Major disasters such as wildfire, tornado, hurricane, tropical storm, flooding cause disruptions in infrastructure systems such as power outage, disruption to water supply system, wastewater management, telecommunication failures, and transportation facilities. Disruptions in electricity infrastructures have negative impacts on sectors throughout a region, including education, medical services, financial, and recreation sectors. In this study, we introduce a novel approach to investigate the factors which can be associated with longer restoration time of power service after a hurricane. Considering restoration time as the dependent variable and utilizing a comprehensive set of county-level data, we have estimated a Generalized Accelerated Failure Time (GAFT) model that accounts for spatial dependence among observations for time to event data. The model fit improved by 12% after considering the effects of spatial correlation in time to event data. Using GAFT model and Hurricane Irma's impact on Florida as a case study, we examined: (1) differences in electric power outages and restoration rates among different types of power companies: investor-owned power companies, rural and municipal cooperatives; (2) the relationship between the duration of power outage and power system variables; (3) the relationship between the duration of power outage and socioeconomic attributes. The findings of this study indicate that counties with a higher percentage of customers served by investor-owned electric companies and lower median household income, faced power outage for a longer time. This paper identifies the key factors to predict restoration time of hurricane-induced power outages, allowing disaster management agencies to adopt strategies required for restoration process.

Real-time crash prediction is a complex task, since there is no existing framework to predict crash likelihood, types, and severity together along with a real-time traffic management strategy. Developing such a framework presents various challenges, including not independent and identically distributed data, imbalanced data, large model size, high computational cost, missing data, sensitivity vs. false alarm rate (FAR) trade-offs, estimation of traffic restoration time after crash occurrence, and real-world deployment strategy. A novel spatial ensemble distillation learning modeling technique is proposed to address these challenges. First, large-scale real-time data were used to develop a crash likelihood prediction model. Second, the proposed crash likelihood model's viability in predicting specific crash types was tested for real-world applications. Third, the framework was extended to predict crash severity in real-time, categorizing crashes into four levels. The results demonstrated strong performance with sensitivities of 90.35%, 94.80%, and 84.23% for all crashes, rear-end crashes, and sideswipe/angle crashes, and 83.32%, 81.25%, 83.08%, and 84.59% for fatal, severe, minor injury, and PDO crashes, respectively, all while remaining very low FARs. This methodology can also reduce model size, lower computation costs, improve sensitivity, and decrease FAR. These results will be used by traffic management center for taking measures to prevent crashes in real-time through active traffic management strategies. The framework was further extended for efficient traffic management after any crash occurrence despite adopting these strategies. Particularly, the framework was extended to predict the traffic state after a crash, predict the traffic restoration time based on the estimated post-crash traffic state, and apply a three-step validation technique to evaluate the performance of the developed approach. Finally, real-world deployment strategies of the proposed methodologies for real-time crash prediction along with their types and severities and real-time post-crash management are discussed. Overall, the methodologies presented in this dissertation offer multifaceted novel contributions and have excellent potential to reduce fatalities and injuries.