Uncertainty, Risk and Related Concepts in Machine Learning. Machine learning is the science of making sense of data. It does not and cannot remove all risk and uncertainty. This project proposes to study the foundations of how machine learning uses, represents and communicates risk and uncertainty. It aims to do so by finding new theoretical connections between diverse notions that have arisen in allied disciplines. These include risk, uncertainty, scoring rules and loss functions, divergences, ....Uncertainty, Risk and Related Concepts in Machine Learning. Machine learning is the science of making sense of data. It does not and cannot remove all risk and uncertainty. This project proposes to study the foundations of how machine learning uses, represents and communicates risk and uncertainty. It aims to do so by finding new theoretical connections between diverse notions that have arisen in allied disciplines. These include risk, uncertainty, scoring rules and loss functions, divergences, statistics and different ways of aggregating information. By building a more complete theoretical map it is expected that new machine learning methods will be developed, but more importantly that machine learning will be able to be better integrated into larger socio-technical systems.Read moreRead less
Towards a superannuation system fit for the future. Towards a superannuation system fit for the future. This project aims to develop a stochastic superannuation model and propose alternative post retirement solutions, using data-led understanding of savings habits. Funding for the increasing cost of the growing older population will, if not modelled, forecast and managed adequately, swamp all other welfare and state funded costs. To manage older age costs adequately, governments need to encourag ....Towards a superannuation system fit for the future. Towards a superannuation system fit for the future. This project aims to develop a stochastic superannuation model and propose alternative post retirement solutions, using data-led understanding of savings habits. Funding for the increasing cost of the growing older population will, if not modelled, forecast and managed adequately, swamp all other welfare and state funded costs. To manage older age costs adequately, governments need to encourage people to save and provide ways people can save—but need to better understand how people save money for their old age. This research is expected to enable the “superannuation change“ necessary for the superannuation system to remain sustainable and fund retirees to live well.Read moreRead less
Feature Learning for High-dimensional Functional Time Series. This project aims to develop new methods and theories for common features on high-dimensional functional time series observed in empirical applications. The significance includes addressing a key gap in adaptive and efficient feature learning, improving forecasting accuracy and understanding forecasting-driven factors comprehensively for empirical data. Expected outcomes involve advances in big data theory and easy-to-implement algori ....Feature Learning for High-dimensional Functional Time Series. This project aims to develop new methods and theories for common features on high-dimensional functional time series observed in empirical applications. The significance includes addressing a key gap in adaptive and efficient feature learning, improving forecasting accuracy and understanding forecasting-driven factors comprehensively for empirical data. Expected outcomes involve advances in big data theory and easy-to-implement algorithms for applied researchers. This project benefits not only advanced manufacturing by finding optimal stopping time for wood panel compression, but also superior forecasting for mortality in demography, climate data in environmental science, asset returns in finance, and electricity consumption in economics. Read moreRead less
Reliable and accurate statistical solutions for modern complex data. This project aims to develop novel methods for reliable and accurate statistical modelling with modern, complex correlated and error-prone data. The project expects to make significant strides towards future-proofing statistical data analysis, equipping practitioners with a suite of robust and computationally efficient methods which provide confidence in the stability and reproducibility of results obtained, while offering guar ....Reliable and accurate statistical solutions for modern complex data. This project aims to develop novel methods for reliable and accurate statistical modelling with modern, complex correlated and error-prone data. The project expects to make significant strides towards future-proofing statistical data analysis, equipping practitioners with a suite of robust and computationally efficient methods which provide confidence in the stability and reproducibility of results obtained, while offering guarantees on their transferability over a range of populations. This will provide important benefits as they are applied in predicting endangered marine species for fisheries conservation, and in enhancing our national understanding of the relationship between education achievement and financial success. Read moreRead less
Nowcasting and Interpreting the Australian Economy. This project aims to investigate methods for nowcasting and interpreting the Australian economy. This is determining the current state of the economy and the factors contributing to it.
This project expects to generate new knowledge on how unconventional, new, data sources and innovative methods can be used to in nowcasting and how the Australian economy can be modelled.
The expected outcomes include timely new indicators of the state of the ec ....Nowcasting and Interpreting the Australian Economy. This project aims to investigate methods for nowcasting and interpreting the Australian economy. This is determining the current state of the economy and the factors contributing to it.
This project expects to generate new knowledge on how unconventional, new, data sources and innovative methods can be used to in nowcasting and how the Australian economy can be modelled.
The expected outcomes include timely new indicators of the state of the economy, and the factors contributing to it. This should provide significant benefits through informing the conduct of Australian macroeconomic policy, as the appropriate policy response depends not only on knowing the current state of the economy but understanding the economic factors underlying it.
