An Artificial Intelligence Integrated Geospatial Decision-Support Framework for Scenario-Based Climate-Adaptive Land-Use Optimization and Environmental Risk Reduction

Abstract

This study developed and empirically validated an Artificial Intelligence-Integrated Geospatial Decision-Support Framework for Scenario-Based Climate-Adaptive Land-Use Optimization and Environmental Risk Reduction. The research examined the relationships among Artificial Intelligence-Integrated Geospatial Decision-Support Systems, Multi-Criteria Spatial Decision Analysis, Climate-Adaptive Land-Use Optimization, and Environmental Risk Reduction using a quantitative cross-sectional research design. Data were collected from 478 environmental planning professionals representing governmental agencies, private organizations, academic institutions, and non-governmental organizations following comprehensive data screening and quality assessment. Descriptive statistics, reliability and validity analyses, Pearson correlation, multiple regression, and Partial Least Squares Structural Equation Modelling (PLS-SEM) were employed to evaluate the proposed conceptual framework. The findings demonstrated high organizational capability across all measured constructs, with mean scores ranging from 4.14 to 4.27. Reliability analysis confirmed excellent internal consistency, with Cronbach's alpha values ranging from 0.944 to 0.952, Composite Reliability values between 0.952 and 0.959, and Average Variance Extracted values from 0.709 to 0.742, confirming satisfactory convergent validity. Pearson correlation coefficients ranged from 0.736 to 0.823, indicating strong positive relationships among the principal constructs. Multiple regression analysis revealed that Artificial Intelligence-Integrated Geospatial Decision-Support Systems significantly predicted Climate-Adaptive Land-Use Optimization (β = 0.612, p < 0.001) and Environmental Risk Reduction. Structural Equation Modelling further demonstrated significant direct effects of Artificial Intelligence-Integrated Geospatial Decision-Support Systems on Multi-Criteria Spatial Decision Analysis (β = 0.758, p < 0.001), Climate-Adaptive Land-Use Optimization (β = 0.512, p < 0.001), and Environmental Risk Reduction (β = 0.463, p < 0.001). Multi-Criteria Spatial Decision Analysis also significantly mediated the relationships between artificial intelligence capability and both outcome variables. The structural model explained 69.4% of the variance in Climate-Adaptive Land-Use Optimization and 68.1% of the variance in Environmental Risk Reduction, while the model demonstrated satisfactory goodness-of-fit (SRMR = 0.047; NFI = 0.931). Overall, the validated framework demonstrated that integrating artificial intelligence with geospatial decision-support and structured spatial decision analysis substantially enhanced organizational capability for climate-adaptive land-use optimization and environmental risk reduction, providing a statistically robust and practically effective model for intelligent environmental planning and sustainable environmental governance.