Application of neural network to identify the remote sensing data of hillslide

Abstract

This study presents the results of neural network simulation of hillside area prediction from remote sensing data. Five neural network methods were compared, which were Back Propagation Network (BPN), Extend Neuron Networks (ENN), Fuzzy Neural Network (FNN), Analysis Adjustment Synthesis Network (AASN), and Genetic Algorithm Neural Network (GANN). Three factors were used as the predictor in this study, which were NDVI value, shape factor, and color difference. The result reveals that the BPN is the best choice, because the error is the lowest among the five schemes in this study.