The rapid classification of building damage states or placards after an earthquake is vital for enabling an efficient emergency response and informed decision-making for rehabilitation and recovery purposes. Traditional methods rely heavily on inspector-led on-site surveys, which are often time-consuming, resource-intensive, and susceptible to human error. This study introduces a machine learning-supported surrogate model designed to streamline the assessment of building damage, focusing on the automated assignment of damage placards within the context of New Zealand's post-earthquake evaluation frameworks. The study evaluates two key safety evaluation protocols—Rapid Building Assessment (RBA) and Detailed Damage Evaluation (DDE)—and integrates corresponding databases derived from the 2010–2011 Canterbury Earthquake Sequence (CES) in Christchurch. Six ML classifiers—Multilayer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Gradient Boosting Classifier (GBC), and Gradient Bagging (GBag)—were rigorously tested across both databases. The results indicate that the RF-based surrogate model outperforms the other classifiers across both RBA and DDE protocols. Two distinct sets of critical predictors have been further identified for each protocol, allowing for the rapid retrieval of essential data for future on-site surveys, while retaining the RF model's predictive accuracy. The developed surrogate model provides a pragmatic tool for practising engineers to rapidly assign placards to damaged structures and for policymakers and building owners to make informed recovery decisions for earthquake-affected buildings.
Road networks are highly exposed to natural hazard events, which can lead to significant economic and social consequences. In New Zealand, events such as the 2011 Christchurch earthquake, the 2016 Kaikōura earthquake, and the Cyclone Gabrielle in 2023 have demonstrated the severe consequences of road network disruptions. Traditional post event economic assessments often focus solely on clean-up and repair costs, neglecting the broader and more enduring impacts these events can have. Furthermore, business cases for resilience investments usually fail when quantifying the economic benefits of mitigation strategies, due to the underestimation of road disruption consequences. Importantly, not all road link disruptions contribute equally to these consequences, making the identification of critical road links a key step in resilience focused investment prioritization. Furthermore, traditional transportation asset management typically evaluates the life cycle of roads under normal conditions, such as traffic loads and standard environmental factors, while neglecting the influence of natural hazards. However, these events can significantly alter road deterioration and increase maintenance costs, emphasizing the need for integrating risk and resilience into transportation asset management approaches. This thesis presents a methodology to evaluate road criticality by assessing the economic consequences of road disruptions in combination with a hazard model in a prioritization index. Initially, the consequences are quantified through increased travel time, higher vehicle operating costs, and increased gas emissions. Thereafter, a new consequence model is introduced to estimate the increase in maintenance costs on alternative routes that absorb diverted traffic following a disruption. These consequence models are initially applied in a 'full-scan' analysis approach, where each road link is removed in turn to quantify its potential impact and, therefore, its criticality. Subsequently, a hazard model is integrated to develop a road prioritization index that combines the expected impacts of road disruptions, the individual road link criticality, and the probability of occurrence of natural hazard events. This index is designed to help road agencies in prioritizing mitigation strategies. Furthermore, the proposed methodology can also be applied to quantify the indirect economic impacts of natural hazard events. The methodology is demonstrated using New Zealand’s South Island inter-urban network as a case study, incorporating an earthquake-induced landslide model, with Python based simulations, providing road agencies a valuable tool to quantify the economic benefits of resilience investments.
