Deep Learning for Ice Sheet Satellite Altimetry

Supervisors: Dr Mal McMillan, Dr Amber Leeson, Dr Ce Zhang, Adam Sykulski

Institute: Lancaster University


The rationale:

Melting of Earth’s Polar ice sheets contributes approximately one-third of global sea level rise. As Earth’s climate warms, this contribution will increase further, with the potential for large scale social and economic disruption. Our understanding of contemporary ice sheet change is largely informed by satellite observations, and the longest continuous record comes from the technique of satellite altimetry.

This fully funded project offers the exciting opportunity to explore fundamentally new approaches to processing satellite altimetry data over ice sheets, with the ultimate aim of improving estimates of ice sheet melt and sea level rise.

The focus:

Altimeters work by transmitting a microwave pulse towards Earth’s surface and listening to the returned echo, allowing them to monitor the surface of the ice sheet and how it evolves through time. This dataset is immensely valuable; however, current methods for analysing these data typically rely upon a range of assumptions that are designed to reduce the dimensionality and complexity of the data. As a result, subtle, yet important, information content may be lost. Given that many billions of echoes have now been acquired over ice sheets, there is the potential to instead use advanced statistical techniques to develop entirely new ways of extracting meaning from these data.

This project is therefore designed to explore fundamentally new approaches for processing satellite altimetry data over ice sheets, by bringing together Environmental Science, Data Science and Statistics to tackle this problem. Specifically, the project will aim to explore the potential of deep learning to extract deep and subtle information directly from the raw satellite data itself. In doing so, the project aims to define an alternative pathway for how these satellite data are processed and, ultimately, to drive new understanding of the contribution of polar ice sheets to global sea level rise.

What’s in it for the candidate:

The successful candidate will develop expertise in both satellite altimetry and advanced statistical techniques, providing excellent training for a future career in glaciology, polar science or data science research. The project will be hosted within the Lancaster Environment Centre (LEC) and benefit from cross-disciplinary supervision by Mal McMillan, Amber Leeson, Ce Zhang and Adam Sykulski. The successful candidate will join a growing community of polar scientists at Lancaster, which currently comprises 8 PhD students and 4 postdoctoral researchers, and offers a collaborative and supportive training environment for PhD study.

Additionally, the successful candidate will also become a member of the UK Centre for Polar Observation and Modelling (a national research centre with over twenty years of experience of satellite radar altimetry design, development and data processing), and the Lancaster University-UKCEH Centre of Excellence in Environmental Data Science (a new initiative that aims to grow collaborations between environmental and data scientists). The PhD will offer extensive opportunities to collaborate with glaciologists, climate scientists and data scientists. In particular, dedicated funding for this project is provided via an EPSRC CASE award, meaning that the successful candidate will have the opportunity to work closely with the European Space Agency as part of the related Earth Observation for Surface Mass Balance project.

The candidate:

This project is particularly well-suited to applicants with a background in statistics, mathematics, computer science, data science, physics, or engineering, who would like to use numerical techniques to study environmental science and climate change.


Applicants should hold a minimum of a UK Honours Degree at 2:1 level or equivalent in environmental science, geography, ecology, statistics or computing.


Please email Dr Mal McMillan (, Dr Amber Leeson ( or Dr Ce Zhang ( to discuss the PhD further.


Deadline for applications: Friday 4 June 2021

Provisional Interview Date: to be confirmed

Start Date: October 2021

Further details on how to apply.