Machine Learning Model for Post-Earthquake Building Damage Evaluation
Model to classify the level of building damage after earthquakes, using high-resolution satellite imagery of underdeveloped areas.
Enable faster and more accurate search & rescue efforts, where there is limited infrastructure and access.
Research Partner (2nd author): Zhanming Yang
Mentored by: Dr. David Woodruff, Professor of Computer Science at Carnegie Melon University, CIS Neoscholar Program 2024 Summer
Rapid assessment of building damage following earthquakes, is particularly challenging in rural regions due to limited infrastructure and accessibility.
Traditional methods like field surveys are time-consuming and labor-intensive
This can serve as an effective tool for directing resources and planning recovery, for emergency responders and aid agencies, ultimately reducing loss, harm and improving disaster resilience
Paper Accepted by:
3rd International Conference on Mechatronics and Smart Systems (CONF-MSS 2025). It will be published in Applied and Computational Engineering (ACE) (Print ISSN 2755-2721)