Remote Sensing Image Classification Based on Decision Tree in the Karst Rocky Desertification Areas: A Case Study of Kaizuo Township

Karst rocky desertification is a phenomenon of land degradation as a result of affection by the interaction of natural and human factors. In the past, in the rocky desertification areas, supervised classification and unsupervised classification are often used to classify the remote sensing image. But they only use pixel brightness characteristics to classify it. So the classification accuracy is low and can not meet the needs of practical application. Decision tree classification is a new technology for remote sensing image classification. In this study, we select the rocky desertification areas Kaizuo Township as a case study, use the ASTER image data, DEM and lithology data, by extracting the normalized difference vegetation index, ratio vegetation index, terrain slope and other data to establish classification rules to build decision trees. In the ENVI software support, we access the classification images. By calculating the classification accuracy and kappa coefficient, we find that better classification results can be obtained, desertification information can be extracted automatically and if more remote sensing image bands used, higher resolution DEM employed and less errors data reduced during processing , classification accuracy can be improve further.