Dynamic monitoring of surface soil moisture fluctuations using synthetic aperture radar and data-driven algorithms

Abstract

The primary goal of the study is to employ Synthetic Aperture Radar (SAR) data and efficacy data driven approaches in modeling Surface Soil Moisture (SSM) of cultivable marginal bare fields. Three experimental test fields were selected which are basically cultivable but due water deficiency the fields are left bare. Samples for surface soil moisture, soil surface roughness and bulk density are collected from test fields in grid sampling manner in parallel with SAR data pass over study area. Sentinel-1 A data is pre-processed and each field sampling grid backscattering energy values are obtained. Surface roughness, dielectric constant and backscattered energy were used as input features to model SSM using Random Forest Regression (RFR), Support Vector Regression (SVR) and Back Propagation Artificial Neural Network (BPANN).We observed that BPANN outperformed SVR and RF by accurately predicting soil moisture with RMSE = 0.077 m³m⁻³, bias = 0.013m³m⁻³, and R = 0.94.This study sheds light on small scale agricultural lands which are deficient of water to support crop growth.