Land‐Use Change Simulation and Municipal Solid Waste Forecasting Through Hybrid Geospatial‐Statistical Methods

ABSTRACT Rapid urbanization in mid‐sized Indian cities is intensifying pressure on land resources and municipal solid waste (MSW) management, highlighting the need for integrated forecasting frameworks to guide sustainable urban development. This study presents a hybrid geospatial‐statistical approach to simulate long‐term land use change and forecast MSW generation in Kota City, India, over the period 2000–2050. Multitemporal Landsat images were classified using the Random Forest algorithm on the Google Earth Engine (GEE) platform, while future land transitions were simulated using Cellular Automata‐Artificial Neural Network (CA‐ANN) model in QGIS. Population was projected using the geometric growth model, and MSW generation was estimated through Multiple Linear Regression (MLR) in R, employing population and built‐up area as predictors. Results indicate a 129.5% increase in built‐up area between 2000 and 2025, largely driven by the conversion of vegetated and barren land. By 2050, built‐up area is projected to increase by 215.3%, with the population reaching approximately 2.89 million and daily MSW generation increasing to 1399.66 tons. Strong Pearson correlations ( r > 0.98) among population, built‐up area, and MSW confirm their interdependence, validating their use as forecasting variables. The proposed framework demonstrates the potential of integrating remote sensing, spatial simulation, and statistical modeling for anticipatory infrastructure planning. It provides a scalable, data‐efficient tool for SDG‐aligned urban sustainability strategies, particularly in data‐scarce regions of the Global South.