Exploring LULC changes in Pakhal Lake area, Telangana, India using QGIS MOLUSCE plugin

Dynamic processes such as environmental, economic, and social factors influence land use and land cover (LULC) changes, with temporal and spatial variations. This study aims to identify changes in LULC and predict future trends in the Pakhal Lake area in Peninsular India. Satellite images for the years from 2016 to 2022 were used for LULC classification using deep learning with Sentinel − 2 imagery in Google Earth Engine (GEE). Dynamic World dataset is used to classify the LULC changes of the study area with a 10 m near-real-time dataset. Images were classified based on six different LULC classes, namely water, vegetation, flooded vegetation, agriculture, built-up area, and bare land. The Cellular Automata–Artificial Neural Network (CA − ANN) technique was used to predict LULC changes. QGIS plugin MOLUSCE with Multi-Layer Perception (MLP), was used to predict and determine potential LULC changes for 2025 and 2028. The overall Kappa coefficient value of 0.78, and an accuracy of 82% indicated good results for LULC changes and projected maps for 2025. Prediction of LULC changes using MLP − ANN for the years 2025 and 2028 showed increase in agriculture, built-up areas, and barren land. The results of the study will be useful to develop better management techniques of natural resources.