Research on the high resolution remote sensing image classification algorithm based on improved neural network model

Abstract

Mapping the spatiotemporal attributes of swampland which is wetland that is forested has essential criticalness to the investigation of swampland environment and numerous related widely varied vegetation. Manuscript discusses innovative strategy in view of incorporation of BP and GA, supposed IBPGA, is suggested for high determination plotting of swampland collection (HSA) from multispectral RSI. The IBGHSA algorithm is produced, including the wellness capacity and incorporation look technique. IBGHSA was assessed utilizing Landsat symbolism from the swampland of a state. Contrasted and conventional HSA techniques, IBGHSA reliably accomplished more precise determination mapping brings about terms of visual and quantitative assessments. In correlation with GAHSA, IBGHSA enhanced the exactness of HSA, as well as quickened the joining velocity of the algorithm. The affectability examination of IBGHSA in connection to standard hybrid rate, Back Propagation hybrid rate and rate of change was likewise completed to talk about the algorithm execution.