Search

found 91 results

Research papers, The University of Auckland Library

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.

Videos, UC QuakeStudies

A video of a presentation by Dr Duncan Webb, Partner at Lane Neave, during the third plenary of the 2016 People in Disasters Conference. The presentation is titled, "Loss of Trust and other Earthquake Damage".The abstract for this presentation reads as follows: It was predictable that the earthquakes which hit the Canterbury region in 2010 and 2011 caused trauma. However, it was assumed that recovery would be significantly assisted by governmental agencies and private insurers. The expectation was that these organisations would relieve the financial pressures and associated anxiety caused by damage to property. Some initiatives did exactly that. However, there are many instances where difficulties with insurance and related issues have exacerbated the adverse effects of the earthquakes on people's wellness. In some cases, stresses around property issues have become and independent source of extreme anxiety and have had significant impacts on the quality of people's lives. Underlying this problem is a breakdown in trust between citizen and state, and insurer and insured. This has led to a pervading concern that entitlements are being denied. While such concerns are sometimes well founded, an approach which is premised on mistrust is frequently highly conflicted, costly, and often leads to worse outcomes. Professor Webb will discuss the nature and causes of these difficulties including: the complexity of insurance and repair issues, the organisational ethos of the relevant agencies, the hopes of homeowners and the practical gap which commonly arises between homeowner expectation and agency response. Observations will be offered on how the adverse effects of these issues can be overcome in dealing with claimants, and how such matters can be managed in a way which promotes the wellness of individuals.