{"title":"Quantification of soil moisture variability over agriculture fields using Sentinel imagery","authors":"H. Benbrahim, A. Merzouki, K. Minaoui","doi":"10.1109/ISCV49265.2020.9204120","DOIUrl":null,"url":null,"abstract":"The purpose of this study is to quantify soil moisture variability in agriculture fields at field scale resolution using the Sentinel data (Sentinel-1 and Sentinel-2) based on a change detection technique. For calibration and validation of our model, ground measurements at 40 sampling sites in southern Manitoba, Canada, were carried out during the field campaign of SMAP Validation Experiment 2016 in Manitoba (SMAPVEX16-MB). The developed method is based on modelling soil moisture change by combining the difference in backscattered signal with that of NDVI observed on two consecutive acquisition days. This approach makes the assumption that the change in Normalized Difference Vegetation Index (NDVI) could better represent the attenuation of the backscattered signal resulting from the vegetation. Our model was evaluated over mature crop fields (canola, soybeans, wheat, corn and oats) using ground measurements and the agreement between satellite estimates and ground measurements was found satisfactory (RMSE lower than 0.093 m3/m3).","PeriodicalId":313743,"journal":{"name":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 International Conference on Intelligent Systems and Computer Vision (ISCV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCV49265.2020.9204120","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
The purpose of this study is to quantify soil moisture variability in agriculture fields at field scale resolution using the Sentinel data (Sentinel-1 and Sentinel-2) based on a change detection technique. For calibration and validation of our model, ground measurements at 40 sampling sites in southern Manitoba, Canada, were carried out during the field campaign of SMAP Validation Experiment 2016 in Manitoba (SMAPVEX16-MB). The developed method is based on modelling soil moisture change by combining the difference in backscattered signal with that of NDVI observed on two consecutive acquisition days. This approach makes the assumption that the change in Normalized Difference Vegetation Index (NDVI) could better represent the attenuation of the backscattered signal resulting from the vegetation. Our model was evaluated over mature crop fields (canola, soybeans, wheat, corn and oats) using ground measurements and the agreement between satellite estimates and ground measurements was found satisfactory (RMSE lower than 0.093 m3/m3).