Verification and analysis of surface water in China based on Landsat8 OLI images. Issue 1 (May 2020)

• Record Type: Journal Article
• Authors: Jiang, Wei; He, Guojin; Pang, Zhiguo; Long, Tengfei; Fu, JUNE; Guo, Hongxiang; Ni, Yuan
• Is Part Of: IOP conference series. Volume 502:Issue 1(2020)
• Publication Date: 2020-05
• Subjects: Earth sciences -- Periodicals; Environmental sciences -- Congresses; Environmental sciences -- Periodicals; 550.5
• DOI: 10.1088/1755-1315/502/1/012030
• Languages: English
• ISSNs: 1755-1307

Abstract

Abstract: Surface water map is important to understand climate change and the hydrologic cycle and manage water resource. This study introduces multilayer perceptron (MLP) neural network to produce a surface water map of China in 2015 (SWMC-2015), Then, a new framework is created to generate a set of random water and not water validation points to assess the accuracy of the SWMC-2015. The overall accuracy and kappa coefficients of SWMC-2015 are 90% and 0.78, respectively. Finally, with the SWMC-2015, the spatial characteristics of surface water are comprehensively analysed at national, basin and province scales. The surface water area in China is 154, 811.1 km 2, accounting for 1.63% of the total land area. There are considerable differences in surface water abundance at both the basin and province scales. The water body areas are largest in the continental basin and Tibet, and water bodies cover the greatest percentage of total surface area in the Huaihe River Basin and Jiangsu.