Machine Learning-Based Classification for Rapid Seismic Damage Assessment of Buildings at a Regional Scale

The damage assessment of numerous buildings after the earthquake is still a challenge by traditional methods as it requires a significant amount of time and resources for carrying out building-by-building seismic damage assessment. This study presents the machine learning (ML)-based damage assessment of buildings after an earthquake. The applicability of the machine learning model will be limited considering only structural properties or ground motion characteristics. Thus, in this study, the applicability of different machine learning techniques is explored using real-world earthquake damage datasets considering both the structural properties and ground motion characteristics. Initially, the entire dataset is used to train the ML models to classify the building's damage into five categories ranging from null to slight damage to collapse. Later, the dataset is divided into three traffic light damage tags: green, yellow, and red. The performance of the ML model to classify the building's damage into three damage tags is found better than that of classifying it into five damage categories. This research aims to be beneficial in planning and decision-making for emergency response and recovery following an earthquake.

Automated summary

This study examines the damage assessment of buildings after an earthquake using machine learning techniques, exploring the applicability of different methods by considering both structural properties and ground motion characteristics. The results show that classifying the damage into three categories performs better than classifying it into five categories. This research contributes to planning and decision-making for emergency response and recovery following an earthquake.