Developing a Framework for Post-disaster Livelihood Recovery

Research papers, The University of Auckland Library

As damage and loss caused by natural hazards have increased worldwide over the past several decades, it is important for governments and aid agencies to have tools that enable effective post-disaster livelihood recovery to create self-sufficiency for the affected population. This study introduces a framework of critical components that constitute livelihood recovery and the critical factors that lead to people’s livelihood recovery. A comparative case study is employed in this research, combined with questionnaire surveys and interviews with those communities affected by large earthquakes in Lushan, China and in Christchurch and Kaikōura, New Zealand. In Lushan, China, a framework with four livelihood components was established, namely, housing, employment, wellbeing and external assistance. Respondents considered recovery of their housing to be the most essential element for livelihood diversification. External assistance was also rated highly in assisting with their livelihood recovery. Family ties and social connections seemed to have played a larger role than that of government agencies and NGOs. However, the recovery of livelihood cannot be fully achieved without wellbeing aspects being taken into account, and people believed that quality of life and their physical and mental health were essential for livelihood restoration. In Christchurch, New Zealand, the identified livelihood components were validated through in-depth interviews. The results showed that the above framework presenting what constitutes successful livelihood recovery could also be applied in Christchurch. This study also identified the critical factors to affect livelihood recovery following the Lushan and Kaikōura earthquakes, and these include community safety, availability of family support, level of community cohesion, long-term livelihood support, external housing recovery support, level of housing recovery and availability of health and wellbeing support. The framework developed will provide guidance for policy makers and aid agencies to prioritise their strategies and initiatives in assisting people to reinstate their livelihood in a timely manner post-disaster. It will also assist the policy makers and practitioners in China and New Zealand by setting an agenda for preparing for livelihood recovery in non-urgent times so the economic impact and livelihood disruption of those affected can be effectively mitigated

A machine learning-supported rapid classification of building damage follo…

Research papers, The University of Auckland Library

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