Read moreRead less
Building Australia's next-generation ocean-sea ice model. Ocean and sea ice models are used for predicting future ocean and climate states, and for climate process research. This project aims to bring the next generation of ocean-sea ice models to Australia and configure the models for our local priorities. The ultimate goal is to create a new coupled ocean-sea ice model for Australia that includes surface waves and biogeochemistry. The model will be optimised and evaluated on Australian facilit ....Building Australia's next-generation ocean-sea ice model. Ocean and sea ice models are used for predicting future ocean and climate states, and for climate process research. This project aims to bring the next generation of ocean-sea ice models to Australia and configure the models for our local priorities. The ultimate goal is to create a new coupled ocean-sea ice model for Australia that includes surface waves and biogeochemistry. The model will be optimised and evaluated on Australian facilities, and released for community use. These developments underpin future ocean state forecasts, sea ice forecasts, wave forecasts, decadal climate prediction and climate process studies. The project will benefit search and rescue, Defence and shipping operations, and will enhance future climate projections.Read moreRead less
New methods in spectral geometry. This project aims to use methods from mathematical scattering theory to resolve problems in the spectral analysis and index theory of differential operators. Both areas underpin the theoretical understanding of physical materials at micro length scales where quantum phenomena dominate. The project will develop new mathematical results in spectral analysis and geometry, and apply its results to theoretical models of quantum phenomena whose spectral properties are ....New methods in spectral geometry. This project aims to use methods from mathematical scattering theory to resolve problems in the spectral analysis and index theory of differential operators. Both areas underpin the theoretical understanding of physical materials at micro length scales where quantum phenomena dominate. The project will develop new mathematical results in spectral analysis and geometry, and apply its results to theoretical models of quantum phenomena whose spectral properties are at the limit of the range of mathematical techniques. Solving these problems is expected to influence non-commutative analysis.Read moreRead less
ARC Centre of Excellence for Climate Extremes. This Centre aims to transform understanding of past and present climate extremes and revolutionise Australia’s capability to predict them into the future. Climate extremes cost Australia up to $4 billion a year and will intensify over coming decades. This Centre’s blue-sky research will discover processes that explain the behaviour of present and future climate extremes. It will use its researchers, data, modelling, collaboration, graduate programme ....ARC Centre of Excellence for Climate Extremes. This Centre aims to transform understanding of past and present climate extremes and revolutionise Australia’s capability to predict them into the future. Climate extremes cost Australia up to $4 billion a year and will intensify over coming decades. This Centre’s blue-sky research will discover processes that explain the behaviour of present and future climate extremes. It will use its researchers, data, modelling, collaboration, graduate programme and early career researcher mentoring to transform Australia’s capacity to predict climate extremes. This research is expected to make Australia more resilient to climate extremes and minimise risks from climate extremes to the Australian environment, society and economy.Read moreRead less
Resilience of eucalypts to future droughts. This project aims to examine how resilient Eucalyptus species are to future droughts by combining data synthesis, manipulative experiments and modelling. Climate change is expected to increase the frequency, magnitude and duration of future droughts, with major environmental and socio-economic consequences for Australia. Current predictive capacity is extremely limited: experiments are limited in scale and cannot capture important global change interac ....Resilience of eucalypts to future droughts. This project aims to examine how resilient Eucalyptus species are to future droughts by combining data synthesis, manipulative experiments and modelling. Climate change is expected to increase the frequency, magnitude and duration of future droughts, with major environmental and socio-economic consequences for Australia. Current predictive capacity is extremely limited: experiments are limited in scale and cannot capture important global change interactions, whilst models do not represent the functional characteristics and adaptions of eucalypts. This project will develop a strong evidence- and process-based understanding to quantify the functional behaviour of drought-adapted Eucalyptus species and leverage this insight to make future model projections.Read moreRead less
Southern Ocean aerosols: sources, sinks and impact on cloud properties. This project aims to provide fundamental process-level understanding of atmospheric aerosol processes over the Southern Ocean, a region that has a profound influence on the Australian and global climate and where climate models perform poorly. Comprehensive observations during 3 Southern Ocean voyages and land-based measurements will enhance our knowledge of aerosols and cloud formation in that region and provide much-needed ....Southern Ocean aerosols: sources, sinks and impact on cloud properties. This project aims to provide fundamental process-level understanding of atmospheric aerosol processes over the Southern Ocean, a region that has a profound influence on the Australian and global climate and where climate models perform poorly. Comprehensive observations during 3 Southern Ocean voyages and land-based measurements will enhance our knowledge of aerosols and cloud formation in that region and provide much-needed data for improving global climate models. Expected outcomes include more accurate seasonal and latitudinal representations of Southern Ocean aerosol populations, properties and sources. The main benefit includes improvements in weather forecasting and future climate projection for Australia and the Southern Hemisphere.Read moreRead less