Integration of Bayesian regulation back-propagation neural network and particle swarm optimization for enhancing sub-pixel mapping of flood inundation in river basins

Abstract

Sub-pixel mapping of flood inundation (SMFI) is one of the hotspots in remote sensing and relevant research and application fields. In this study, a novel method based on the integration of Bayesian regulation back-propagation neural network (BRBP) and particle swarm optimization (PSO), so-called IBRBPPSO, is proposed for SMFI in river basins. The IBRBPPSO–SMFI algorithm was developed and evaluated using Landsat images from the Changjiang river basin in China and the Murray-Darling basin in Australia. Compared with traditional SMFI methods, IBRBPPSO–SMFI consistently achieves the most accurate SMFI results in terms of visual and quantitative evaluations. IBRBPPSO–SMFI is superior to PSO–SMFI with not only an improved accuracy, but also an accelerated convergence speed of the algorithm. IBRBPPSO–SMFI reduces the uncertainty in mapping inundation in river basins by improving the accuracy of SMFI. The result of this study will also enrich the SMFI methodology, and thereby benefit the environmental studies of river basins.