Democratisation of Deep Learning: Neural Architecture Search at Low Cost. The need to manually design Deep Learning-based Neural Networks (DNNs) limits their usage to AI experts and hinders the exploitation of their true potential more broadly, e.g., in farming, humanities. We aim to replace this tedious process through novel AI methods capable of generating DNNs that can perform significantly better and at a lower computational cost than manually designed DNNs. We further expand this idea to so ....Democratisation of Deep Learning: Neural Architecture Search at Low Cost. The need to manually design Deep Learning-based Neural Networks (DNNs) limits their usage to AI experts and hinders the exploitation of their true potential more broadly, e.g., in farming, humanities. We aim to replace this tedious process through novel AI methods capable of generating DNNs that can perform significantly better and at a lower computational cost than manually designed DNNs. We further expand this idea to solve complex real-world problems with both labelled and unlabelled data found in various applications including energy and climate change. The expected outcomes include the novel AI methods, highly trained AI researchers and a number of critical applications that will bring significant benefits to Australia and the world.Read moreRead less
A novel and efficient approach for optimisation involving iterative solvers. Computationally expensive simulations involving iterative solvers are increasingly being used in industry to assess performance of products and processes. Repeated use of such simulations is necessary to identify optimum solutions. Even with today's computing power, many such tasks remain computationally prohibitive. This project presents a novel approach to solve optimisation problems involving iterative solvers with l ....A novel and efficient approach for optimisation involving iterative solvers. Computationally expensive simulations involving iterative solvers are increasingly being used in industry to assess performance of products and processes. Repeated use of such simulations is necessary to identify optimum solutions. Even with today's computing power, many such tasks remain computationally prohibitive. This project presents a novel approach to solve optimisation problems involving iterative solvers with limited computing budget. A wide range of industries involved in product and process design would gain a significant competitive advantage from this unique technical innovation. In addition, this technology will be invaluable to uncover and understand complex natural phenomena.Read moreRead less
Adaptive modelling of human responses in complex interaction. This project aims to combine strengths of human cognition and evolutionary computing to efficiently solve problems which neither can do alone. The project will develop techniques combining advanced non-intrusive sensor measures of behaviour and emotional reaction in interaction tasks to enable high level computer support for human goal seeking, in complex data and design environments. This project will allow non-expert users to use to ....Adaptive modelling of human responses in complex interaction. This project aims to combine strengths of human cognition and evolutionary computing to efficiently solve problems which neither can do alone. The project will develop techniques combining advanced non-intrusive sensor measures of behaviour and emotional reaction in interaction tasks to enable high level computer support for human goal seeking, in complex data and design environments. This project will allow non-expert users to use tools normally requiring extensive training in settings where the user can 'see' when they get something they like but do not know how to instruct a computer system to show or do it. Applications of the project will include visualisation for bespoke manufacturing or for high dimensional data, generating abstract art, or improving teleconferencing systems.Read moreRead less
Temperature sensitivity of soil respiration and its components. This project aims to demonstrate how temperate evergreen forests could buffer against climate change. Soil respiration returns around half the carbon taken up by forests to the atmosphere. This project will characterise and quantify how microbes and roots in soils depend on temperature and substrate supply, and so predict how rising temperatures and drought will affect forests as natural carbon sequestration sinks. This project will ....Temperature sensitivity of soil respiration and its components. This project aims to demonstrate how temperate evergreen forests could buffer against climate change. Soil respiration returns around half the carbon taken up by forests to the atmosphere. This project will characterise and quantify how microbes and roots in soils depend on temperature and substrate supply, and so predict how rising temperatures and drought will affect forests as natural carbon sequestration sinks. This project will resolve the roles of environmental drivers of soil respiration across forests; integrate mechanistic understanding of differing plant and microbial responses to temperature within a common modelling framework; and evaluate the implications of this knowledge in predictions of climatic impacts on terrestrial carbon cycling.Read moreRead less
Linking terrestrial–aquatic fluxes to rectify the Australian carbon balance. This project aims to rectify the Australian carbon balance by determining the amount of terrestrial carbon that is lost to streams and rivers across the country. Through a novel integration of high-resolution hydrochemical and gas measurements, remote sensing and machine learning algorithms, the project intends to generate new knowledge about the links between terrestrial carbon sequestration and aquatic carbon export. ....Linking terrestrial–aquatic fluxes to rectify the Australian carbon balance. This project aims to rectify the Australian carbon balance by determining the amount of terrestrial carbon that is lost to streams and rivers across the country. Through a novel integration of high-resolution hydrochemical and gas measurements, remote sensing and machine learning algorithms, the project intends to generate new knowledge about the links between terrestrial carbon sequestration and aquatic carbon export. Expected outcomes include a refined estimate of the net carbon sequestration potential across Australian biomes and seasons. This should provide significant benefits such as avoiding misalignment of greenhouse gas abatement policies and advancing carbon cycling models and predictions.Read moreRead less