A remote sensing aided multi-layer perceptron-Markov chain analysis for land use and land cover change prediction in Patna district (Bihar), India

Abstract

Land use and land cover (LULC) changes are recognized as one of the most significant driver of environmental changes, mainly due to rapid urbanization. In this paper, an attempt has been made to appraise the ability of multi-layer perceptron-Markov chain analysis (MLP-MCA) integrated method to monitor and predict the future LULC change scenarios in Patna district, Bihar using remote sensing images. A supervised maximum likelihood classification method was applied to derive LULC maps from 1988, 2001, and 2013 Landsat Thematic Mapper (TM)/Enhanced Thematic Mapper Plus (ETM+)/Operational Land Imager (OLI) images, respectively. The LULC maps of 1988 and 2001 were employed to predict the LULC scenario for 2013 using MLP-MCA method. The predicted result was compared with the observed LULC map of 2013 to validate the method using kappa index statistics. Finally, based on the results, the future LULC change prediction for 2038 and 2050 was performed. The outcomes of this study reveal the rapid growth in ​built up area results in continuous decrease in agricultural lands.