Soil Moisture Inversion Based on Data Augmentation Method Using Multi-Source Remote Sensing Data

Soil moisture is an important land environment characteristic that connects agriculture, ecology, and hydrology. Surface soil moisture (SSM) prediction can be used to plan irrigation, monitor water quality, manage water resources, and estimate agricultural production. Multi-source remote sensing is a crucial tool for assessing SSM in agricultural areas. The field-measured SSM sample data are required in model building and accuracy assessment of SSM inversion using remote sensing data. When the SSM samples are insufficient, the SSM inversion accuracy is severely affected. An SSM inversion method suitable for a small sample size was proposed. The alpha approximation method was employed to expand the measured SSM samples to offer more training data for SSM inversion models. Then, feature parameters were extracted from Sentinel-1 microwave and Sentinel-2 optical remote sensing data, and optimized using three methods, which were Pearson correlation analysis, random forest (RF), and principal component analysis. Then, three common machine learning models suitable for small sample training, which were RF, support vector regression, and genetic algorithm-back propagation neural network, were built to retrieve SSM. Comparison experiments were carried out between various feature optimization methods and machine learning models. The experimental results showed that after sample augmentation, SSM inversion accuracy was enhanced, and the combination of utilizing RF for feature screening and RF for SSM inversion had a higher accuracy, with a coefficient of determination of 0.7256, a root mean square error of 0.0539 cm3/cm3, and a mean absolute error of 0.0422 cm3/cm3, respectively. The proposed method was finally used to invert the regional SSM of the study area. The inversion results indicated that the proposed method had good performance in regional applications with a small sample size.