This thesis presents the application of data science techniques, especially machine learning, for the development of seismic damage and loss prediction models for residential buildings. Current post-earthquake building damage evaluation forms are developed for a particular country in mind. The lack of consistency hinders the comparison of building damage between different regions. A new paper form has been developed to address the need for a global universal methodology for post-earthquake building damage assessment. The form was successfully trialled in the street ‘La Morena’ in Mexico City following the 2017 Puebla earthquake. Aside from developing a framework for better input data for performance based earthquake engineering, this project also extended current techniques to derive insights from post-earthquake observations. Machine learning (ML) was applied to seismic damage data of residential buildings in Mexico City following the 2017 Puebla earthquake and in Christchurch following the 2010-2011 Canterbury earthquake sequence (CES). The experience showcased that it is readily possible to develop empirical data only driven models that can successfully identify key damage drivers and hidden underlying correlations without prior engineering knowledge. With adequate maintenance, such models have the potential to be rapidly and easily updated to allow improved damage and loss prediction accuracy and greater ability for models to be generalised. For ML models developed for the key events of the CES, the model trained using data from the 22 February 2011 event generalised the best for loss prediction. This is thought to be because of the large number of instances available for this event and the relatively limited class imbalance between the categories of the target attribute. For the CES, ML highlighted the importance of peak ground acceleration (PGA), building age, building size, liquefaction occurrence, and soil conditions as main factors which affected the losses in residential buildings in Christchurch. ML also highlighted the influence of liquefaction on the buildings losses related to the 22 February 2011 event. Further to the ML model development, the application of post-hoc methodologies was shown to be an effective way to derive insights for ML algorithms that are not intrinsically interpretable. Overall, these provide a basis for the development of ‘greybox’ ML models.
Many buildings with relatively low damage from the 2010-2011 Canterbury were deemed uneconomic to repair and were replaced [1,2]. Factors that affected commercial building owners’ decisions to replace rather than repair, included capital availability, uncertainty with regards to regional recovery, local market conditions and ability to generate cash flow, and repair delays due to limited property access (cordon). This poster provides a framework for modeling decision-making in a case where repair is feasible but replacement might offer greater economic value – a situation not currently modeled in engineering risk analysis.
Natural catastrophes are increasing worldwide. They are becoming more frequent but also more severe and impactful on our built environment leading to extensive damage and losses. Earthquake events account for the smallest part of natural events; nevertheless seismic damage led to the most fatalities and significant losses over the period 1981-2016 (Munich Re). Damage prediction is helpful for emergency management and the development of earthquake risk mitigation projects. Recent design efforts focused on the application of performance-based design engineering where damage estimation methodologies use fragility and vulnerability functions. However, the approach does not explicitly specify the essential criteria leading to economic losses. There is thus a need for an improved methodology that finds the critical building elements related to significant losses. The here presented methodology uses data science techniques to identify key building features that contribute to the bulk of losses. It uses empirical data collected on site during earthquake reconnaissance mission to train a machine learning model that can further be used for the estimation of building damage post-earthquake. The first model is developed for Christchurch. Empirical building damage data from the 2010-2011 earthquake events is analysed to find the building features that contributed the most to damage. Once processed, the data is used to train a machine-learning model that can be applied to estimate losses in future earthquake events.
The latest two great earthquake sequences; 2010- 2011 Canterbury Earthquake and 2016 Kaikoura Earthquake, necessitate a better understanding of the New Zealand seismic hazard condition for new building design and detailed assessment of existing buildings. It is important to note, however, that the New Zealand seismic hazard map in NZS 1170.5.2004 is generalised in effort to cover all of New Zealand and limited to a earthquake database prior to 2001. This is “common” that site-specific studies typically provide spectral accelerations different to those shown on the national map (Z values in NZS 1170.5:2004); and sometimes even lower. Moreover, Section 5.2 of Module 1 of the Earthquake Geotechnical Engineering Practice series provide the guidelines to perform site- specific studies.
The 2010-2011 Canterbury earthquake sequence, and the resulting extensive data sets on damaged buildings that have been collected, provide a unique opportunity to exercise and evaluate previously published seismic performance assessment procedures. This poster provides an overview of the authors’ methodology to perform evaluations with two such assessment procedures, namely the P-58 guidelines and the REDi Rating System. P-58, produced by the Federal Emergency Management Agency (FEMA) in the United States, aims to facilitate risk assessment and decision-making by quantifying earthquake ground shaking, structural demands, component damage and resulting consequences in a logical framework. The REDi framework, developed by the engineering firm ARUP, aids stakeholders in implementing resilience-based earthquake design. Preliminary results from the evaluations are presented. These have the potential to provide insights on the ability of the assessment procedures to predict impacts using “real-world” data. However, further work remains to critically analyse these results and to broaden the scope of buildings studied and of impacts predicted.
