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.
The skills agenda has grown in prominence within the construction industry. Indeed, skill shortages have been recognised as a perennial problem the construction industry faces, especially after a major disaster. In the aftermath of the Christchurch earthquakes, small and medium construction companies were at the forefront of rebuilding efforts. While the survival of these companies was seen to be paramount, and extreme events were seen to be a threat to survival, there is a dearth of research centring on their resourcing capacity following a disaster. This research aims to develop workforce resourcing best practice guidelines for subcontractors in response to large disaster reconstruction demands. By using case study methods, this research identified the challenges faced by subcontracting businesses in resourcing Christchurch recovery projects; identified the workforce resourcing strategies adopted by subcontracting businesses in response to reconstruction demand; and developed a best practice guideline for subcontracting businesses in managing the workforce at the organisational and/or project level. This research offers a twofold contribution. First, it provides an overview of workforce resourcing practices in subcontracting businesses. This understanding has enabled the development of a more practical workforce resourcing guideline for subcontractors. Second, it promotes evidence-informed decision-making in subcontractors’ workforce resourcing. Dynamics in workforce resourcing and their multifaceted interactions were explicitly depicted in this research. More importantly, this research provides a framework to guide policy development in producing a sustainable solution to skill shortages and establishing longterm national skill development initiatives. Taken together, this research derives a research agenda that maps under-explored areas relevant for further elaboration and future research. Prospective researchers can use the research results in identifying gaps and priority areas in relation to workforce resourcing.
This thesis is a creative and critical exploration of how transmedia storytelling meshes with political documentary’s nature of representing social realities and goals to educate and promote social change. I explore this notion through Obrero (“worker”), my independently produced transmedia and transjournalistic documentary project that explores the conditions and context of the Filipino rebuild workers who migrated to Christchurch, New Zealand after the earthquake in 2011. While the project should appeal to New Zealanders, it is specifically targeted at an audience from the Philippines. Obrero began as a film festival documentary that co-exists with strategically refashioned Web 2.0 variants, a social network documentary and an interactive documentary (i-doc). Using data derived from the production and circulation of Obrero, I interrogate how the documentary’s variants engage with differing audiences and assess the extent to which this engagement might be effective. This thesis argues that contemporary documentary needs to re-negotiate established film aesthetics and practices to adapt in the current period of shifting technologies and fragmented audiences. Documentary’s migration to new media platforms also creates a demand for filmmakers to work with a transmedia state of mind—that is, the capacity to practise the old canons of documentary making while comfortably adjusting to new media production praxis, ethics, and aesthetics. Then Obrero itself, as the creative component of this thesis, becomes an instance of research through creative practice. It does so in two respects: adding new knowledge about the context, politics, and experiences of the Filipino workers in New Zealand; and offering up a broader model for documentary engagement, which I analyse for its efficacy in the digital age.
