Predictive Modeling of Land Use and Land Cover Changes Using Q-GIS to Improve Geospatial Decision-Making and Sustainable Strategies

Abstract

Abstract A systematic approach to comprehending both physical and non-physical interactions between ecosystems in nature with the aim of ecological sustainability is called LULC alteration analysis. An extensive overview of the development potential for both present and future is provided through an investigation of spatially shifting behaviors of LULC and modeling of prospective eventualities. With a 20-year approximation from 2000 to 2020, we used substantial multi-temporal data collected via satellite to explore opportunities for evolution from one spatiotemporal transition state to a subsequent and prospective LULC model. In the MOLUSCE plugin of Q-GIS, uncorrelated parameters (DEM, gradient, and location concerning roadways) have been combined with an incorporated CA-ANN technique. Throughout previous three decades, impervious surface area increased from 12.48% to 28.91%, while water levels increased from 1.43% to 1.39%, demonstrating that physical and social driving forces had significant influence on landscape pattern. Urbanization and development are reflected from rising water table and shrinking impermeable surface. Land use shifts or climatic variability may result decline in water levels, whereas the rise in impermeable surfaces points in the direction of proliferation of metropolitan region. The quantity of dry land decreased from 48.28% to 43.11%, the verdant area was 27.34% to 13.77%, and woodland shrank from 22.70% to 12.64%. The estimates from 2030 to 2040 further endorse an increasing shift toward impermeable terrain at the expense of substantial forests and natural habitats. For successful land management, urban planning, and sustainable development, LULC trends must be precisely predicted. In-depth reviews and analyses of predictive modeling approaches utilized for LULC prediction are provided in the study. This study investigates frequently used data sources and preprocessing methods, looks at difficulties with LULC prediction, and offers critical assessment of modeling strategies. The report also outlines future research priorities and explores possible uses of the LULC prediction model uses.