Physics-aware machine learning for data-driven fire risk prediction. The 2019/20 Australian fire season was unprecedented in its extent, impact, and the response of fire agencies. In this project, we aim to answer the question: was the scale of these fires driven by known drivers of fire (drought, weather, fuels and ignitions), or were fundamentally new undescribed processes and phenomena involved? We will accomplish this by developing an innovative, physics-aware machine learning model of fire ....Physics-aware machine learning for data-driven fire risk prediction. The 2019/20 Australian fire season was unprecedented in its extent, impact, and the response of fire agencies. In this project, we aim to answer the question: was the scale of these fires driven by known drivers of fire (drought, weather, fuels and ignitions), or were fundamentally new undescribed processes and phenomena involved? We will accomplish this by developing an innovative, physics-aware machine learning model of fire risk and spread, trained and validated on a two-decade satellite fire record. The predictive ability of the model will be tested on the 2019/20 fire season to determine if novel drivers of fire can be identified, and the model itself will be operationalised into a novel short-to-mid term fire risk prediction tool. Read moreRead less
Fractional dynamic models for MRI to probe tissue microstructure. This project aims to develop new mathematical tools for mapping tissue microstructural properties via the use of space-time fractional calculus methods. In magnetic resonance imaging, mathematical models and their parameters play a key role in associating information between images and biology, with the overall aim of producing spatially resolved maps of tissue property variations. However, models which can inform on changes in mi ....Fractional dynamic models for MRI to probe tissue microstructure. This project aims to develop new mathematical tools for mapping tissue microstructural properties via the use of space-time fractional calculus methods. In magnetic resonance imaging, mathematical models and their parameters play a key role in associating information between images and biology, with the overall aim of producing spatially resolved maps of tissue property variations. However, models which can inform on changes in microscale tissue properties are lacking. The tools developed by this project will be used to generate new magnetic resonance image based maps to convey information on tissue microstructure changes in the human brain. Additionally, the mathematical tools developed will be transferable to other applications where diffusion and transport in heterogeneous porous media play a role.Read moreRead less
Dynamics and control of complex social networks. This project aims to understand the extent to which a given complex social network can be controlled and how different control mechanisms influence network structure and dynamics. There is a great interest in controlling complex networks including social networks as it might contribute to solving important societal challenges. Using gender imbalance, minority marginalisation, and criminal behaviour as case studies, this project will investigate t ....Dynamics and control of complex social networks. This project aims to understand the extent to which a given complex social network can be controlled and how different control mechanisms influence network structure and dynamics. There is a great interest in controlling complex networks including social networks as it might contribute to solving important societal challenges. Using gender imbalance, minority marginalisation, and criminal behaviour as case studies, this project will investigate the direction of networks controllability and mechanisms that would enable alteration of the network in a desired way. This project will have an impact on our current understanding of network's behaviour, and will contribute to solving a range of societal challenges.Read moreRead less
An intelligent machine modelling assistant for combinatorial optimisation. This project aims to discover key fundamental technologies for automating assistance to non-expert users in the formulation of mathematical models. Through automating the modelling of combinatorial optimization problems, this research will generate new knowledge to address the fundamental challenges of automatic mathematical modelling. This intelligent assistant will enable synthesis of new mathematical models through th ....An intelligent machine modelling assistant for combinatorial optimisation. This project aims to discover key fundamental technologies for automating assistance to non-expert users in the formulation of mathematical models. Through automating the modelling of combinatorial optimization problems, this research will generate new knowledge to address the fundamental challenges of automatic mathematical modelling. This intelligent assistant will enable synthesis of new mathematical models through the utilisation of pioneering natural language processing components and novel custom-made machine-readable knowledge bases. The outcome of this research will broaden access to high-quality models by non-expert workforce and alleviate the shortage of expert mathematicians, bringing significant social and economic benefits.Read moreRead less
Quantification, optimisation, and application of deep uncertainty. This project aims to develop a framework for deep uncertainty quantification. There is currently a fundamental gap between deep learning research and the methods required to quantify and manage uncertainties. The research will propose a novel distribution-free methodology to generate deep predictive uncertainty estimates to avoid the assumptions of existing methods. The quality of estimates will be enhanced by applying an interva ....Quantification, optimisation, and application of deep uncertainty. This project aims to develop a framework for deep uncertainty quantification. There is currently a fundamental gap between deep learning research and the methods required to quantify and manage uncertainties. The research will propose a novel distribution-free methodology to generate deep predictive uncertainty estimates to avoid the assumptions of existing methods. The quality of estimates will be enhanced by applying an interval-based adversarial training step. The project is expected to help data-driven Australian organisations and industries to better quantify and manage forecasting uncertainties. This project will provide them with significant cost savings through better decision making and more robust planning.Read moreRead less
