Urban Spatio-Temporal Foundation Models for Climate-Resilient Housing: Scaling Diffusion Transformers for Disaster Risk Prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908816693526528 |
|---|---|
| author | Imanov, Olaf Yunus Laitinen Kulali, Derya Umut Yilmaz, Taner |
| author_facet | Imanov, Olaf Yunus Laitinen Kulali, Derya Umut Yilmaz, Taner |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06129 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Urban Spatio-Temporal Foundation Models for Climate-Resilient Housing: Scaling Diffusion Transformers for Disaster Risk Prediction Imanov, Olaf Yunus Laitinen Kulali, Derya Umut Yilmaz, Taner Machine Learning Artificial Intelligence 68T07, 62P12, 62M45 I.2.6; I.2.10; H.2.8 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. |
| title | Urban Spatio-Temporal Foundation Models for Climate-Resilient Housing: Scaling Diffusion Transformers for Disaster Risk Prediction |
| topic | Machine Learning Artificial Intelligence 68T07, 62P12, 62M45 I.2.6; I.2.10; H.2.8 |
| url | https://arxiv.org/abs/2602.06129 |