The design of adaptation strategies that promote urban health and well-being in the face of climate change requires an understanding of the feedback interactions that take place between the dynamical state of a city, the health of its people, and the state of the planet. Complexity, contingency and uncertainty combine to impede the growth of such systemic understandings. In this paper we suggest that the collaborative development of conceptual models can help a group to identify potential leverage points for effective adaptation. We describe a three-step procedure that leads from the development of a high-level system template, through the selection of a problem space that contains one or more of the group’s adaptive challenges, to a specific conceptual model of a sub-system of importance to the group. This procedure is illustrated by a case study of urban dwellers’ maladaptive dependence on private motor vehicles. We conclude that a system dynamics approach, revolving around the collaborative construction of a set of conceptual models, can help communities to improve their adaptive capacity, and so better meet the challenge of maintaining, and even improving, urban health in the face of climate change.

Rapid increases in the world’s population, increased urban density and increased congestion have created upwards pressure that has seen traffic-related pollution growing at a rapid pace. As atmospheric pollution has a proven detrimental effect on human health and decreases the ambience and general liveability of the world’s cities. Developing, deciding and implementing effective atmospheric pollution and mitigation strategies has become of the utmost importance to policy-makers around the world. Alongside the increase in urban densification, there has been a rapid increase in Smart City infrastructure, made possible by harnessing data from low-cost sensors that can report information in a timely, dependable and accurate manner. This paper proposes a decision support system (DSS) that uses an underlying traffic model to inform an atmospheric dispersion model. Mitigation strategies can then be tested within the DSS through simulation of strategies in the underlying traffic model and analysing the effect on the forecasted atmospheric pollution levels. The proposed DSS is used to detect a critical level of atmospheric pollution and then may respond via the implementation of full road closures. While a partial road closure is not incorporated in this paper it is a trivial extension and diverting a subsection of the polluting traffic (e.g. heavy trucks) may be an easier policy to implement. The paper demonstrates the ability of the DSS to prevent atmospheric pollution from reaching hazardous levels and inform policy-makers as to when and where mitigation treatments should be implemented for the best outcome.

As part of a curriculum reform process, The Australian National University (ANU) is introducing a universal undergraduate requirement that responds to decades-long calls for universities to take seriously the development of expertise in the transdisciplinary problem solving required to address the major challenges facing society. Described here are the process and outcomes of the deliberations of the working group tasked with setting parameters for the implementation of this expertise. The working group identified relevant context, including that the requirement has to work for all of the University’s 13,000 undergraduate students, allowing them to tailor coursework in transdisciplinary problem solving according to their disciplinary choices, personal interests and career aspirations. The expertise is to be developed in existing and new courses, featuring small classes with flexible interactive delivery and should build on the University’s comprehensive coverage of academic disciplines and fields, along with the university’s strong track records in transdisciplinary research and education. The working group developed an ANU framework for transdisciplinary problem solving, focused on the following six characteristics: change-oriented, systemic, context-based, pluralistic, interactive and integrative. How these characteristics can be translated into learning outcomes is demonstrated, along with relevant ways of teaching. The working group highlighted two key challenges that those involved in the mechanics of the implementation will have to deal with and proposed a way forward for the first of them. One is for students to be able to readily identify relevant courses. The working group proposed a tag-and-points system, with the ‘tag’ identifying courses relevant to transdisciplinary problem solving and ‘points’ indicating the number of characteristics covered and the depth of that coverage. The second challenge is coordination across courses to minimise duplication and maximise the opportunity to keep building skills. The paper concludes by summarising key areas that may be useful to others deliberating on the expertise required for university graduates to effectively contribute to addressing societal challenges, as well as how universities can best foster the development of that expertise.

Capstone projects have been an established vehicle of student–industry engagement in a university setting. In engineering, capstone projects are a point of transition from student to professional, as student engineers gain practical work experience and apply their technical skills and knowledge for an industry-proposed design, research, and/or development challenge. In this paper, we report on a supplementary program—the Technical Leadership Program (TLP)—which was designed and delivered for students to hone their technical leadership skills within a capstone project. To report on the outcomes of this case study, we use a student-as-partners philosophy to share the case study as a series of vignettes from co-authors who participated in the TLP. These have been collated into four key thematic areas including building awareness through technical leadership; building a personal repertoire of leadership; creating a common platform for collaboration; and transitioning into a professional workplace environment. The reflections are then shown to map to relevant competencies in technical leadership. Alongside these themes, the paper shares the design of the TLP delivery and reflects on the challenges and benefits of this mechanism to enhance student experience.

Predicting hospital length of stay (LoS) stands as a critical factor in shaping public health strategies. This data serves as a cornerstone for governments to discern trends, patterns, and avenues for enhancing healthcare delivery. In this study, we introduce a robust hybrid deep learning model, a combination of Multi-layer Convolutional (CNNs) deep learning, Gated Recurrent Units (GRU), and Dense neural networks, that outperforms 11 conventional and state-of-the-art Machine Learning (ML) and Deep Learning (DL) methodologies in accurately forecasting inpatient hospital stay duration. Our investigation delves into the implementation of this hybrid model, scrutinising variables like geographic indicators tied to caregiving institutions, demographic markers encompassing patient ethnicity, race, and age, as well as medical attributes such as the CCS diagnosis code, APR DRG code, illness severity metrics, and hospital stay duration. Statistical evaluations reveal the pinnacle LoS accuracy achieved by our proposed model (CNN-GRU-DNN), which averages at 89% across a 10-fold cross-validation test, surpassing LSTM, BiLSTM, GRU, and Convolutional Neural Networks (CNNs) by 19%, 18.2%, 18.6%, and 7%, respectively. Accurate LoS predictions not only empower hospitals to optimise resource allocation and curb expenses associated with prolonged stays but also pave the way for novel strategies in hospital stay management. This avenue holds promise for catalysing advancements in healthcare research and innovation, inspiring a new era of precision-driven healthcare practices.