Super-resolution mapping of wetland inundation from remote sensing

Mapping the spatio-temporal characteristics of wetland 19 inundation has important significance to the study of wetland environment and 20 associated flora and fauna. High temporal remote sensing imagery is widely 21 used for this purpose with the limitations of relatively low spatial resolutions. In 22 this study, a novel method based on integration of back-propagation neural 23 network (BP) and genetic algorithm (GA), so-called IBPGA, is proposed for 24 super-resolution mapping of wetland inundation (SMWI) from multispectral 25 remote sensing imagery. The IBPGA-SMWI algorithm is developed, including 26 the fitness function and integration search strategy. IBPGA-SMWI was 27 evaluated using Landsat TM/ETM+ imagery from the Poyanghu wetland in 28 China and the Macquarie Marshes in Australia. Compared with traditional 29 SMWI methods, IBPGA-SMWI consistently achieved more accurate super30 resolution mapping results in terms of visual and quantitative evaluations. In 31 comparison with GA-SMWI, IBPGA-SMWI not only improved the accuracy of 32 1 SMWI, but also accelerated the convergence speed of the algorithm. The 33 sensitivity analysis of IBPGA-SMWI in relation to standard crossover rate, BP 34 crossover rate and mutation rate was also carried out to discuss the algorithm 35 performance. It is hoped that the results of this study will enhance the 36 application of median-low resolution remote sensing imagery in wetland 37 inundation mapping and monitoring, and ultimately support the studies of 38 wetland environment. 39