combining a change detection approach together with a neural network algorithm. The methodology is based on Sentinel-1 and Sentinel-2 data with the use of numerous metrics, including vertical–vertical (VV) and vertical–horizontal (VH) polarization radar signals, the classical change detection surface soil moisture (SSM) index <inline-formula><math display="inline"><semantics><mrow><msub><mi>I</mi><mrow><mi mathvariant="italic">SSM</mi></mrow></msub></mrow></semantics></math></inline-formula>, radar incidence angle, normalized difference vegetation index (<i>NDVI</i>) optical index, and the VH/VV ratio. Those approaches are tested using in situ data from the ISMN (International Soil Moisture Network) with observations covering different climatic contexts. The results show an improvement in soil moisture estimations using the hybrid algorithms, in particular the change detection with the neural network one, for which the correlation increases by 54% and 33% with respect to that of the neural network or change detection alone, respectively.https://www.mdpi.com/2072-4292/14/10/2434soil moistureSentinel-1Sentinel-2change detectionartificial neural network |
spellingShingle | Simon Nativel Emna Ayari Nemesio Rodriguez-Fernandez Nicolas Baghdadi Remi Madelon Clement Albergel Mehrez Zribi Hybrid Methodology Using Sentinel-1/Sentinel-2 for Soil Moisture Estimation Remote Sensing soil moisture Sentinel-1 Sentinel-2 change detection artificial neural network |
title | Hybrid Methodology Using Sentinel-1/Sentinel-2 for Soil Moisture Estimation |
title_full | Hybrid Methodology Using Sentinel-1/Sentinel-2 for Soil Moisture Estimation |
title_fullStr | Hybrid Methodology Using Sentinel-1/Sentinel-2 for Soil Moisture Estimation |
title_full_unstemmed | Hybrid Methodology Using Sentinel-1/Sentinel-2 for Soil Moisture Estimation |
title_short | Hybrid Methodology Using Sentinel-1/Sentinel-2 for Soil Moisture Estimation |
title_sort | hybrid methodology using sentinel 1 sentinel 2 for soil moisture estimation |
topic | soil moisture Sentinel-1 Sentinel-2 change detection artificial neural network |
url | https://www.mdpi.com/2072-4292/14/10/2434 |
work_keys_str_mv | AT simonnativel hybridmethodologyusingsentinel1sentinel2forsoilmoistureestimation AT emnaayari hybridmethodologyusingsentinel1sentinel2forsoilmoistureestimation AT nemesiorodriguezfernandez hybridmethodologyusingsentinel1sentinel2forsoilmoistureestimation AT nicolasbaghdadi hybridmethodologyusingsentinel1sentinel2forsoilmoistureestimation AT remimadelon hybridmethodologyusingsentinel1sentinel2forsoilmoistureestimation AT clementalbergel hybridmethodologyusingsentinel1sentinel2forsoilmoistureestimation AT mehrezzribi hybridmethodologyusingsentinel1sentinel2forsoilmoistureestimation |