AI-Driven Dataset

We develop scalable, AI-powered methods to generate, enhance, and validate datasets critical for urban resilience and infrastructure risk analysis. By leveraging machine learning, remote sensing, and generative models, we create high-quality, geospatially grounded datasets in data-scarce regions to support equitable and data-informed decision-making.

RoofNet: A Global Multimodal Dataset for Roof Material Classification
N. Law and Y. Miura. (2025). Under Review. [DOI] [GitHub]

We present RoofNet, the first geographically diverse dataset for global roof material classification. With over 51,500 EO image-text pairs from 184 sites and 112 countries, RoofNet enables scalable, AI-driven risk assessment of building vulnerability to natural hazards. Fine-tuned with a vision-language model (VLM) using expert annotations and prompt tuning, it supports downstream tasks in disaster preparedness, insurance, and infrastructure resilience.