1. Background and Objectives This poster presents results from ground motion simulations of small-to-moderate magnitude (3.5≤Mw≤5.0) earthquake events in the Canterbury, New Zealand region using the Graves and Pitarka (2010,2015) methodology. Subsequent investigation of systematic ground motion effects highlights the prediction bias in the simulations which are also benchmarked against empirical ground motion models (e.g. Bradley (2013)). In this study, 144 earthquake ruptures, modelled as point sources, are considered with 1924 quality-assured ground motions recorded across 45 strong motion stations throughout the Canterbury region, as shown in Figure 1. The majority of sources are Mw≥4.0 and have centroid depth (CD) 10km or shallower. Earthquake source descriptions were obtained from the GeoNet New Zealand earthquake catalogue. The ground motion simulations were performed within a computational domain of 140km x 120km x 46km with a finite difference grid spacing of 0.1km. The low-frequency (LF) simulations utilize the 3D Canterbury Velocity Model while the high-frequency (HF) simulations utilize a generic regional 1D velocity model. In the LF simulations, a minimum shear wave velocity of 500m/s is enforced, yielding a maximum frequency of 1.0Hz.
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.
