Time-evolving traffic resilience performance forecasting during hazardous weather toward proactive intervention

Transportation systems experience significant disruptions and loss during hazardous weather events, exhibiting great needs of timely intervention to effectively improve the resilience of the affected traffic systems. An informed and science-based proactive intervention strategy depends on accurate forecasting of the resilience performance of traffic systems with essential lead time during hazards. A new resilience performance forecasting methodology at both global and local scales is proposed for traffic networks under natural hazards by addressing unique challenges such as scarcity and time-evolving nature of hazard-specific data. The proposed methodology consists of two modules: the local traffic resilience performance short-term forecasting module based on the modified diffusion convolutional recurrent neural network (DCRNN) and transfer learning techniques, and the global traffic resilience performance forecasting module integrating percolation-based robustness assessment and SIR-based congestion propagation modeling. A case study of an urban traffic network during a major snowstorm hazard is conducted as a demonstration, followed by the feasibility investigation to guide proactive intervention during hazards. It is found the proposed methodology can forecast the time-evolving traffic resilience performance with good accuracy at both global and local scales. With sufficient lead time for the forecast, it bears promising potential to assist the stakeholders to make informed and timely decision about possible proactive intervention by providing key information to help identify the optimal moments and individual strategic links for possible intervention.