LAUSR

China has undergone significant land cover changes since the 1980s. However, there are limited consistent and continuous dataset of national scale. Using advanced very high resolution radiometer and moderate resolution imaging spectrometer data from the land long-term data record, we developed a large-scale classification approach to produce a decadal 5-km resolution land cover dataset for China (ChinaLC) from 1981 to 2010. A total of 19 classes of training and validation samples were obtained from visual interpretation of high-resolution Google Earth images and historical vegetation maps. Combined efforts of standard criteria, rigid check, and detailed recording were conducted to strengthen the robustness of the multitemporal samples. The different compositions of metrics and parameters were tested to obtain the optimal support vector machine (SVM) classification results. The ChinaLC dataset has an average overall accuracy of approximately 75%, which is much higher compared with other large-scale land cover datasets. Furthermore, a high consistency was found between the land cover changes of ChinaLC and other studies using higher spatial resolution data. The decadal spatial–temporal transition patterns were analyzed and the important reasons for accelerated landscape changes were also explained over the 30 years.