Deep learning‐based classification of earthquake‐damaged buildings using terrestrial images

Bibliographic Data

ID21539231
AuthorsHamed Kashani (0000-0003-2479-7387, Center for Infrastructure Sustainability and Resilience Research, Department of Civil Engineering Sharif University of Technology Iran, corresponding author), Amirmohammad Sahebzadeh (Department of Civil Engineering Sharif University of Technology Iran), Mahdi Naimi Jamal (Department of Civil Engineering Sharif University of Technology Iran), Abolfazl Nazari (Department of Civil Engineering Sharif University of Technology Iran)
Year2026
Volume50
Issue4
Pagese70061-e70061
Publication date2026-10-01
Open AccessYes
TypeARTICLE
VenueDisasters (JOURNAL)
Journal identifiersISSN: 0361-3666 • E-ISSN: 1467-7717
PublisherWiley (PUBLISHER • GB)
DOI10.1111/disa.70061
PMID42376797
OpenAlexW7166692259
LanguageEN
References cited45

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

Aerial imagery · Deep learning · Poison control · Satellite imagery · Situation awareness · Triage · Disaster Management and Resilience · Remote-Sensing Image Classification · Seismology and Earthquake Studies

Tools

Open DOI