Abstract
A novel methodology is proposed for soil moisture content (SMC) estimation using the feature level fusion of Senti-nel-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 dur-ing 2017. The preliminary SMC estimation results show lower RMSE errors (by 0.474%) and less bias than the IEM inversion method.