Moisture retrieval based on an optimized Least Squares Support Vector Machine Model

Soil moisture retrieval is important in microwave remote sensing, but its high dimensional and non-linearity make it difficult to realize. In this paper, an improved Fruit Fly Optimization Algorithm (IFOA) to optimize the Least Squares Support Vector Machine (LSSVM) Model is used for soil moisture retrieval. The sampling data for training and test is generated by using Advanced Integral Equation Model (AIEM). To verify the performance of IFOA optimized LSSVM (IFOA-LSSVM), we apply it to the soil moisture retrieval in L and C bands and compare the results with those of FOA-LSSVM and LSSVM.