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.
PurposeThe purpose of this research is to highlight the role of not-for-profit (NFP) organisations in enhancing disaster preparedness. The authors set out to understand their perspectives and practices in regard to disaster preparedness activities to support people who live precarious lives, especially those who live as single parents who are the least prepared for disasters.Design/methodology/approachThe research draws on in-depth, semi-structured interviews with 12 staff members, either in a group setting or individually, from seven NFP organisations, who were located in Ōtautahi (Christchurch) and Kaiapoi in Aotearoa New Zealand. These participants were interviewed eight years after the 2011 Christchurch earthquake.FindingsFour key narrative tropes or elements were drawn from across the interviews and were used to structure the research results. These included: “essential” support services for people living precarious lives; assisting people to be prepared; potential to support preparedness with the right materials and relationships; resourcing to supply emergency goods.Originality/valueThis research contributes to disaster risk reduction practices by advocating for ongoing resourcing of NFP groups due to their ability to build a sense of community and trust while working with precarious communities, such as single parents.
On November 14, 2016 an earthquake struck the rural districts of Kaikōura and Hurunui on New Zealand’s South Island. The region—characterized by small dispersed communities, a local economy based on tourism and agriculture, and limited transportation connections—was severely impacted. Following the quake, road and rail networks essential to maintaining steady flows of goods, visitors, and services were extensively damaged, leaving agrifood producers with significant logistical challenges, resulting in reduced productivity and problematic market access. Regional tourism destinations also suffered with changes to the number, characteristics, and travel patterns of visitors. As the region recovers, there is renewed interest in the development and promotion of agrifood tourism and trails as a pathway for enhancing rural resilience, and a growing awareness of the importance of local networks. Drawing on empirical evidence and insights from a range of affected stakeholders, including food producers, tourism operators, and local government, we explore the significance of emerging agrifood tourism initiatives for fostering diversity, enhancing connectivity, and building resilience in the context of rural recovery. We highlight the motivation to diversify distribution channels for agrifood producers, and strengthen the region’s tourism place identity. Enhancing product offerings and establishing better links between different destinations within the region are seen as essential. While such trends are common in rural regions globally, we suggest that stakeholders’ shared experience with the earthquake and its aftermath has opened up new opportunities for regeneration and reimagination, and has influenced current agrifood tourism trajectories. In particular, additional funding for tourism recovery marketing and product development after the earthquake, and an emphasis on greater connectivity between the residents and communities through strengthening rural networks and building social capital within and between regions, is enabling more resilient and sustainable futures.
