AI-driven Remote Sensing for Urban Climate Resilience

Urban areas are increasingly vulnerable to climate-related risks such as extreme heat, flooding, drought, and compound environmental stresses. At the same time, rapid advances in Earth observation, thermal remote sensing, geospatial data infrastructure, and artificial intelligence are transforming how cities are monitored, modeled, and managed. AI-driven remote sensing now enables more timely, fine-scale, and scalable assessment of urban climate processes, environmental exposure, and infrastructure vulnerability. These developments create new opportunities for supporting climate adaptation, resilient urban planning, and evidence-based policy. However, challenges remain in integrating multi-source data, improving model interpretability, ensuring transferability across cities, and translating technical outputs into actionable urban governance tools. This Research Topic aims to provide a focused platform for emerging work at the intersection of AI, remote sensing, and urban climate resilience.This Research Topic seeks to address the growing need for robust, interpretable, and policy-relevant approaches to understanding and enhancing urban climate resilience through AI-driven remote sensing. Recent advances in deep learning, geospatial foundation models, multimodal data fusion, and high-resolution Earth observation have expanded the capacity to detect, predict, and evaluate urban climate risks and adaptation outcomes. Yet substantial gaps remain between methodological innovation and operational application in planning, infrastructure management, and climate governance.The goal of this collection is to bring together interdisciplinary contributions that advance both theory and practice. We welcome studies that develop new methods, evaluate real-world applications, compare urban contexts, and explore how remote sensing and AI can support decision-making under climate uncertainty. By bridging geospatial intelligence, urban science, and resilience policy, this Research Topic aims to foster reproducible, impactful, and internationally relevant research.This Research Topic welcomes original research, review articles, methods papers, case studies, data reports, and perspective articles related to AI-driven remote sensing for urban climate resilience. Topics of interest include, but are not limited to: urban heat island dynamics; thermal anisotropy; climate risk mapping; flood and drought monitoring; land surface temperature retrieval and interpretation; multi-source geospatial data fusion; explainable and trustworthy AI for Earth observation; urban climate adaptation assessment; resilient infrastructure monitoring; digital twins and geospatial decision support; and cross-city comparative studies. Contributions may focus on methodological innovation, applied urban analysis, policy support, or operational workflows. We particularly encourage submissions that connect technical advances with planning practice, governance needs, and sustainable urban development. Topic editors: Yue Chang, Yinxia Cao, Yifu Ou Source: https://www.frontiersin.org/research-topics/82446/ai-driven-remote-sensing-for-urban-climate-resilience