5 papers · 1 filter
DisasterLex: An Expert Concept-to-Schema Knowledge Graph for Geospatial Reasoning in Disaster Analytics
Yiming Xiao, Ankit Basu, Kai Yin +3
Disasters are inevitable and increasingly costly, and effective response depends on querying structured tabular data: precise, information-dense records of hazard, exposure, vulner…
Training-free retrieval-augmented generation with reinforced reasoning for flood damage nowcasting
Lipai Huang, Kai Yin, Chia-Fu Liu +1
We propose R2RAG-Flood, a training-free retrieval-augmented generation framework for flood damage nowcasting with reinforced reasoning. The framework builds a reasoning-centric kno…
WildfireGenome: Interpretable Machine Learning Reveals Local Drivers of Wildfire Risk and Their Cross-County Variation
Chenyue Liu, Ali Mostafavi
Current wildfire risk assessments rely on coarse hazard maps and opaque machine learning models that optimize regional accuracy while sacrificing interpretability at the decision s…
Unsupervised Graph Deep Learning Reveals Emergent Flood Risk Profile of Urban Areas
Kai Yin, Junwei Ma, Ali Mostafavi
Urban flood risk emerges from complex and nonlinear interactions among multiple features related to flood hazard, flood exposure, and social and physical vulnerabilities, along wit…
FloodDamageCast: Building Flood Damage Nowcasting with Machine Learning and Data Augmentation
Chia-Fu Liu, Lipai Huang, Kai Yin +2
Near-real time estimation of damage to buildings and infrastructure, referred to as damage nowcasting in this study, is crucial for empowering emergency responders to make informed…