Characterizing the Up-To-Date Land-Use and Land-Cover Change in Xiong’an New Area from 2017 to 2020 Using the Multi-Temporal Sentinel-2 Images on Google Earth Engine

Land use and land cover (LULC) are fundamental units of human activities. Therefore, it is significance to accurately in a timely manner obtain the LULC maps where dramatic changes undergoing. Since 2017 April, new state-level area, Xiong’an New Area, was established China. In order better characterize this study makes full multi-temporal 10-m Sentinel-2 images, cloud-computing Google Earth Engine (GEE) platform, powerful classification capability random forest (RF) models generate continuous from 2020. To do so, novel multiple RF-based framework adopted by outputting probability based on each monthly composite aggregating final map. Based obtained maps, analyzes spatio-temporal types last four years different change patterns three counties. Experimental results indicate that derived achieve high accuracy for year, with overall Kappa values no less than 0.95. It also found changed areas account nearly 36%, dry farmland, impervious surface, other land-cover have dramatically present varying counties, which might be caused latest planning Area. The four-year supposed provide some valuable information monitoring understanding what kinds taken place