Subglacial Variability of Antarctic Glacier Systems Investigated Using Radar Data and Machine Learning

About the research project

Antarctica's future ice loss constitutes the largest source of uncertainty in projections of global sea level rise over the coming centuries. A key contributor to this uncertainty is our limited understanding of the processes occurring at the ice-bed interface zone (IBIZ), where the continental bed meets the ice above it. Here, subglacial hydrology, sediment presence and porosity, bed topography, and geothermal heat flow interact to modulate basal melting and sliding, driving ice dynamics and fundamental glaciological processes. Despite this critical control, conditions at the ice-bed interface, buried beneath kilometres of ice, remain less well characterised than the surface of Mars. Ice-penetrating radar, however, can see straight through the ice to probe this otherwise inaccessible interface, with the strength and character of the reflected radar signal revealing a signature of the conditions below. While decades of radar survey campaigns across Antarctica have built an extensive observational archive, analysis of radargrams has mostly focused on ice thickness estimation, leaving its potential to understand important spatial variations in IBIZ largely untapped.

This PhD project will develop innovative machine learning methods to automatically unearth new knowledge on subglacial properties beneath the grounded portions of the Thwaites and Totten-Vanderford glacier systems — two of Antarctica's most dynamic and consequential outlet systems. We aim to get to the bottom of subglacial processes for these important ice sheet catchments. For instance, novel computer vision approaches, tailored to radar imagery and its underlying physics, will be developed to map spatial variability in subglacial water content (e.g. through subglacial lake segmentation), bed material (e.g. through sediment vs. bedrock classification), and bed geometry (e.g. through topographic roughness estimation) at previously unattainable scale and resolution. By integrating these radar-derived characterisations with insights from seismic surveys and passing this new knowledge into ice sheet models and machine learning emulators thereof, the project will close the loop between geophysical observations and ice dynamical response. Sitting at the intersection of applied machine learning, geophysics, and radioglaciology, this project will deliver both novel methodological tools and new scientific insights of profound importance to understanding Antarctica's response to a warming climate.

Primary supervisor

Meet Doctor Kim Bente

Funding

The successful applicant will receive a scholarship which provides:

• a living allowance stipend co-funded with ARC Laureate of $34,315 per annum for 3.5 years
• a relocation allowance of up to $2,000
• a tuition fees offset covering the cost of tuition fees for up to four years (domestic applicants only)

A tuition fee offset may be offered to eligible international applicants following competitive assessment 

As part of the application process you may indicate if you do not wish to be considered for scholarship funding.

Additional Funding

If successful, applicants will also be considered for a ARC Top-up top-up scholarship of $5,000 per annum for 3.5 years. This scholarship is funded from ARC.

Other funding opportunities and fees

For further information regarding other scholarships on offer, and the various fees for undertaking a research degree, please visit our Scholarships and fees on research degrees page.

Eligibility

Applicants should review the Higher Degree by Research minimum entry requirements.

Ensure your eligibility for the scholarship round by referring to our Key Dates.

Additional eligibility criteria specific to this project/scholarship:

• Applicants must hold, or have a confirmed pending award of, a University degree in one of the following areas: computer science, applied mathematics, statistics, geophysics, physics, engineering, or a qualification equivalent to those listed. For international applicants, a Masters-level degree that includes a research project assessed through a written dissertation/thesis is preferred.

Selection criteria

The project is competitively assessed and awarded. Selection is based on academic merit and suitability to the project as determined by the College.

Additional essential selection criteria specific to this project:

• A demonstrated interest in, and aptitude for, machine learning applied to remote sensing data. 
• A demonstrated interest in ice sheet processes and the wider context of global change. 

Additional desirable selection criteria specific to this project:

• Experience in data-driven computing applied to spatial data. 

Application process

1. Select your project, and check that you meet the eligibility and selection criteria, including citizenship;
2. Contact Doctor Kim Bente to discuss your suitability and the project's requirements; and
3. In your application:
   • Copy and paste the title of the project from this advertisement into your application. If you don’t correctly do this your application may be rejected.
   • Submit a signed supervisory support form, a CV including contact details of 2 referees and your project research proposal.
4. Apply prior to 15 January 2027.

Full details of the application process can be found under the ' How to apply ' section of the Research Degrees website.

Following the closing date applications will be assessed within the College. Applicants should expect to receive notification of the outcome by email by the advertised outcome date.

Apply nowExplore other projects