AI-Driven Multi-Scale Pathways for Enhancing Urban Infrastructure Resilience

Global urban infrastructure systems are increasingly exposed to complex challenges arising from climate change, aging assets, and rapid urbanization. Enhancing resilience requires not only system-level strategies, but also a deeper understanding of infrastructure performance across multiple scales: from material behavior under extreme conditions to structural response, and network-level functionality. In this context, artificial intelligence (AI) is emerging as a powerful tool to integrate data-driven approaches with physics-based insights, enabling more reliable, adaptive, and sustainable urban infrastructure systems.Recent advances demonstrate the potential of AI to bridge scales by linking material degradation mechanisms, structural health monitoring, and system-level resilience assessment. However, significant challenges remain in integrating multi-source data, coupling physics-informed models with machine learning, improving prediction accuracy under complex and uncertain conditions, and translating these insights into practical solutions for infrastructure management and urban resilience.This Research Topic aims to showcase cutting-edge research on AI-driven approaches for enhancing the resilience and long-term performance of urban infrastructure, with a particular emphasis on multi-scale integration. From materials and components to structures and interconnected urban systems. We welcome contributions that combine experimental, computational, and data-driven methods to advance the understanding, monitoring, and optimization of infrastructure in real-world urban environments.Submissions may include experimental studies, simulation-based research, or theoretical developments, particularly those addressing infrastructure behavior under operational and extreme conditions.Topics of interest include, but are not limited to:• AI-driven analysis of material performance and degradation under thermal, mechanical, and environmental loading• Multi-scale modeling linking material behavior, structural response, and infrastructure system performance• AI-based structural health monitoring, damage detection, and reliability assessment• Physics-informed and hybrid AI models for infrastructure performance prediction• Infrastructure vulnerability, risk, and cascading failure analysis• Resilience assessment and optimization of urban infrastructure systems• Integration of AI with advanced simulation, sensing, and data-driven frameworks• Decision-support tools for resilient infrastructure planning and lifecycle management Topic editors: Chongsen Ma, Zhiyuan Zhou, Lina Wu, Zhaochao Li Source: https://www.frontiersin.org/research-topics/79601/ai-driven-multi-scale-pathways-for-enhancing-urban-infrastructure-resilience