Session Description:

Geological disasters, such as earthquakes, landslides, debris flows, and ground subsidence, pose escalating threats to human life, critical infrastructure, and the global environment. The dynamic, complex, and uncertain nature of these geohazards presents significant challenges to traditional risk assessment methods, which often struggle to accurately predict their occurrence, intensity, and impact. In response, Artificial Intelligence (AI) has emerged as a transformative paradigm for addressing complex geotechnical and geological challenges. Advanced AI techniques, encompassing data analytics, machine learning, deep learning, and hybrid intelligent systems, offer unprecedented capabilities for understanding disaster mechanisms, predicting hazard evolution, and quantifying risk under uncertainty. From traditional algorithms like Random Forest and Support Vector Machines to cutting-edge approaches such as Physics-Informed Neural Networks, Graph Neural Networks, and Reinforcement Learning, AI provides a powerful toolkit for tackling the multifaceted challenges of geological disaster risk assessment.

This mini-symposium is organized in conjunction with the ongoing Special Issue on “Intelligent Risk Assessment for Geological Disasters” in the Georisk journal, aiming to bring together researchers, engineers, and practitioners to explore the latest advancements and applications of AI in disaster risk assessment, fostering collaboration and shaping future research directions. Contributions are welcomed in areas including, but not limited to:

• Advanced data analytics, such as database modeling, correlation analysis, and multi-source data fusion, for disaster risk characterization
• Novel AI and Machine Learning algorithms (e.g., Deep Learning, Physics-informed ML, Graph-based Learning) for disaster modeling and prediction
• Benchmarking, validation, and comparative studies of AI models against traditional methods (e.g., numerical simulation, empirical analysis)
• AI-driven assessment of disaster susceptibility, hazard, vulnerability, and risk
• Integration of AI with monitoring technologies (e.g., Remote Sensing, GIS, IoT) for creating intelligent early warning systems
• Explainable AI and uncertainty quantification in intelligent disaster assessment to enhance model trust and transparency
• Case studies and practical implementations of AI applications for disaster risk assessment, resource allocation, early warning, and decision support.