城市时空基础模型用于气候韧性住房：扩散变换器的扩展用于灾害风险预测
Urban Spatio-Temporal Foundation Models for Climate-Resilient Housing: Scaling Diffusion Transformers for Disaster Risk Prediction
AI总结：
本文提出Skjold-DiT模型，通过整合时空城市数据预测建筑气候风险，并结合交通网络结构提升灾害响应能力。
摘要：
气候灾害日益扰乱城市交通和应急响应操作，通过破坏住房存量、降级基础设施和减少网络可达性来实现。本文提出了Skjold-DiT，一种整合异构时空城市数据的扩散变换器框架，用于预测建筑层面的气候风险指标，同时明确纳入与智能车辆相关的交通网络结构和可达性信号（例如应急可达性和疏散路线约束）。具体而言，Skjold-DiT通过生成校准的、具有不确定性的可达性层（可达性、旅行时间膨胀和路线冗余）来实现灾害条件下的路由约束，这些层可以被智能车辆路由和应急调度系统所利用。Skjold-DiT结合了：(1) Fjell-Prompt，一个基于提示的条件化接口，旨在支持跨城市迁移；(2) Norrland-Fusion，一种跨模态注意力机制，将灾害地图/影像、建筑属性、人口统计数据和交通基础设施统一到共享的潜在表示中；以及(3) Valkyrie-Forecast，一个反事实模拟器，用于在干预提示下生成概率风险轨迹。我们介绍了包含847,392个建筑层面观测数据的波罗的海-里海城市韧性（BCUR）数据集，涵盖六个城市，包括多灾害注释（例如洪水和热指标）和交通可达性特征。实验评估了预测质量、跨城市泛化、校准以及下游与交通相关的结果，包括在反事实干预下的可达性和灾害条件下的旅行时间。
英文摘要：
Climate hazards increasingly disrupt urban transportation and emergency-response operations by damaging housing stock, degrading infrastructure, and reducing network accessibility. This paper presents Skjold-DiT, a diffusion-transformer framework that integrates heterogeneous spatio-temporal urban data to forecast building-level climate-risk indicators while explicitly incorporating transportation-network structure and accessibility signals relevant to intelligent vehicles (e.g., emergency reachability and evacuation-route constraints). Concretely, Skjold-DiT enables hazard-conditioned routing constraints by producing calibrated, uncertainty-aware accessibility layers (reachability, travel-time inflation, and route redundancy) that can be consumed by intelligent-vehicle routing and emergency dispatch systems. Skjold-DiT combines: (1) Fjell-Prompt, a prompt-based conditioning interface designed to support cross-city transfer; (2) Norrland-Fusion, a cross-modal attention mechanism unifying hazard maps/imagery, building attributes, demographics, and transportation infrastructure into a shared latent representation; and (3) Valkyrie-Forecast, a counterfactual simulator for generating probabilistic risk trajectories under intervention prompts. We introduce the Baltic-Caspian Urban Resilience (BCUR) dataset with 847,392 building-level observations across six cities, including multi-hazard annotations (e.g., flood and heat indicators) and transportation accessibility features. Experiments evaluate prediction quality, cross-city generalization, calibration, and downstream transportation-relevant outcomes, including reachability and hazard-conditioned travel times under counterfactual interventions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
