Search

Despite the considerable success of deep learning methods in modelling physical processes, they suffer from a variety of issues such as overfitting and lack of interpretability. In hydrology, conceptual rainfall-runoff models are simple yet fast and effective tools to represent the underlying physical processes through lumped storage components. Although conceptual rainfall-runoff models play a vital role in supporting decision-making in water resources management and urban planning, they have limited flexibility to take data into account for the development of robust region-wide models. The combination of deep learning and conceptual models has the potential to address some of the aforementioned limitations. This paper presents a sub-model hybridization of the GR4J rainfall-runoff model with deep learning architectures such as convolutional neural networks (CNN) and long short-term memory (LSTM) networks. The results show that the hybrid models outperform both the base conceptual model as well as the canonical deep neural network architectures in terms of the Nash–Sutcliffe Efficiency (NSE) score across 223 catchments in Australia. We show that our hybrid model provides a significant improvement in predictive performance, particularly in arid catchments, and generalizing better across catchments. • Hybrid modelling features parsimony of data-driven and conceptual hydrologic models. • We present a deep learning-based hybridization for the GR4J rainfall-runoff model. • We present a hierarchical training approach consisting of gradient-based and evolutionary optimization of the respective models. • The results show that hybrid models outperform the canonical (base) hydrologic and deep learning model. • The addition of surface temperature and antecedent streamflow further improves the predictive performance. [ABSTRACT FROM AUTHOR]

Background: Systems science methods such as dynamic simulation modelling are well suited to address questions about public health policy as they consider the complexity, context and dynamic nature of system-wide behaviours. Advances in technology have led to increased accessibility and interest in systems methods to address complex health policy issues. However, the involvement of policy decision makers in health-related simulation model development has been lacking. Where end-users have been included, there has been limited examination of their experience of the participatory modelling process and their views about the utility of the findings. This paper reports the experience of end-user decision makers, including senior public health policy makers and health service providers, who participated in three participatory simulation modelling for health policy case studies (alcohol related harm, childhood obesity prevention, diabetes in pregnancy), and their perceptions of the value and efficacy of this method in an applied health sector context., Methods: Semi-structured interviews were conducted with end-user participants from three participatory simulation modelling case studies in Australian real-world policy settings. Interviewees were employees of government agencies with jurisdiction over policy and program decisions and were purposively selected to include perspectives at different stages of model development., Results: The 'co-production' aspect of the participatory approach was highly valued. It was reported as an essential component of building understanding of the modelling process, and thus trust in the model and its outputs as a decision-support tool. The unique benefits of simulation modelling included its capacity to explore interactions of risk factors and combined interventions, and the impact of scaling up interventions. Participants also valued simulating new interventions prior to implementation in the real world, and the comprehensive mapping of evidence and its gaps to prioritise future research. The participatory aspect of simulation modelling was time and resource intensive and therefore most suited to high priority complex topics with contested options for intervening., Conclusion: These findings highlight the value of a participatory approach to dynamic simulation modelling to support its utility in applied health policy settings.