MS1 – AI-Powered Climate-Resilient Infrastructure: Risk, Adaptation, and Life-Cycle Decision-Making

China

China

USA

USA
Session Summary
Civil infrastructure is threatened by structural aging and climate-driven hazards with increasing frequencies, intensities, which are all exacerbated by compound interactions. These shifting conditions challenge traditional assumptions of stationarity embedded in many design codes and analytical models, introducing substantial uncertainty into long-term system performance and resilience. Concurrently, rapid advances in artificial intelligence (AI), agentic AI, digital twins, physics-informed modeling, and intelligent decision-support technologies are creating new opportunities to better understand and manage infrastructure systems throughout their life cycles.
This Mini-Symposium provides a platform to explore how emerging AI technologies can be integrated with climate adaptation, reliability analysis, probabilistic risk assessment, resilience, and life-cycle management across component, system, network, and community scales. The session will highlight advances that enable systems to anticipate and adapt to evolving hazards, optimize maintenance, and strengthen resilience while balancing sustainability, societal, and economic objectives. This Mini-Symposium will bring together researchers and practitioners from structural and infrastructure engineering, climate-risk analysis, reliability, resilience, and AI to exchange methodological advances and real-world applications. Topics of interest include, but are not limited to: (1) AI, agentic AI, and physics-informed approaches for deterioration, reliability, and life-cycle performance assessment; (2) probabilistic methods for non-stationary, multi-hazard, compound, and cascading risk assessment and infrastructure management; (3) AI-enabled resilience assessment, climate adaptation, and decision-making at all scales ranging from components to full communities; (4) robust and adaptive decision frameworks integrating risk, resilience, and life-cycle cost under climate uncertainty.











































