Prediction of Land Use and Land Cover Changes in Mumbai City, India, Using Remote Sensing Data and a Multilayer Perceptron Neural Network-Based Markov Chain Model

In this study, prediction of the future land use cover (LULC) changes over Mumbai and its surrounding region, India, was conducted to have reference information in urban development. To obtain historical dynamics LULC, a supervised classification algorithm applied Landsat images 1992, 2002, 2011. Based on spatial drivers LULC 1992 multiple perceptron neural network (MLPNN)-based Markov chain model (MCM) simulate 2011, which further validated using kappa statistics. Thereafter, by 2002 2011 MLPNN-MCM predict 2050. This study predicted prompt growth suburban regions Mumbai, shows, 2050, Urban class will occupy 46.87% (1328.77 km2) entire area. As compared Forest areas 2050 increase 14.31% 2.05%, respectively, while area under Agriculture/Sparsely Vegetated Barren decline 16.87%. The water coastal feature experience minute fluctuations (<1%) future. for can be used as thematic map various climatic, environmental, planning models achieve aims sustainable development region.