Enhancing Post-Disaster Building Damage Interpretation with Multisource Data Fusion

Global disasters are becoming increasingly frequent, leading to persistent and widespread impacts on human safety, critical infrastructure, and economic activities. Therefore, emergency response and recovery decisions urgently require rapid, large-area, and reliable situational awareness. Owing to its wide coverage and timely availability, satellite-based remote sensing has become an important data source for post-disaster assessment. However, post-event observations are often missing or degraded due to harsh on-site conditions, particularly weather- and cloud-related interference, which introduces substantial uncertainty in damage interpretation. In addition, approaches that rely solely on a single data source or manual interpretation are constrained by limited timeliness and scalability, making it difficult to provide consistent and stable damage information when it is most needed. Meanwhile, damage is not only reflected by visible appearance changes. Visual evidence alone may be insufficient to capture building-level vulnerability, construction characteristics, and damage mechanisms that are not directly observable from imagery. In practice, building-level metadata are often scarce, heterogeneous, and unevenly available across regions and events. As a result, such information is rarely incorporated into existing damage assessment pipelines, which can limit the interpretability of model outputs and reduce confidence in their use for decision support.

This study proposes a Transformer-based multimodal framework for building damage assessment that integrates post-disaster optical imagery, SAR imagery, and building metadata to generate timely and explainable damage information. To strengthen operational applicability, the proposed approach is further evaluated on real-world ㄍcases from major disasters worldwide. Experimental results indicate that tokenizing heterogeneous multimodal inputs into a unified sequence representation substantially enhances architectural flexibility for cross-modality integration. Compared with conventional approaches that typically cascade or couple multiple modality-specific models to handle different data sources, our framework performs multi-source fusion within a consistent representation space and enables a simpler end-to-end design. Through multi-source data fusion and explainable analysis, the proposed framework improves the transparency and traceability of post-disaster building damage assessment, provides a more comprehensive characterization of damage conditions, and supports more robust, evidence-based response and recovery decision-making.