MS Title:
Data-Driven and Hybrid Approaches for Risk and Resilience Analysis of Infrastructure

Description:
As the world confronts the challenges of urbanization, climate change, frequent natural disasters, and aging infrastructure, the need for innovative solutions to assess the risk and resilience of critical infrastructure has never been more pressing. More conventional approaches which were developed solely based on classical mechanics and physics have been used in the past decades. With the growing development of Artifical Intelligence (AI), novel data-driven approaches for risk and resilience assessment of infrastructure have been investigated as an alternative in recent years. In addition, intead of using purely black-box AI models, efforts have been made to combine data-driven techniques and physical interpretations, toward estabilishing explainable predictive models to support risk and resilience analysis of infrastructure. To this end, the aim of this mini-symposium is to address the advances in data-driven and hybrid approaches for risk and resilience analysis of infrastructure under natural hazards, aging deterioration, and other extreme disturbances. The scope of the mini-symposium is broad and will include contributions related to the following topics.

• AI-enhanced predictive modelling for infrastructure
• Physics-informed machine learning and deep learning methods in risk and resilience assessment
• Data-driven structural design and performance assessment
• Quantification of resilience for distributed infrastructure systems
• Structural damage and recovery prediction under natural and man-made disasters
   

Session Chairs:
Kaoshan Dai, Sichuan University, Chengdu, China. E-mail: kdai@scu.edu.cn
Tso-Chien Pan, Nanyang Technology University, Singapore. E-mail: CPAN@ntu.edu.sg
Henry V. Burton, University of California, Los Angeles, USA. E-mail: hvburton@seas.ucla.edu
Jianze Wang, Sichuan University, Chengdu, China. E-mail: jzwang@scu.edu.cn