PhD Studentship: Self-Supervised Learning for Sparse and Heterogeneous Spatio-Temporal Data

About the Project

Primary Supervisor - Professor Beatriz de la Iglesia

Can AI Learn When Data Are Scarce?

Artificial Intelligence is transforming our ability to understand and predict complex systems. But what happens when the data we need most are scarce, incomplete or irregularly collected? Can AI algorithms learn from the vast amounts of unlabelled information available and make reliable predictions with very few observations?

This exciting PhD project will tackle one of the fundamental challenges in modern machine learning: developing AI methods that learn meaningful patterns from complex spatial and temporal data without relying on large labelled datasets.

You will investigate cutting-edge self-supervised learning approaches, developing novel algorithms that exploit relationships across space, time and different data sources. Potential research directions include representation learning, graph neural networks, masked learning, transfer learning and methods for integrating heterogeneous observations.

The research will initially connect with an ongoing NERC-funded project developing AI methods to predict microbial contamination in bathing waters. This provides a challenging real-world application where environmental measurements are abundant but direct observations of pathogens are limited. However, the methodological advances will have much wider relevance, with opportunities to explore applications in healthcare, environmental monitoring, infrastructure and beyond.

Based on the School of Computing Sciences at the University of East Anglia, you will join an interdisciplinary research environment and collaborate with researchers in AI, environmental science, medicine and hydrodynamic modelling.

We are looking for a curious, motivated researcher with a strong interest in machine learning and a desire to develop new methods rather than simply apply existing techniques. You will have opportunities to publish methodological research, develop open-source tools and contribute to AI approaches capable of addressing important scientific and societal challenges.

Entry Requirements

The standard minimum entry requirement is 2:1 in Computer Sciences, Data Science or related subject.

Mode of Study

Full-time

Start Date

1 October 2027

Additional Funding Information

This PhD project is in a competition for a Faculty of Science funded studentship. Funding is available to UK applicants and comprises ‘home’ tuition fees and an annual stipend for 3 years. The current UEA / institutional PhD stipend rate is £21,805 and will be subject to any agreed inflationary uplift for 2027/28.