The geological environment conditions of Guizhou Province are complex and geological hazards are seriously developed.Therefore,it is of great significance to carry out geological hazard susceptibility analysis based on artificial neural network algorithm to improve the efficiency of the province's susceptibility evaluation and realize intelligent analysis.By comparing various artificial neural network algorithms,radial basis function network(RBF),probabilistic neural network(PNN)and fuzzy neural network(FNN)are selected as model algo-rithms,and spatial data modeling software(SDM)based on GIS platform is used to construct an artificial intelli-gence-based geological disaster risk analysis model system.Through the steps of data preparation,data process-ing,model training,model invocation,evaluation and optimization,the paper carries out three kinds of geological disaster susceptibility analysis based on artificial neural networks in mountainous areas of Guizhou.The results of the three kinds of artificial neural network calculation are reasonably partitioned,the accuracy test is quali-fied,and the AUC test shows that it has good prediction value;Compared with the expert experience analysis re-sults,the evaluation results of RBF algorithm are more consistent with the reality,which indicates that RBF algo-rithm can be better applied to the geological disaster susceptibility analysis.
维普
万方数据