A deep learning approach to improve built asset operations and disaster management in critical events: an integrative simulation model for quicker decision making

Increasing levels of urbanisation and the rapid growth of modern cities require that particular attention be paid to ensuring the safety and protection of living conditions for their inhabitants. In this context, natural and human-induced disasters pose a major threat to the safety and normal operational procedures of buildings and infrastructures. In consequence, disaster management and built assets operations demand modern tools to be effectively prepared in order to better respond to such critical events. This study explores the potential of artificial intelligence in these operational fields by developing a deep learning model that is able to provide a rapid assessment of an asset's structural condition in the case of a seismic excitation. The proposed simulation model makes an accurate prediction of the damage status of individual elements in a built asset, thus leading to operational improvements across all disaster management phases. In addition, the above development integrates the deep learning algorithm into building information modelling and then uploads the graphical information to a web dashboard. By following the framework proposed, an integrative model is designed that provides a visual and user-friendly interface that allows different stakeholders to navigate and comprehend essential information on the effects of a disaster; thus enabling quicker decision making and strengthening operational resilience in critical events.

Automated summary

With increasing urbanisation and the rapid growth of modern cities, ensuring the safety and protection of living conditions for inhabitants is crucial. This study explores the potential of artificial intelligence in disaster management and built assets operations by developing a deep learning model that assesses the structural condition of assets during seismic events. The model accurately predicts the damage status of individual elements, leading to operational improvements and providing essential information for quicker decision making and strengthened operational resilience in critical events.