面向气候韧性住房的城这时空基础模型：基于扩散变换器的灾害风险预测规模化研究

Urban Spatio-Temporal Foundation Models for Climate-Resilient Housing: Scaling Diffusion Transformers for Disaster Risk Prediction

February 5, 2026

作者: Olaf Yunus Laitinen Imanov, Derya Umut Kulali, Taner Yilmaz

cs.AI

摘要

气候灾害通过损毁住房存量、破坏基础设施及降低路网可达性，正日益扰乱城市交通与应急响应系统的运行。本文提出Skjold-DiT——一种融合异构时空城市数据的扩散-变换器框架，能够预测建筑级气候风险指标，并显式纳入与智能车辆相关的交通网络结构与可达性信号（如应急可达范围与疏散路线约束）。具体而言，该框架通过生成经过校准且具备不确定性感知的可达性图层（可达范围、行程时间膨胀率及路线冗余度），为智能车辆路径规划与应急调度系统提供灾害条件约束的路径决策支持。Skjold-DiT集成三大核心组件：（1）Fjell-Prompt：基于提示词的跨城市迁移适配接口；（2）Norrland-Fusion：跨模态注意力机制，将灾害地图/影像、建筑属性、人口统计数据与交通基础设施统一至共享潜空间表征；（3）Valkyrie-Forecast：基于干预提示生成概率性风险轨迹的反事实模拟器。我们同步发布波罗的-里海城市韧性（BCUR）数据集，涵盖六座城市847,392条建筑级观测记录，包含多灾种标注（如洪涝与高温指标）及交通可达性特征。实验从预测质量、跨城市泛化能力、校准效果及下游交通相关指标（包括反事实干预下的可达性与灾害条件行程时间）四个维度进行评估。

English

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.