Sentinel-1 and Landsat-7 ETM+ feature level fusion for soil moisture content estimation
Conference: EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar
06/04/2018 - 06/07/2018 at Aachen, Germany
Proceedings: EUSAR 2018
Pages: 6Language: englishTyp: PDFPersonal VDE Members are entitled to a 10% discount on this title
Yahia, Oualid; Guida, Raffaella; Iervolino, Pasquale (University of Surrey, UK)
A novel methodology is proposed for soil moisture content (SMC) estimation using the feature level fusion of Sentinel-1 and Landsat-8 satellite datasets. This fusion consists of concatenating Temperature Vegetation Dryness Index (TVDI) to the feature vector (radar and physical features) of the inversion of the Integral Equation Model (IEM) through Artificial Neural Networks (ANN) to reduce vegetation effects on Sentinel-1 estimation. This methodology is applied on Blackwell farms, Guildford, United Kingdom, where ground truth and satellite data were collected during 2017. The preliminary SMC estimation results show lower RMSE errors (by 0.474%) and less bias than the IEM inversion method.