A dynamical systems theory approach to machine learning. Forecasting the future state of a high-dimensional complex multi-scale system is a challenge we face in areas ranging from climate science to epidemiology. Even when basic physical mechanisms have been identified, the actual evolution equations are often unknown. This project will develop a computationally cheap machine learning framework for forecasting. The proposed mathematical framework provides a forecast together with a quantificati ....A dynamical systems theory approach to machine learning. Forecasting the future state of a high-dimensional complex multi-scale system is a challenge we face in areas ranging from climate science to epidemiology. Even when basic physical mechanisms have been identified, the actual evolution equations are often unknown. This project will develop a computationally cheap machine learning framework for forecasting. The proposed mathematical framework provides a forecast together with a quantification of its uncertainty. We will develop sophisticated mathematical theory underpinning the novel methodology, as well as applying it to the perennial problem of subgrid-scale parametrisation of tropical convection, a missing key element in current climate models.Read moreRead less
Three-dimensional atmospheric acoustic tomography using unmanned aerial vehicles. This project will develop technology that uses the sound of a small robotic aircraft as it passes overhead to visualise a complex array of properties of the intervening atmosphere in three dimensions. This will allow measurements to be taken in otherwise inaccessible locations and improve the understanding of atmospheric dynamics and meteorological phenomena.
Uncertainties in coherent transport of particles and intrinsic properties. This Project aims to quantify the uncertainty of a model output in terms of uncertainties in modelling assumptions, by developing new mathematical techniques and applying them to real-world data. This will be in the context of assessing the accuracy of tracking coherently moving structures (e.g., hurricanes, oceanic biodiversity hotspots, pollutant patches, insect swarms) from experimental/observational data sets. Novel, ....Uncertainties in coherent transport of particles and intrinsic properties. This Project aims to quantify the uncertainty of a model output in terms of uncertainties in modelling assumptions, by developing new mathematical techniques and applying them to real-world data. This will be in the context of assessing the accuracy of tracking coherently moving structures (e.g., hurricanes, oceanic biodiversity hotspots, pollutant patches, insect swarms) from experimental/observational data sets. Novel, data-tested, mathematical methods for uncertainty quantification of coherent structures will be developed as Project outcomes. Project benefits include new insights into protecting the environment, improved uncertainty quantification in climate modelling, and the generation of interdisciplinary knowledge and training.Read moreRead less
Digitally-Integrated Smart Sensing of Diverse Airborne Grass Pollen Sources. Grass pollen is the main outdoor allergen source globally, triggering hayfever and asthma in up to 500 million people. With over 10,000 species, the influence of grass type, location and climate on pollen in the air is not yet known. This is a key issue since subtropical and temperate grasses differ in response to environmental factors. The project aims to use artificial intelligence on digital camera images to learn to ....Digitally-Integrated Smart Sensing of Diverse Airborne Grass Pollen Sources. Grass pollen is the main outdoor allergen source globally, triggering hayfever and asthma in up to 500 million people. With over 10,000 species, the influence of grass type, location and climate on pollen in the air is not yet known. This is a key issue since subtropical and temperate grasses differ in response to environmental factors. The project aims to use artificial intelligence on digital camera images to learn to see local grass flowers and integrate this with air sensors trained to detect grass pollen types. The expected outcomes are new capacities to track airborne grass pollen types. These outcomes can transform how pollen can be monitored to reduce the burden of allergies, and provide evidence of changing airborne pollen loads.
