Land use suitability analysis using artificial intelligence and machine learning for developing urban areas

Urban areas around the globe are now seeing a significant surge in growth, characterized by an escalating pace of expansion. This phenomenon has presented several obstacles to pursuing sustainable development within these regions. The increasing trend of urbanization has resulted in significant population growth and a notable expansion of building infrastructure. Given these transformations, using Land Use Suitability Analysis (LUSA) to inform urban planning, allocate resources, and promote sustainable development has become crucial. Nevertheless, the current LUSA approaches need help with precision, resilience, and incorporating several environmental parameters. This research study presents a Hybrid Land Use Suitability Analysis (HLUSA) technique to tackle these issues using Artificial Intelligence (AI) and Machine Learning (ML). The HLUSA framework integrates a range of established methodologies, including Machine Learning, Geographic Information Systems (GIS), and Multi-Criteria Decision Analysis (MCDA), to thoroughly and precisely evaluate land use appropriateness. The findings of the HLUSA study exhibit its efficacy across various indicators, including Land Use Change (%) - 12.87%, Transition Probability - 0.54, Agreement Kappa Index - 0.82, Assessment Accuracy (%) - 92.43%, Spatial Trend (%) - 18.86, Euclidean Distance (m) - 1156.60, Temperature (
^○
C) - 28.94, and Rainfall (mm) - 139.22. The results above highlight the resilience of HLUSA in tackling the intricacies associated with urban expansion, rendering it a helpful instrument for urban planners and policymakers aiming to promote sustainable development and optimize land usage among the challenges posed by fast urbanization.