Multilayer perceptron and Markov Chain analysis based hybrid-approach for predicting land use land cover change dynamics with Sentinel-2 imagery

As urbanization accelerates, the degree of human impact on land use is increasing. Changes in land use land cover (LULC) are widely acknowledged as crucial factors in environmental change. The most precise approach to comprehending the historical patterns of land use, the types of changes that have occurred, the driving forces behind them, and the overall developments are through a rigorous assessment of LULC changes. By considering the causes of LULC dynamics in this study, we aim to identify LULC changing patterns, gains, and losses, spatial trends of change from 2015 to 2022, and predict the dynamics of LULC changes for 2030 in Islamabad, Pakistan. Multispectral Sentinel-2 satellite images, devoid of cloud cover, were employed to discern patterns of LULC change and forecast the prospective dynamics of LULC. The Random Forest algorithm was used to classify the various LULC classes with high accuracy and reliability. All the classified LULC maps exhibit outstanding accuracy, with overall accuracies exceeding 90%. Multilayer Perceptron and Markov Chain Analysis (MLP-MCA) based Hybrid-Approach was employed to model the time series data and predict the future dynamics of LULC Change for 2030. The validation of the forecasted LULC map exhibited an overall accuracy of over 90%. The study revealed that built-up expanded by an area of 90.64 km2 over an 8-year interval (2015 - 2022) using the substitution of natural resources. Based on future predictions, it is anticipated that a substantial portion of the entire study area, precisely 58.84%, will transform into built-up terrain by 2030. The significant augmentation of the built-up region and a corresponding decline in crops, forests, and other natural resources are poised to imperil the environmental sustainability of Islamabad. This study's findings can give urban planners and policymakers valuable insights into the shifting patterns of LULC, enabling them to make informed and productive decisions about sustainable development.