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.
While societal messages can encourage an unhealthy strive for perfection, the notion of embracing individual flaws and openly displaying vulnerabilities can appear foreign and outlandish. However, when fallibility is acknowledged and imperfection embraced, intimate relationships built on foundations of acceptance, trust and understanding can be established. In an architectural context, similar deep-rooted connections can be formed between a people and a place through the retention of layers of historical identity. When a building is allowed to age with blemishes laid bare for all to see, an architectural work can exhibit a sense of 'humanising vulnerability' where the bruises and scars it bears are able to visually communicate its contextual narrative. This thesis explores the notion of designing to capitalise on past decay through revitalisation of the former Wood Brothers Flour Mill in Addington, Christchurch (1891). Known as one of the city's last great industrial buildings, the 130-year-old structure remains hugely impressive due to its sheer size and scale despite being abandoned and subject to vandalism for a number of years. Its condition of obsolescence ensured the retention of visible signs of wear and tear in addition to the extensive damage caused by the 2010-12 Canterbury earthquakes. In offering a challenge to renovation and reconstruction as a means of conservation, this thesis asks if 'doing less' has the potential to 'do more'. How can an understanding of architecture as an ongoing process inform a design approach to celebrate ageing and patina? While the complex is undergoing redevelopment at the time of writing, the design project embraces the condition of the historic buildings in the immediate aftermath of the earthquakes and builds upon the patina of the mill and adjacent flour and grain store in developing a design for their adaptation as a micro-distillery. Research into the traditional Japanese ideology of wabi-sabi and its practical applications form the basis for a regenerative design approach which finds value in imperfection, impermanence and incompleteness. The thesis combines a literature review, precedent review and site analysis together with a design proposal. This thesis shows that adaptive reuse projects can benefit from an active collaboration with the processes of decay. Instead of a mindset where an architectural work is considered the finished article upon completion of construction, an empathetic and sensitive design philosophy is employed in which careful thought is given to the continued preservation and evolution of a structure with the recognition that evidence of past wear, tear, patina and weathering can all contribute positively to a building's future. In this fashion, rather than simply remaining as relics of the past, buildings can allow the landscape of their urban context to shape and mould them to ensure that their architectural experience can continue to be enjoyed by generations to come.
