Abstract
Abstract
Rapid, reliable assessment of building damage immediately after an earthquake is essential for prioritising search and rescue, allocating scarce resources, and establishing early situational awareness. This study develops and evaluates a deep learning classifier that uses terrestrial images—which provide critical ground‐level detail often missed by aerial or satellite views—to categorise buildings as not damaged, damaged, or collapsed. Trained on a curated corpus of post‐event building images sourced from multiple earthquakes, a ResNet50‐based model achieved 93.5 per cent overall accuracy in terms of validation. The results demonstrate the feasibility of fast, initial triage at building scale and serve to complement existing aerial/remote sensing workflows, including potential integration into crowdsourced and reconnaissance imagery streams. This approach offers a practical path to accelerating post‐event decision support while recognising that finer‐grained damage classification may be developed for later recovery phases, ultimately improving urban resilience and saving human lives during critical, time‐sensitive operations in vulnerable, disaster‐stricken communities.