Soil Texture Estimation Using Radar and Optical Data from Sentinel-1 and Sentinel-2
This paper discusses the combined use of remotely sensed optical and radar data for the estimation and mapping of soil texture. The study is based on Sentinel-1 (S-1) and Sentinel-2 (S-2) data acquired between July and early December 2017, on a semi-arid area about 3000 km<sup>2</sup> in...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/11/13/1520 |
| _version_ | 1823960221710548992 |
|---|---|
| author | Safa Bousbih Mehrez Zribi Charlotte Pelletier Azza Gorrab Zohra Lili-Chabaane Nicolas Baghdadi Nadhira Ben Aissa Bernard Mougenot |
| author_facet | Safa Bousbih Mehrez Zribi Charlotte Pelletier Azza Gorrab Zohra Lili-Chabaane Nicolas Baghdadi Nadhira Ben Aissa Bernard Mougenot |
| author_sort | Safa Bousbih |
| collection | DOAJ |
| description | This paper discusses the combined use of remotely sensed optical and radar data for the estimation and mapping of soil texture. The study is based on Sentinel-1 (S-1) and Sentinel-2 (S-2) data acquired between July and early December 2017, on a semi-arid area about 3000 km<sup>2</sup> in central Tunisia. In addition to satellite acquisitions, texture measurement samples were taken in several agricultural fields, characterized by a large range of clay contents (between 13% and 60%). For the period between July and August, various optical indicators of clay content Short-Wave Infrared (SWIR) bands and soil indices) were tested over bare soils. Satellite moisture products, derived from combined S-1 and S-2 data, were also tested as an indicator of soil texture. Algorithms based on the support vector machine (SVM) and random forest (RF) methods are proposed for the classification and mapping of clay content and a three-fold cross-validation is used to evaluate both approaches. The classifications with the best performance are achieved using the soil moisture indicator derived from combined S-1 and S-2 data, with overall accuracy (OA) of 63% and 65% for the SVM and RF classifications, respectively. |
| first_indexed | 2024-12-17T16:45:12Z |
| format | Article |
| id | doaj.art-6af223906d334572869b17cc3550aa43 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-12-17T16:45:12Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6af223906d334572869b17cc3550aa432022-12-21T21:40:45ZengMDPI AGRemote Sensing2072-42922019-06-011113152010.3390/rs11131520rs11131520Soil Texture Estimation Using Radar and Optical Data from Sentinel-1 and Sentinel-2Safa Bousbih0Mehrez Zribi1Charlotte Pelletier2Azza Gorrab3Zohra Lili-Chabaane4Nicolas Baghdadi5Nadhira Ben Aissa6Bernard Mougenot7CESBIO (CNRS/UPS/IRD/CNES/INRA), 18 Avenue Edouard Belin, 31401 Toulouse CEDEX9, FranceCESBIO (CNRS/UPS/IRD/CNES/INRA), 18 Avenue Edouard Belin, 31401 Toulouse CEDEX9, FranceFaculty of Information Technology, Monash University, Melbourne, VIC 3800, AustraliaUniversité de Carthage/INAT/LR GREEN-TEAM, 43 Avenue Charles Nicolle, Tunis 1082, TunisiaUniversité de Carthage/INAT/LR GREEN-TEAM, 43 Avenue Charles Nicolle, Tunis 1082, TunisiaIRSTEA, University of Montpellier, UMR TETIS, 34093 Montpellier CEDEX 5, FranceUniversité de Carthage/INAT/LR GREEN-TEAM, 43 Avenue Charles Nicolle, Tunis 1082, TunisiaCESBIO (CNRS/UPS/IRD/CNES/INRA), 18 Avenue Edouard Belin, 31401 Toulouse CEDEX9, FranceThis paper discusses the combined use of remotely sensed optical and radar data for the estimation and mapping of soil texture. The study is based on Sentinel-1 (S-1) and Sentinel-2 (S-2) data acquired between July and early December 2017, on a semi-arid area about 3000 km<sup>2</sup> in central Tunisia. In addition to satellite acquisitions, texture measurement samples were taken in several agricultural fields, characterized by a large range of clay contents (between 13% and 60%). For the period between July and August, various optical indicators of clay content Short-Wave Infrared (SWIR) bands and soil indices) were tested over bare soils. Satellite moisture products, derived from combined S-1 and S-2 data, were also tested as an indicator of soil texture. Algorithms based on the support vector machine (SVM) and random forest (RF) methods are proposed for the classification and mapping of clay content and a three-fold cross-validation is used to evaluate both approaches. The classifications with the best performance are achieved using the soil moisture indicator derived from combined S-1 and S-2 data, with overall accuracy (OA) of 63% and 65% for the SVM and RF classifications, respectively.https://www.mdpi.com/2072-4292/11/13/1520Sentinel-1Sentinel-2Soil MoistureTextureClaySVMRandom Forest |
| spellingShingle | Safa Bousbih Mehrez Zribi Charlotte Pelletier Azza Gorrab Zohra Lili-Chabaane Nicolas Baghdadi Nadhira Ben Aissa Bernard Mougenot Soil Texture Estimation Using Radar and Optical Data from Sentinel-1 and Sentinel-2 Remote Sensing Sentinel-1 Sentinel-2 Soil Moisture Texture Clay SVM Random Forest |
| title | Soil Texture Estimation Using Radar and Optical Data from Sentinel-1 and Sentinel-2 |
| title_full | Soil Texture Estimation Using Radar and Optical Data from Sentinel-1 and Sentinel-2 |
| title_fullStr | Soil Texture Estimation Using Radar and Optical Data from Sentinel-1 and Sentinel-2 |
| title_full_unstemmed | Soil Texture Estimation Using Radar and Optical Data from Sentinel-1 and Sentinel-2 |
| title_short | Soil Texture Estimation Using Radar and Optical Data from Sentinel-1 and Sentinel-2 |
| title_sort | soil texture estimation using radar and optical data from sentinel 1 and sentinel 2 |
| topic | Sentinel-1 Sentinel-2 Soil Moisture Texture Clay SVM Random Forest |
| url | https://www.mdpi.com/2072-4292/11/13/1520 |
| work_keys_str_mv | AT safabousbih soiltextureestimationusingradarandopticaldatafromsentinel1andsentinel2 AT mehrezzribi soiltextureestimationusingradarandopticaldatafromsentinel1andsentinel2 AT charlottepelletier soiltextureestimationusingradarandopticaldatafromsentinel1andsentinel2 AT azzagorrab soiltextureestimationusingradarandopticaldatafromsentinel1andsentinel2 AT zohralilichabaane soiltextureestimationusingradarandopticaldatafromsentinel1andsentinel2 AT nicolasbaghdadi soiltextureestimationusingradarandopticaldatafromsentinel1andsentinel2 AT nadhirabenaissa soiltextureestimationusingradarandopticaldatafromsentinel1andsentinel2 AT bernardmougenot soiltextureestimationusingradarandopticaldatafromsentinel1andsentinel2 |