We currently have 16 committed and excited PhD candidates working on Centre projects. DARE HDR’s have an understanding of the foundations of data science, for example a qualification in mathematics, statistics, computer science or a strong quantitative background such as engineering, econometrics or earth sciences.
The DARE PhD candidates are undertaking a cohort based learning and professional development program including advanced data science. Candidates may also undertake field work in rural and regional Australia as part of their one-year industry placement. Opportunities for conference presentations, exchange study with the Alan Turing Institute (UK) and employment in industry or government at the end of the program are also available. Stipends support candidatures of three years, with the opportunity to spend some of the time (up to one year) in an industry placement programme, applying their data science skills to support best possible evidence-based management of the nation’s natural resources.
We are no longer looking for DARE PhD candidates for this program, however we have many thesis topics on offer for those future students interested in Data Science.
The following proposals are developed in collaboration with the Natural Resources Commission (NRC), a DARE industry partner. The projects aim to develop Data Science skills and tools to protect Australia’s natural resources and make the best possible evidence-based decisions in exploiting and stewarding them.
This project will work closely with WildCount, a large-scale wildlife monitoring program run by National Parks and Wildlife Service, NSW Government and the School of Life and Environmental Sciences, University of Sydney. It will test the feasibility of using machine learning algorithms for identifying species in camera trap images and the impacts of the 2019/20 mega-fires on identifying species from images taken from burnt landscapes.
This project will provide land managers with trained deep learning models to rapidly identify species within camera trap surveys to urgently monitor post-fire recovery.
This project will use Bayesian Networks to model complex interconnected systems such as forest structures. There are several data science techniques that need to be developed in order to estimate model parameters, such as graph structures or topologies and make inference about them. This PhD thesis will develop novel simulation techniques for marginalisation to improve estimation efficiency as well as develop new models for the dependency between different types of data.
In forest systems with closed canopy cover, there is a reduction in the amount of light that reaches past the canopy, which leads to large uncertainties in sub-canopy measurements. This project will provide forest managers and the timber industry with accurate estimates of forest structure and biomass. This includes the ability to assess impacts from disturbance events, such as wildfires and floods, on timber supply.
Forested landscapes are constantly adapting to changes in environmental conditions and perpetuations and shocks such as dieback and fire. This dynamism results in landscapes that are a mosaic of forest patches. The home ranges of forest species differ widely, and species utilise different patches at different times in their life cycle. Moreover, forest patches of different age classes respond to fire differently. And the optimum configuration of patches in a forest landscape which can maximise environmental benefits and manage the risk of fire is uncertain. This optimisation process must also consider the maintenance of habitat quality, diversity and connectedness.
Maintaining the forest goods and services on which society depends in a changing environment is a challenge. This project will provide insight for forest managers to control the risk of catastrophic fire by influencing the mosaic structure of forests.
The DARE Centre is developing data science skills that can be translated across each of the three domain areas of minerals, water and biodiversity. Capability will be built through three core data science areas beginning with understanding the priors (or history) and data of the domain, progressing to model construction and concluding with the interpretation and information for better decision making.
Studying the three domain areas jointly is crucial. It highlights that an action taken to maximise some payoff function in one domain area has consequences for the payoff function in another, thereby explicitly encoding the cumulative impact of an action.
Additionally, although different in surface structure, the three domain areas share a need for probabilistic thinking and proper uncertainty quantification for optimal decision making.
Biodiversity, the diversity of livings things on Earth, underpins and influences almost every product and service we value today and is essential to provide future generations of Australians with a healthy, sustainable economy and environment. Decisions for the management of biodiversity, the ability to prioritise actions and policy, must be informed by complex models based on relatively sparse measurement data where uncertainty quantification is key to decision making.
Water is a fundamental resource, vital to the genesis and sustainability of communities, ecosystems and industry. Understanding the drivers behind water supply and usage and quantifying the joint uncertainty around supply, and demand is critical to many areas of the Australian economy.
The foremost challenge in water resource management today is to make uncertainty quantified predictions in a changing environment for applications such as ecosystem management, flood warning, and water allocation. This is a difficult task when one considers the uncertainty associated with modelling daily rainfall, hydrologic observations, and future climate.
Mineral discovery underpins large parts of the Australian economy where mining contributes over $60bn a year to national GDP. However, most of Australia’s current mineral production and exports are sourced from deposits discovered during an exploration high more than two decades ago. The grand data science challenge is to exploit the vast amount of minerals exploration data to discover what mineralogy exists beneath the 80% of Australia where favourable geology lies below regolith or other barren cover.
DARE is building the new skills and capabilities necessary to meet this challenge: in managing the vast amount of available geophysical information, in developing methods that can fuse this data in to uncertainty quantified geological models, and in developing evidence-based approaches to characterisation of mineralisation.
If you are interested in pursuing a PhD in any of the listed topics, please e-mail your CV, a research proposal and copy of academic transcript to firstname.lastname@example.org.
DARE is no longer providing scholarships, so interested HDR Candidates should be willing to apply for an RTP scholarship or equivalent.