PhD Study : Monitoring glacier change in the Arctic using multi-spectral satellite imagery and machine learning techniques

Summary

Ice sheets and glaciers are an integral part of the global climate system that are sensitive to climate change and are known to influence global sea levels. Currently, there is concern regarding the future stability of the cryosphere in a warming world and if ice sheets and glaciers continue to melt, global sea levels will potentially rise by over 90m. Given that most of the world’s population lives within several kilometres of the coast, it is critical that we develop a better understanding of how ice sheets and glaciers are responding to climatic warming so that governments can develop mitigation strategies for future generations.  Currently, glaciers in the Arctic are showing increasing signs of instability due to Arctic amplification of the climate system, making it a key region for monitoring changes.  Future projections of glacier change in the Arctic rely on observations of recent glacier change and an understanding of the processes that are driving these changes.

To date, such observations have been undertaken in a piecemeal fashion, with most research focussed on particular regions and with observations over variable time periods. Furthermore, there is a large imbalance across the Arctic, with most studies focussing on the Greenland Ice Sheet and Canadian Arctic Archipelago and with less research for example on Svalbard, and only a handful of studies in the Russian High Arctic. This means that our understanding of past changes is incomplete and that there are large uncertainties for some regions when attempting to predict future change.  To understand what is happening we need better monitoring tools that can be applied Pan Arctic and using new satellite remote sensing datasets such as the Copernicus Earth observation (EO) programme provides an unprecedented opportunity to develop new methods for mapping changes to glacial systems in the Arctic.

This interdisciplinary PhD project involving the Geography and Environmental Sciences Research Institute and Intelligent Systems Research Centre will build on the expertise developed in both research centres to focus on change detection of Arctic glaciers using remote sensing data and novel machine learning techniques. The rapid increase in computing power has enabled the use of powerful machine learning algorithms on large datasets. In particular, recent breakthroughs in computer vision methods and deep learning models for image classification and object detection now make it possible to automatically obtain a much more accurate representation of the composition of the environment than could be previously achieved. It is only recently that advances in deep learning methods have permitted the analysis of satellite imagery and as such, land use classification is still at an early stage but this approach shows great potential for identifying landscape changes. Much work has focussed on the application of convolutional neural networks for land use classification. Deep learning architectures which are pre-trained on natural images from the ImageNet dataset are often used due to a lack of appropriately labelled land-use image data.

In this approach, called transfer learning, a deep network is first trained using the ImageNet dataset and then the network weights are refined using a smaller set of labelled land use images. In this project, low-level (pixel) image processing approaches and object-based approaches will be used in conjunction with deep learning for temporal analysis of image satellite image data for change detection in glaciated landscapes. Algorithms will be developed to automatically learn region representations using a deep neural network in a data-driven fashion. Based on these highly discriminative representations, changes will be determined and predicted using low-level and object based labelling the candidate images.

Essential criteria

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.

We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.

In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.

• A comprehensive and articulate personal statement

Desirable Criteria

If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.

• First Class Honours (1st) Degree
• Masters at 65%
• Research project completion within taught Masters degree or MRES
• Experience using research methods or other approaches relevant to the subject domain
• Work experience relevant to the proposed project
• Experience of presentation of research findings

Funding and eligibility

The University offers the following levels of support:

Vice Chancellors Research Studentship (VCRS)

The following scholarship options are available to applicants worldwide:

• Full Award: (full-time tuition fees + £19,000 (tbc))
• Part Award: (full-time tuition fees + £9,500)
• Fees Only Award: (full-time tuition fees)

These scholarships will cover full-time PhD tuition fees for three years (subject to satisfactory academic performance) and will provide a £900 per annum research training support grant (RTSG) to help support the PhD researcher.

Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Please note: you will automatically be entered into the competition for the Full Award, unless you state otherwise in your application.

Department for the Economy (DFE)

The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).

This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

• Candidates with pre-settled or settled status under the EU Settlement Scheme, who also satisfy a three year residency requirement in the UK prior to the start of the course for which a Studentship is held MAY receive a Studentship covering fees and maintenance.
• Republic of Ireland (ROI) nationals who satisfy three years’ residency in the UK prior to the start of the course MAY receive a Studentship covering fees and maintenance (ROI nationals don’t need to have pre-settled or settled status under the EU Settlement Scheme to qualify).
• Other non-ROI EU applicants are ‘International’ are not eligible for this source of funding.
• Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Due consideration should be given to financing your studies. Further information on cost of living