MODELING THE SECURITY AND RESILIENCE OF GIS SYSTEMS USING ARTIFICIAL INTELLIGENCE

Abstract

Geographic information systems (GIS) play a critical role in the functioning of modern states and economies by supporting crisis management, critical infrastructure protection, and the delivery of public services. The increasing integration of GIS with cloud computing environments, Internet of Things (IoT) networks, and real time analytical mechanisms significantly enhances their operational capabilities, but at the same time increases system complexity and exposure to cyber threats, technical failures, and operational disturbances.
This paper proposes an integrated approach to modeling the security and resilience of GIS systems using artificial intelligence techniques, including machine learning, neural networks, and probabilistic modeling. The proposed framework supports automated anomaly detection, vulnerability forecasting, and assessment of the impact of disruptions on the operational continuity of geoinformatics components across data, analytical, and service layers. The model explicitly accounts for data quality, AI model stability, and API based service behavior within a unified resilience assessment structure.
Experimental results demonstrate that AI based solutions enable earlier identification of incidents and more effective analysis of GIS resilience compared to conventional methods. In particular, the proposed approach improves detection of subtle anomalies and supports systematic evaluation of cascading effects under compound disturbance scenarios. The findings confirm the potential of artificial intelligence to enhance the automation and adaptability of GIS security processes and provide a foundation for further research on intelligent, adaptive mechanisms for spatial data protection and resilient geoinformatics infrastructures.