| Abstract: | Annual Land Use/Land Cover(LULC) change information at medium spatial resolution(i.e., at 30 m) is used in applications ranging from land management to achieving sustainable development goals related to food security. However, obtaining annual LULC information over large areas and long periods is challenging due to limitations on computational capabilities, training data, and workflow design. Using the Google Earth Engine(GEE), which provides a catalog of multi-source data and a cloud-based environment, we developed a novel methodology to generate a high accuracy 30-m LULC cover map collection of the Yangtze River Delta by integrating free and public LULC products with Landsat imagery. Our major contribution is a hybrid approach that includes three major components: 1) a high-quality training dataset derived from multi-source LULC products, filtered by k-means clustering analysis; 2) a yearly 39-band stack feature space, utilizing all available Landsat data and DEM data; and 3) a self-adaptive Random Forest(RF) method, introduced for LULC classification. Experimental results show that our proposed workflow achieves an average classification accuracy of 86.33% in the entire Delta. The results demonstrate the great potential of integrating multi-source LULC products for producing LULC maps of increased reliability. In addition, as the proposed workflow is based on open source data and the GEE cloud platform, it can be used anywhere by anyone in the world. |