Read moreRead less
Interactions between small scale cyclones and sea ice and their role in the Southern Ocean climate system. The Southern Ocean cyclone belt has a strong influence on Australian weather and climate. This project will allow improvements in the understanding of intense small scale cyclones in the region. Importantly, the research will highlight key sensitivities in the coupling between these atmospheric circulations and the underlying sea ice. Further, the compilation of an updated Southern Ocean cy ....Interactions between small scale cyclones and sea ice and their role in the Southern Ocean climate system. The Southern Ocean cyclone belt has a strong influence on Australian weather and climate. This project will allow improvements in the understanding of intense small scale cyclones in the region. Importantly, the research will highlight key sensitivities in the coupling between these atmospheric circulations and the underlying sea ice. Further, the compilation of an updated Southern Ocean cyclone climatology will provide a basis for evaluating future changes in cyclone distribution and frequency of occurrence in the Antarctic region. Finally, by leading this unique international collaboration with German and US scientists, the profile of Australian scientists in Antarctic atmospheric research will be strongly enhanced.Read moreRead less
Forecasting and management using imperfect models, with a focus on weather and climate. Research into complex systems is predicted to be the focus of twenty-first century science, since most of the problems of simple systems are solved. Examples include the weather and climate, economies, argriculture, ecologies, the mind and brain, genetics, biochemistry. Confidence in the reliability and usefulness of models will have significant bearing on how these models are used by decision making and how ....Forecasting and management using imperfect models, with a focus on weather and climate. Research into complex systems is predicted to be the focus of twenty-first century science, since most of the problems of simple systems are solved. Examples include the weather and climate, economies, argriculture, ecologies, the mind and brain, genetics, biochemistry. Confidence in the reliability and usefulness of models will have significant bearing on how these models are used by decision making and how the community perceives the value of this science. Specific immediate benefits of the project include better policy and management responses to climate change and servere weather events.Read moreRead less
Synthesis of dynamics, stochastics and information in forecasting and management of complex systems. Research into complex systems is predicted to be the focus of twenty-first century science, since most of the problems of simple systems are solved. Examples include the weather and climate, economies, agriculture, ecologies, the mind and brain, genetics, biochemistry. Confidence in the reliability and usefulness of models will have significant bearing on how these models are used by decision ma ....Synthesis of dynamics, stochastics and information in forecasting and management of complex systems. Research into complex systems is predicted to be the focus of twenty-first century science, since most of the problems of simple systems are solved. Examples include the weather and climate, economies, agriculture, ecologies, the mind and brain, genetics, biochemistry. Confidence in the reliability and usefulness of models will have significant bearing on how these models are used by decision making and how the community perceives the value of this science. Specific immediate benefits of the project include better policy and management responses to climate change and severe weather events.Read moreRead less
A low-cost water vapour profiler for the lower troposphere. Water vapour plays an important role in weather forecasting, as well as being the most important greenhouse gas. Its distribution is not known in sufficient detail for many aspects of predicting weather and climate change. With the Bureau of Meteorology we will develop a low-cost laser ranging system to measure the profile of water vapour in the lower atmosphere. A low-cost instrument can be placed at a sufficient number of locations ....A low-cost water vapour profiler for the lower troposphere. Water vapour plays an important role in weather forecasting, as well as being the most important greenhouse gas. Its distribution is not known in sufficient detail for many aspects of predicting weather and climate change. With the Bureau of Meteorology we will develop a low-cost laser ranging system to measure the profile of water vapour in the lower atmosphere. A low-cost instrument can be placed at a sufficient number of locations to significantly enhance weather forecasting and climate modelling. The instrument will be useful for detecting fog formation, measuring cloudbase heights and can be adapted for pollution detection and measurement.Read moreRead less
Open Agent Architectures for Intelligent Distributed Decision Making. Sophisticated software systems are part of the essential infrastructure of our daily lives. Complex systems such as the internet, finance, or telecommunications software cannot have a centralised point of control or a single developer. The aim of this project is to develop an architecture and support infrastructure enabling intelligent agents to locate and use services in such open systems. The fundamental questions that must ....Open Agent Architectures for Intelligent Distributed Decision Making. Sophisticated software systems are part of the essential infrastructure of our daily lives. Complex systems such as the internet, finance, or telecommunications software cannot have a centralised point of control or a single developer. The aim of this project is to develop an architecture and support infrastructure enabling intelligent agents to locate and use services in such open systems. The fundamental questions that must be addressed include issues such as how agents will find and use newly added services and how services will communicate with each other, given that they are developed independently.Read moreRead less
The dynamics and predictability of fire weather over southern Australia. As illustrated by the recent Victorian bushfires, Australia has one of the most severe fire climates in the world. Fires play a major role in modifying our landscape, affecting native flora and fauna, and damaging infrastructure and property. Effective fire fighting and fire management relies heavily on the prediction of fire weather and the impact of atmospheric conditions on fire behaviour. This project investigates some ....The dynamics and predictability of fire weather over southern Australia. As illustrated by the recent Victorian bushfires, Australia has one of the most severe fire climates in the world. Fires play a major role in modifying our landscape, affecting native flora and fauna, and damaging infrastructure and property. Effective fire fighting and fire management relies heavily on the prediction of fire weather and the impact of atmospheric conditions on fire behaviour. This project investigates some of the key processes that cause local enhancements in fire weather in regions of complex terrain like southern Australia.Read moreRead less