Support Vector Machines with PSO Algorithm for Soil Erosion Evaluation and Prediction

Abstract

Soil erosion is a very complicated process, and influenced by many correlatively factors, so it is hard to evaluate and predict the condition of soil erosion, especially in those regions where there have not sufficiently observation date. To solve the above problem, this paper proposed a new assessment model based on the support vector machines (SVM), In order to improve the accuracy of the model, the algorithm of particle swarm optimization (PSO) is used to hunt the optimum solution of the parameters sigma, penalty factor C and xi -insensitive loss function of SVM. The model is carried out in Shiqiaopu catchment of Hubei province, the results of training and validation have shown that the model has higher forecasting accuracy, compared with the algorithm of BP artificial neural network model. Thus, the model based on SVM provides a new method for evaluating and predicting the condition of soil erosion.