Geospatial modelling of changes in land use/land cover dynamics using Multi-layer Perceptron Markov chain model in Rajshahi City, Bangladesh

Abstract

Cities are developing rapidly and subsequently influences the land use/land cover (LU/LC) changes. Rajshahi city in Bangladesh facing rapid urban expansion by replacing LU/LC such as vegetation cover, water bodies (natural resources) and bare land to urban settlements. This study aims to identify the LU/LC changing patterns of Rajshahi city for 2000, 2010 and 2020 and simulate future LU/LC changes for 2040. Multi-temporal cloud-free Landsat satellite images were used to estimate the LU/LC and urban settlement changing pattern using remote sensing and geographic information system techniques. A support vector machine algorithm was used to classify the LU/LC classes. All the classified LU/LC maps demonstrate excellent accuracy by showing more than 85% overall accuracy. The multi-layer perception Markov chain (MLP-MC) model was used to predict the future LU/LC scenario for 2040. Validation of the predicted LU/LC map demonstrated more than 90% overall accuracy. The study found that an average of 3.6 km2 urban settlements increased at 10 years interval by replacing the natural resources. The future prediction shows that more than 60% of the total city area will be transformed into urban settlements by 2040. The dramatic increase in urban settlements and reduction in green cover and water bodies will damage the environmental sustainability of Rajshahi city by increasing temperature and heatwaves. This study will help the urban planners and policymakers to make proper sustainable development decisions by understanding the LU/LC changing pattern.