Abstract: Land cover change is one of the most direct manifestations of global environmental change, and it also can influence the global environment. The dynamic analysis of regional land cover change is the basic work for the researches on the global change, ecosystem assessment and interaction between human and environment. In this study we take the northwest China as the research area, including the Xinjiang Uygur Autonomous Region, Qinghai Province, Gansu Province, Ningxia Hui Autonomous Region, Shaanxi Province and Alashan league in Inner Mongolia Autonomous Region, collect the Landsat TM image data in 1990, 2005 and 2010, and Landsat ETM+ image data in 2000, and extract the land cover data in four periods using the object-oriented computer automatic classification combined with artificial visual interpretation methods with the eCognition software platform. Finally, we use three methods to verify the data accuracy, including field sample point survey, high-resolution image recognition and Google Earth sample point identification. This dataset can be used as a background data of regional ecological environment assessment, and is also the basic data for the regional planning, climate change research, environmental modeling, biodiversity, and ecosystem carbon research.
Keywords: northwest region of China; land cover; oriented-object classification method; eCongnition; Landsat