What question did this study set out to answer?

This study aims to develop a deep learning classifier to evaluate building damage after earthquakes using terrestrial images.

July 2, 2026Disasters

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

View Full Paper

Ask AI

Bookmark

This study aims to develop a deep learning classifier to evaluate building damage after earthquakes using terrestrial images.
Developed a ResNet50-based deep learning classifier
Trained on a curated corpus of post-earthquake building images from multiple earthquakes
Achieved validation accuracy of 93.5%.
Achieved 93.5% overall accuracy in building damage categorization
Demonstrated feasibility for fast initial triage
Offers potential for integration into existing aerial/remote sensing workflows.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Randomized trial develops a deep learning model for classifying building damage after earthquakes, highlighting its importance in efficient disaster response.

Cite This Study

Kashani et al. (2026) studied this question.

synapsesocial.com/papers/6a4600a29ed1343031310c6f https://doi.org/10.1111/disa.70061

View Full Paper

Ask AI

Bookmark

Implication

Randomized trial develops a deep learning model for classifying building damage after earthquakes, highlighting its importance in efficient disaster response.

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

Key Points

Discussion

Implication

Cite This Study

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

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider