Blast Hazard Resilience Using Machine Learning for West Fertilizer Plant Explosion

Abstract

To investigate the effect of infrastructure traits on resilience after an exploration, a blast case (West Fertilizer Plant in West, Texas, 2013) was studied, in which all the buildings’ damage data (damage pictures, damage scales, and building locations) and resilience information (recovery decision, recovery time, and recovery cost) were collected by authors through site visits, interviews, and appraisal data collections. The novel analysis methods and machine learning algorithms (logistical/linear regression, neural networks, k-nearest neighbor, support vector machine, and gradient boosting) were applied to analyze the West Fertilizer Plant explosion resilience. This study is unique because it implements a resilience analysis for an explosion hazard, although there are some reports discussing the resilience after natural hazards, such as earthquakes, tsunamis, hurricanes, and tornados. Additionally, using machine learning for resilience analysis is also unique. The results can assist decision-makers, civil engineers, and building designers in designing the most resilient structures and/or materials for buildings. The findings in this study can help to develop the most resilient buildings, communities, and cities by considering the impact of explosion hazards.