Analysis of urban landscape pattern change in Yanzhou city based on TM/ETM plus images

To provide a scientific basis for ecological construction of urban landscape, we take Yanzhou for an example to analyze the urban landscape pattern change. The images of the multi-temporal Landsat TM/ETM+ data in 1998 and 2002 are used to select the best band combinations to interpret images based on the correlation coefficient of bands and Optimum Index Factor (OIF). Then we classify the images using Maximum Likelihood Classifier (MLC) and Support Vector Machines (SVM) classifier. The results of SVM are used for analyzing the urban landscape pattern change in Yanzhou city to obtain its characteristics because it has higher classification precision. The experiment shows a rich diversity, a low dominance of landscape and the common development of landscapes. In the development process of urban and mining area in Yanzhou city, the balanceable development of protecting the objects style is paid more attention to and the ecological environment type keeps in good condition on the whole.