AI-Derived Structural Building Intelligence for Urban Resilience: An Application in Saint Vincent and the Grenadines

2025-09-17

AI Summary

Small Island Developing States (SIDS), such as those in the Caribbean, face significant challenges in hazard risk assessment and resilience planning for hurricanes and floods due to the scarcity of high-resolution building structure data. To address this, we propose a lightweight AI-driven remote sensing framework that integrates a geospatial foundation model with a shallow classifier, augmented by a novel cross-island transfer learning strategy to enhance generalization in data-scarce regions. Compared to end-to-end fine-tuning, our approach achieves F1 scores of 0.88 and 0.83 on roof slope and roofing material classification tasks, respectively—substantially improving automated building attribute identification. The framework enables scalable, low-cost, building-level risk modeling in resource-constrained settings, offering a new evidence-based paradigm for urban resilience governance.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Detailed structural building information is used to estimate potential damage from hazard events like cyclones, floods, and landslides, making them critical for urban resilience planning and disaster risk reduction. However, such information is often unavailable in many small island developing states (SIDS) in climate-vulnerable regions like the Caribbean. To address this data gap, we present an AI-driven workflow to automatically infer rooftop attributes from high-resolution satellite imagery, with Saint Vincent and the Grenadines as our case study. Here, we compare the utility of geospatial foundation models combined with shallow classifiers against fine-tuned deep learning models for rooftop classification. Furthermore, we assess the impact of incorporating additional training data from neighboring SIDS to improve model performance. Our best models achieve F1 scores of 0.88 and 0.83 for roof pitch and roof material classification, respectively. Combined with local capacity building, our work aims to provide SIDS with novel capabilities to harness AI and Earth Observation (EO) data to enable more efficient, evidence-based urban governance.

Problem

• Lack of structural building data in small island developing states for disaster risk assessment
• Need to automatically extract rooftop attributes from satellite imagery using AI methods
• Improving urban resilience planning through AI-derived building intelligence in vulnerable regions

Innovation

• AI workflow infers rooftop attributes from satellite imagery
• Compares geospatial foundation models with fine-tuned deep learning
• Incorporates training data from neighboring islands to improve performance