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

• DOI: 10.1016/j.horiz.2023.100061
• Publication Date: 2023-07-05T03:53:25Z
• Authors: Jintao Liang; Chao Chen; Yongze Song; Weiwei Sun; Gang Yang
• Keywords: Land Cover

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