Smart Transfer: Leveraging Vision Foundation Model for Rapid Building Damage Mapping with Post-Earthquake VHR Imagery

2026-04-02

AI Summary

Traditional post-disaster damage assessment methods suffer from limited generalizability and heavy reliance on manual annotation, hindering rapid building damage mapping during the critical 72-hour post-earthquake rescue window. To address this, this work proposes the Smart Transfer framework, which leverages vision foundation models enhanced with pixel-level clustering to achieve prototype-level global feature alignment and a distance-penalized triplet loss that incorporates spatial autocorrelation to strengthen semantic proximity constraints. Evaluated on data from the 2023 Turkey–Syria earthquake, the method demonstrates superior performance in cross-domain scenarios such as LODO and SSDC, offering a scalable and automated solution for high-resolution disaster damage mapping to support timely emergency response.

Abstract

Living in a changing climate, human society now faces more frequent and severe natural disasters than ever before. As a consequence, rapid disaster response during the "Golden 72 Hours" of search and rescue becomes a vital humanitarian necessity and community concern. However, traditional disaster damage surveys routinely fail to generalize across distinct urban morphologies and new disaster events. Effective damage mapping typically requires exhaustive and time-consuming manual data annotation. To address this issue, we introduce Smart Transfer, a novel Geospatial Artificial Intelligence (GeoAI) framework, leveraging state-of-the-art vision Foundation Models (FMs) for rapid building damage mapping with post-earthquake Very High Resolution (VHR) imagery. Specifically, we design two novel model transfer strategies: first, Pixel-wise Clustering (PC), ensuring robust prototype-level global feature alignment; second, a Distance-Penalized Triplet (DPT), integrating patch-level spatial autocorrelation patterns by assigning stronger penalties to semantically inconsistent yet spatially adjacent patches. Extensive experiments and ablations from the recent 2023 Turkiye-Syria earthquake show promising performance in multiple cross-region transfer settings, namely Leave One Domain Out (LODO) and Specific Source Domain Combination (SSDC). Moreover, Smart Transfer provides a scalable, automated GeoAI solution to accelerate building damage mapping and support rapid disaster response, offering new opportunities to enhance disaster resilience in climate-vulnerable regions and communities. The data and code are publicly available at https://github.com/ai4city-hkust/SmartTransfer.

Problem

• building damage mapping
• disaster response
• generalization
• manual annotation
• VHR imagery

Innovation

• Foundation Models
• Building Damage Mapping
• Cross-domain Transfer
• Spatial Autocorrelation
• GeoAI