Analysis on Land-Use/Cover Change in Hangzhou Bay, China during 2000–2020 Using the Google Earth Engine

Abstract

Large-scale, long-time series and high-precision land use mapping are the basis for urban planning and environmental protection. Based on Google Earth Engine (GEE) and Landsat satellite remote sensing imagery, we used a random forest (RF) classification algorithm to create the 2000-2020 Hangzhou Bay, China land-use/cover change (LUCC) dataset, extracted the area of each feature based on classified pixels, and studied the spatial and temporal characteristics of LUCC, and the change mechanism. The main results are as follows: (1) The GEE platform can achieve efficient extraction of LUCC data with an overall accuracy (OA) mean value of 91.95% and a Kappa coefficient of 88.87%. (2) The area of construction area has been increasing (+2015.18km2) and the area of cultivated land has been decreasing (-1919.38km2) in the past two decades. (3) The area of bare land (+404.60km2), forest land (-10.01km2), and water bodies (-49.20km2) fluctuate and change. (4) The area of mudflats is decreasing on the north coast, and the area of mudflats on the south coast is gradually moving north, with fluctuating changes. The overall mudflat area decreases (-76.86km2). This study provides data support for the scientific management of land resources in the Hangzhou Bay region, and the resulting dataset is important for the sustainable development of the area.