The dynamic monitoring and mapping of soil salinization is a practical significance work at present. In this paper, the middle reaches of Heihe River, China, was taken as a study case to discuss the effectiveness of extracting saline land information applying decision tree approach, based on Landsat TM data acquired on Sep.23, 2007. Through visual interpretation and statistical analysis of spectral characteristic associated with field survey and Google Earth image with higher resolution, finally five feature variables: thermal infrared band (TM6), Normalized Difference Vegetation Index (NDVI), Modified Normalized Difference Water Index (MNDWI), the third component of MNF rotation (MNF3) and the wetness of K-T transformation (TC3) were selected to construct decision tree model by setting the proper threshold values. The research suggested that MNF3 is an optimal band to discriminate saline land from other object-grounds on condition of MNF<-1. The water body and vegetation district can be extracted by NDVI and MNDWI, respectively. Combining MNF3, TC3 and TM6 can well obtain sandy land and farmland information. The overall accuracy of classification results achieves 85.34% and Kappa Coefficient is 0.795, both of which show the effectiveness and feasibility of decision tree approach for monitoring and mapping spatial distribution of soil salinization.