Climate change is creating increasingly dynamic and interconnected challenges for human–environment systems, while conventional approaches to climate-risk assessment often struggle to capture nonlinear interactions among hazards, infrastructure, human behaviour, institutions, and environmental change. Rapid advances in artificial intelligence (AI), geospatial data science, machine learning, and digital technologies provide new opportunities to understand, predict, and enhance climate resilience.

This session brings together interdisciplinary research exploring how data-driven and AI-enhanced approaches can advance the assessment, modelling, and practice of climate resilience. We particularly welcome contributions that move beyond conventional vulnerability and risk assessment toward understanding adaptive capacity, resilience dynamics, and pathways for proactive adaptation. Topics include GeoAI and spatial-temporal data analytics; AI-enhanced climate-impact and resilience modelling; integration of machine learning with agent-based and other process-based models; human mobility, behaviour, and social networks; urban digital twins and interactive visual analytics; remote sensing and Earth observation; data-driven assessment of adaptation potential; and AI-supported planning and decision-making.

We encourage empirical, theoretical, methodological, and applied contributions across different hazards, spatial scales, and geographical contexts. Particular interest lies in approaches that integrate physical and social data, combine data-driven and knowledge-driven modelling, incorporate stakeholder and human dimensions, or translate AI-based insights into actionable adaptation strategies.

By bringing together researchers from climate science, geography, environmental science, data science, AI, and related disciplines, the session aims to advance a human-centred and solution-oriented research agenda for climate resilience and explore how emerging technologies can support more effective, adaptive, and sustainable responses to climate change.