Soil-Moisture Estimation Based on Multiple-Source Remote-Sensing Images

Soil moisture plays a significant role in the global hydrological cycle, which is an important component of soil parameterization. Remote sensing one most methods used to estimate moisture. In this study, we developed new nonlinear Erf-BP neural network method establish soil-moisture-content-estimation model with integrated multiple-resource remote-sensing data from high-resolution, hyperspectral and microwave sensors. Next, compared result single-resource for SMC (soil-moisture content) estimation models by using linear-fitting method. The results showed that soil-moisture offers better accuracy data. Furthermore, predicted good overall correlation coefficient 0.6838. Compared linear model’s results, was increased, RMSE decreased 0.017 g/g 0.0146 g/g, decrease 16.44%. These also indicate improved algorithm artificial has fitting precision. This research provides reference estimation.