AI-Driven Geospatial Technologies for Disaster Risk Assessment, Monitoring, and Management

Natural hazards and climate-related extremes, including floods, droughts, wildfires, landslides, earthquakes, land subsidence, sinkholes, coastal hazards, and extreme weather events, increasingly threaten human and environmental systems. Satellite Earth observation and GIS have become essential tools for detecting, mapping, and monitoring these hazards across multiple spatial and temporal scales. At the same time, the rapid development of artificial intelligence has substantially expanded our ability to extract meaningful information from complex and high-dimensional geospatial datasets.The integration of AI with remote sensing and GIS enables automated feature extraction, susceptibility and hazard mapping, change detection, forecasting, exposure and vulnerability assessment, and rapid post-disaster analysis. However, challenges remain regarding model interpretability, uncertainty, transferability, data integration, reproducibility, and the transformation of analytical outputs into practical decision-support information.The increasing frequency, intensity, and complexity of natural and climate-related hazards pose significant challenges to communities, infrastructure, ecosystems, and sustainable development worldwide. Effective disaster risk reduction requires timely, spatially explicit, and reliable information for understanding hazards, identifying exposed elements, assessing vulnerability, monitoring rapidly evolving events, and supporting informed decision-making. Recent advances in artificial intelligence (AI), Earth observation, remote sensing, Geographic Information Systems (GIS), and geospatial data science provide unprecedented opportunities to transform conventional approaches to disaster risk assessment and management.This Research Topic welcomes original and innovative contributions addressing the integration of artificial intelligence, remote sensing, GIS, and geospatial technologies for disaster risk assessment, monitoring, and management. Relevant themes include, but are not limited to:•AI, machine learning, and deep learning for hazard susceptibility, prediction, and risk mapping;•GeoAI and explainable AI for disaster risk assessment and environmental applications;•Satellite, UAV, LiDAR, SAR/InSAR, and multi-source Earth observation for disaster monitoring;•Flood, drought, wildfire, landslide, earthquake, land subsidence, sinkhole, coastal, and climate-related hazard assessment;•Multi-hazard and cascading-risk assessment;•Hazard, exposure, vulnerability, resilience, and integrated disaster risk modeling;•Spatiotemporal analysis, change detection, early warning, and rapid damage assessment;•Big geospatial data, cloud computing, and automated Earth observation workflows;•Uncertainty, explainability, validation, reproducibility, and transferability of AI-based geospatial models;•GIS-based decision-support systems, risk-informed planning, disaster preparedness, mitigation, response, and recovery; and•Digital twins and emerging geospatial technologies for disaster resilience.We welcome Original Research, and Review articles that provide methodological advances, practical applications, comparative evaluations, or interdisciplinary frameworks relevant to environmental hazards and disaster risk reduction. Topic editors: Osman Orhan, Vahdettin Demir Source: https://www.frontiersin.org/research-topics/85241/ai-driven-geospatial-technologies-for-disaster-risk-assessment-monitoring-and-management