Assessing and Improving the Accuracy of GlobeLand30 Data for Urban Area Delineation by Combining Multisource Remote Sensing Data

For a long time, the available global products of the urban area extent were limited to a coarse spatial resolution, e.g., Moderate Resolution Imaging Spectroradiometer (MODIS) global land cover (GLC) 500-m data and European Space Agency GlobCover 300-m data. This limitation was broken by the GlobeLand30 data, which is the world's first 30-m resolution GLC data set. However, detection accuracies of urban areas for the GlobeLand30 data (i.e., artificial surfaces) are not satisfactory. Therefore, in order to refine the detection accuracy of urban areas on the basis of the GlobeLand30 data, we propose a novel framework for urban area delineation by combining a set of remote sensing images and a geographical information system database, including the GlobeLand30 data, the National Land Cover Database (NLCD), the Land Use Interpretation Map (LUIM) of China, and Landsat images. First, the GlobeLand30 and land use/land cover products (e.g., NLCD or LUIM) are overlapped, and the study area is then separated into reliable and unreliable areas with a majority voting rule. Finally, the unreliable areas are confirmed by use of the Landsat data with a multiclassifier system. Experiments were conducted over two study areas that, respectively, represent typical patterns of American and Chinese urban areas: 1) the states of Utah, Mississippi, and Pennsylvania in the U.S. and 2) the provinces of Ningxia, Fujian, and Jilin in China. The results show that the accuracy of the GlobeLand30 data for urban area delineation can be significantly improved by integrating the multisource data and using the multiclassifier system.