AI-DRIVEN MIS APPLICATIONS IN ENVIRONMENTAL RISK MONITORING: A SYSTEMATIC REVIEW OF PREDICTIVE GEOGRAPHIC INFORMATION SYSTEMS

Abstract

This integrative review investigates the convergence of Artificial Intelligence (AI), Geographic Information Systems (GIS), and Management Information Systems (MIS) in advancing environmental risk monitoring through predictive modeling and data-driven decision-making. A total of 142 peer-reviewed articles published between 2010 and 2025 were systematically selected and analyzed to explore how these technologies are being integrated to enhance the accuracy, efficiency, and institutional coordination of environmental hazard assessment. The review synthesizes applications across diverse hazard domains, including flood forecasting, wildfire prediction, drought monitoring, and urban pollution management. Findings reveal that AI techniques—particularly machine learning and deep learning models—significantly improve the predictive power of GIS platforms, with over 60% of the reviewed studies reporting model accuracy above 85%. The review highlights global implementations from regions such as South Asia, North America, East Asia, and sub-Saharan Africa, demonstrating the adaptability of AI-MIS-GIS systems across varied institutional and environmental contexts. Theoretical frameworks including Spatial Decision Support Systems (SDSS), the Technology Acceptance Model (TAM), and Environmental Information Systems (EIS) theory are discussed to contextualize system design and stakeholder adoption. This study offers a comprehensive foundation for understanding how technological integration is reshaping environmental intelligence systems and fostering proactive risk governance on a global scale.