Computation of Soil Moisture using Passive Microwave Remote Sensing An ANN Approach

n empirical model incorporating the effects of vegetation and surface roughness has been proposed which uses the least square fit of a third order polynomial using real time data. Further an Artificial Neural Network (ANN) architecture has been developed using back propagation algorithm to train the neural network which predicts coefficients of the model for a given radiometer data. The accuracy of the proposed model and the performance of the ANN architecture have been ascertained by comparing the results with the in-situ measured values of soil moisture.