Long-term mapping of land use and cover changes using Landsat images on the Google Earth Engine Cloud Platform in bay area - A case study of Hangzhou Bay, China

Large-scale, long-term series, and high-precision land use and cover change (LUCC) mapping is the basic support for territorial spatial planning and sustainable development in the Bay Area. In response to the sustainable development agenda, for characteristics of high landscape fragmentation, strong surface heterogeneity and frequent land use type conversion in the Bay Area, this study developed a random forest (RF) algorithm that considers spectral bands, remote sensing indices and components of a principal component analysis, and the mapping and monitoring of LUCC in Hangzhou Bay from 1985 to 2020 based on Google Earth Engine (GEE) and Digital Shoreline Analysis System (DSAS) were carried out. The results are as follows. (1) The overall accuracy (OA) and kappa coefficient were 92.83% and 0.91, respectively. (2) During the study period, the areas of the construction land, water area, and bare land increased, while the areas of the wood land, cultivated fields, and tidal flats decreased. (3) During the study period, the total area of the tidal flats decreased from 181.65 km2 to 161.50 km2, with an average annual decrease of 0.58 km2, and the tidal flats were primarily concentrated on the south shore of Hangzhou Bay. (4) During the study period, the transfer of cultivated fields to construction land was the most significant (2268.05 km2). (5) During the study period, the length of the coastline decreased from 383.73 km to 362.80 km, with an average annual decrease of 0.60 km. According to the DSAS statistics, the net shoreline movement (NSM) of the coastline on the north shore of Hangzhou Bay was 773.58 m, the end point rate (EPR) and the linear regression rate (LRR) were 22.10 m/a and 27.00 m/a, respectively. The NSM of the south shore was 4109.57 m, and the EPR and LRR were 117.42 m/a and 132.22 m/a, respectively. The proposed methods improve the accuracy of land use classification of the RF algorithm in the complex environment of the Bay Area, and it can provide technical support for natural resource survey and regional sustainable development in the Bay Area. © 2023 The Author(s)