DOI: 10.26833/ijeg.1828589 ISSN: 2548-0960

Integrating GEE, Machine Learning, and MOLUSCE for Predicting Urban LULC Dynamics of Ahmedabad Metropolitan Region, India

Rupesh Gupta
Show PDF Cite
The Ahmedabad Metropolitan Region in India has witnessed rapid, spatially uneven urbanisation over the past two decades, profoundly altering land use and land cover (LULC) patterns and generating significant environmental and planning challenges. This study integrates advanced geospatial analytics and machine learning techniques to evaluate past and future LULC transitions from 2000 to 2020, with projections through 2045. Landsat imagery was processed in Google Earth Engine (GEE), and land cover was classified into five major classes: built-up, vegetation, agricultural land, barren land, and water bodies. This classification was achieved using the Random Forest algorithm, which proved highly effective in handling complex, heterogeneous urban environments. Classification accuracy was assessed using a confusion matrix, yielding an overall accuracy of 92.8% and a Kappa coefficient of 0.89, confirming the robustness of the results. Future simulations were conducted using the QGIS-MOLUSCE plugin based on a Cellular Automata–Artificial Neural Network (CA–ANN) model to capture the spatial dynamics of urban expansion. Results indicate a significant 38.34% increase in built-up area (from 161.40 km² in 2000 to 223.39 km² in 2020) alongside declines in vegetation, agriculture, and barren land, reflecting mounting ecological stress and thermal vulnerability. The model projects that by 2045, built-up areas could expand to 310.22 km², potentially encroaching upon vital green and hydrological systems. While the model demonstrates high predictive accuracy, it remains constrained by the spatial resolution of input data and the exclusion of socio-economic variables. The study highlights the pressing need for integrated urban policies, enhanced green infrastructure, and the establishment of a Metropolitan Land Use Observatory to ensure continuous monitoring, data-informed governance, and sustainable urban development across Ahmedabad’s expanding metropolitan landscape.

More from our Archive