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.
As cities evolve, change and grow, the need and desire for adaptable architecture becomes evident across the nation. Architecture needs to undertake techniques that are flexible in order to adapt and align with the development of future generations in New Zealand. The Education industry is a primary example of a sector which requires flexibility within both classroom architectural form and interior configuration. This is a resultant of the recently updated Ministry of Education requirements; which state that every new classroom built or renovated nationwide, must implement the MoE classroom design standards for Innovative Learning Environments. ILE teaching spaces are configured as an open plan interior, supporting flexibility in classroom arrangement and teaching techniques. ILE classrooms are capable of evolving and adapting as educational practices evolve and change, allowing schools to remain modern and future focused. As part of this movement to ILE, the Ministry of Education has also recently made an attempt to improve the quality of temporary classrooms. This has been done by looking into the initiation of a programme that utilizes relocatable classroom buildings. Relocatable classrooms have been selected for multiple reasons, primarily flexibility. Flexibility is key for a school environment as it allows the school to actively respond to fluctuating school rolls. It is anticipated that the programme will provide a faster delivery process with a standardised design that allows the classrooms to be relocated from one school to another with relative ease. Following the devastating February 2011 earthquake the Greater Christchurch Region, the Education sector is in the midst of the Canterbury Schools Rebuild Programme. As a repercussion of this natural disaster, the majority of Christchurch schools have redevelopment or rebuild projects in progress, with preliminary design phases already in action for a small group of select schools regarded as high priority. The primary funding for these projects are sourced from insurance money, implementing tight budget restrictions, affecting the architectural design, quality and speed of the construction and repair works. The available funding limits the affordable classroom options to basic teaching spaces that have been stripped back to simple architectural forms, dictating not only the re-design, but also how our future generations will learn. Thus causing the development of the new student-led learning ILE concept to become controlled by existing construction techniques and the Rebuild Programmes budget restrictions. This thesis focuses on the future proofing of New Zealand schools by providing an affordable and time efficient alternative option to the current static, traditional construction, an option that has the ability to cater to the unpredictable fluctuating school rolls across the nation. This has been done by developing a prefabricated system for standalone classroom blocks. These blocks have the ability to be relocated between different school sites, dynamically catering to the unpredictable school roll numbers experienced across New Zealand. This site flexibility is reflected with the interior flexibility in the classrooms, enhancing the internal teaching space composition and challenges the existing design standards set by the Ministry of Education for Innovative Learning Environments. This system is called “Flexi-Ed”. Flexibility has been a key driver for this thesis, as the prefabricated structure is have to be flexible in three ways; first in the sense of being easy to assemble and disassemble. Second by offering flexible interior learning environments and thirdly the joints of the structure are designed with the ability to be flexible in order to cope with seismic activity. These three principles will provide schools with long term flexibility, minimal on-site interruption and heighten the standard of ILE across the nation. I strive to provide schools with long term flexibility and minimal site interruption, whilst heightening the standard of Innovative Learning Environments across New Zealand.