Managing infectious disease through partial wildlife social networks. This project aims to investigate the dynamics of the spread of infectious disease in wildlife, derived from incomplete information about contact networks. Infectious diseases in wildlife are difficult to track and control, because it is not feasible to monitor each individual in a population and know the contact network for a population. The project will create ways to best utilise incomplete observational data of contact netw ....Managing infectious disease through partial wildlife social networks. This project aims to investigate the dynamics of the spread of infectious disease in wildlife, derived from incomplete information about contact networks. Infectious diseases in wildlife are difficult to track and control, because it is not feasible to monitor each individual in a population and know the contact network for a population. The project will create ways to best utilise incomplete observational data of contact networks to develop robust predictions of disease spread and population fate, and to reliably predict the outcomes of management interventions. These robust prediction methods will provide better insights for conservation of Australian wildlife.Read moreRead less
Building insights of our largest terrestrial carbon sink: rangelands soils. Rangelands soils represent Australia’s largest carbon sink. Yet, little is known about their potential for carbon sequestration or their vulnerability to climate and environmental change. This project leverages investments in national terrestrial observation platforms and integrates previous research outputs to develop new methods to measure and build understanding of soil carbon composition and dynamics in rangeland eco ....Building insights of our largest terrestrial carbon sink: rangelands soils. Rangelands soils represent Australia’s largest carbon sink. Yet, little is known about their potential for carbon sequestration or their vulnerability to climate and environmental change. This project leverages investments in national terrestrial observation platforms and integrates previous research outputs to develop new methods to measure and build understanding of soil carbon composition and dynamics in rangeland ecosystems. Under a framework that connects detailed measurements and small-scale processes, with machine-learning, data-model assimilation and large-scale next-generation biogeochemical modelling, it’ll allow more accurate predictions of soil carbon change and better decision-making to guide sustainable rangelands management.Read moreRead less
Automated assessment of data quality in biological knowledge resources. This project aims to develop methods for identifying poor quality data in biological databases. Research in biomedicine is underpinned by massive databases of biological data. Data quality is largely managed through manual curation, but automated methods to assess quality are critically needed. This project expects to develop a suite of computational tools for assessing biological data quality, utilising an innovative approa ....Automated assessment of data quality in biological knowledge resources. This project aims to develop methods for identifying poor quality data in biological databases. Research in biomedicine is underpinned by massive databases of biological data. Data quality is largely managed through manual curation, but automated methods to assess quality are critically needed. This project expects to develop a suite of computational tools for assessing biological data quality, utilising an innovative approach based on network analysis of database record connectivity. These tools will enable quantifying data quality at scale. Researchers, evidence-based decision-makers in biomedicine, and the analytical or predictive tools that use this data will make more reliable inferences and decisions.Read moreRead less
Personalised public transport. This project aims to address urban congestion by utilising people’s travel plans to coordinate journeys. The project expects to generate new knowledge in scalable optimisation, based on innovative modelling of urban transport, and tested on historical data from Melbourne. The expected outcomes of the project are an active transport database and optimised mode choice and routing system, with predicted reductions in congestion based on simulation of its use. This pro ....Personalised public transport. This project aims to address urban congestion by utilising people’s travel plans to coordinate journeys. The project expects to generate new knowledge in scalable optimisation, based on innovative modelling of urban transport, and tested on historical data from Melbourne. The expected outcomes of the project are an active transport database and optimised mode choice and routing system, with predicted reductions in congestion based on simulation of its use. This project aims to design an urban trip advisory system that could be followed by automated vehicles as well as human drivers, to reduce the financial and environmental cost of current urban congestion.Read moreRead less
Individualisation for 3D Audio. The project aim is to allow the general listener to enjoy high-fidelity 3-D sound over headphones. Such 3-D audio is of paramount importance when inter-personal communication requires situational awareness, (eg search and rescue, fire-fighting, and air traffic control). To achieve this, the project aims to address one of the toughest problems in audio signal processing: deriving high-fidelity 3-D audio headphone filters from photos and/or 3D scans of ears. The pro ....Individualisation for 3D Audio. The project aim is to allow the general listener to enjoy high-fidelity 3-D sound over headphones. Such 3-D audio is of paramount importance when inter-personal communication requires situational awareness, (eg search and rescue, fire-fighting, and air traffic control). To achieve this, the project aims to address one of the toughest problems in audio signal processing: deriving high-fidelity 3-D audio headphone filters from photos and/or 3D scans of ears. The project plans to address fundamental research questions in statistical shape and data analysis and to perceptually evaluate the 3-D audio methods developed.Read moreRead less