The rapid classification of building damage states or placards after an earthquake is vital for enabling an efficient emergency response and informed decision-making for rehabilitation and recovery purposes. Traditional methods rely heavily on inspector-led on-site surveys, which are often time-consuming, resource-intensive, and susceptible to human error. This study introduces a machine learning-supported surrogate model designed to streamline the assessment of building damage, focusing on the automated assignment of damage placards within the context of New Zealand's post-earthquake evaluation frameworks. The study evaluates two key safety evaluation protocols—Rapid Building Assessment (RBA) and Detailed Damage Evaluation (DDE)—and integrates corresponding databases derived from the 2010–2011 Canterbury Earthquake Sequence (CES) in Christchurch. Six ML classifiers—Multilayer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Gradient Boosting Classifier (GBC), and Gradient Bagging (GBag)—were rigorously tested across both databases. The results indicate that the RF-based surrogate model outperforms the other classifiers across both RBA and DDE protocols. Two distinct sets of critical predictors have been further identified for each protocol, allowing for the rapid retrieval of essential data for future on-site surveys, while retaining the RF model's predictive accuracy. The developed surrogate model provides a pragmatic tool for practising engineers to rapidly assign placards to damaged structures and for policymakers and building owners to make informed recovery decisions for earthquake-affected buildings
Many contemporary urban communities are challenged by increased flood risks and rising temperatures, declining water quality and biodiversity, and reduced mental, physical, cultural and social wellbeing. The development of urban blue-green infrastructure (BGI), defined as networks of natural and semi-natural blue-green spaces which enable healthy ecosystem processes, has been identified as one approach to mitigate these challenges and enable more liveable cities. Multiple benefits associated with urban BGI have been identified, including reduced flood risk and temperatures, improved water quality and biodiversity, enhanced mental and physical wellbeing, strengthened social cohesion and sense of place, and the facilitation of cultural connections and practices. However, socio-cultural benefits have tended to be neglected in BGI research and design, resulting in a lack of awareness of how they may be maximised in BGI design. As such, this research sought to understand how BGI can best be designed to enable liveable cities. Four questions were considered: (i) what benefits are associated with urban BGI, (ii) how does the design process influence the benefits achieved by BGI, (iii) what challenges are encountered during BGI design, and (iv) how might the incorporation of communities and Indigenous knowledge into BGI research and design enhance current understandings and applications of urban BGI? To address these questions, a mixed methods case study approach was employed in Ōtautahi Christchurch and Kaiapoi. The four selected case studies were Te Oranga Waikura, Wigram Basin, Te Kuru and the Kaiapoi Honda Forest. The cases are all council owned urban wetlands which were primarily designed or retrofitted to reduce urban flood risks following the Canterbury Earthquake Sequence. To investigate BGI design processes in each case, as well as how communities interact with, value and benefit from these spaces. BGI projects were found to be designed by interdisciplinary design teams driven by stormwater engineers, landscape architects and ecologists which prioritised bio-physical outcomes. Further, community and Indigenous engagement approaches closely resembled consultation, with the exception of Te Kuru which employed a co-design approach between councils and Indigenous and community groups. This co-design approach was found to enhance current understandings and applications of urban BGI, while uncovering multiple socio-cultural values to be incorporated into design, such as access to cultural healing resources, increased community connections to water, and facilitating cultural monitoring methodologies and citizen science initiatives. Communities frequently identified the opportunity to connect with natural environments and enhanced mental and physical wellbeing as key benefits of BGI. Conversely, strengthened social cohesion, sense of place and cultural connections were infrequently identified as benefits, if at all. This finding indicates a disconnect between the bio-physical benefits which drive BGI design and the outcomes which communities value. As such, there is a need for future BGI design to more fully consider and design for socio- cultural outcomes to better enable liveable cities. To better design BGI to enhance urban liveability, this research makes three key contributions. First, there is a need to advance current approaches to transdisciplinary design to better account for the full scope of perspectives and values associated with BGI. Second, there is a need to transition towards relational co-design with Indigenous and community groups and knowledge. Third, it is important to continue to monitor, reflect on and share both positive and negative BGI design experiences to continually improve outcomes. The incorporation of social and cultural researchers, knowledges and perspectives into open and collaborative transdisciplinary design teams is identified as a key method to achieve these opportunities.
