About the Centre for Doctoral Training
This project is being offered as part of the STFC Centre for Doctoral Training in Data Intensive Science, called NUdata, which is a collaboration between Northumbria and Newcastle Universities, STFC, and a portfolio of over 40 industrial partners, including SMEs, large/multinational companies, Government and not-for profit organisations, and international humanitarian organisations. Please visit https://research.northumbria.ac.uk/nudata/ for full information.
PhD project description
Machine learning and artificial intelligence techniques are increasingly used to understand phenomena in near-Earth space and to develop space weather forecasting abilities, for example to protect satellites from high-energy particles in Earth’s radiation belts. Unfortunately, our predictions are strongly biased towards “quiet” conditions, which are observed more frequently, while we are most interested in predicting extreme (storm) conditions. Storm and non-storm conditions are very different so we should be disentangling our observations to remove this bias. However, near-Earth space is a highly interdependent complex system and extracting individual drivers and impacts is difficult. This project will address an unavoidable obstacle in using AI for space physics: how interconnected are all the phenomena and how do we get physics back out? Causal science is a growing field and this project offers the opportunity to develop new techniques, applied to the unique challenges of space physics datasets.
The successful student will begin with an initial project to identify the causal pathway behind observations of the particle population in Earth’s radiation belts, comparing this to our current understanding of physics. From this point, the student will adapt this causal pathway to extract storm-time effects using counterfactual techniques developed over the past few years for healthcare and responsible AI. Counterfactual methods remove the effect of complex drivers from the output of a given machine learning technique, e.g. removing a protected characteristic (class/gender/race) which impacts multiple variables in a dataset (access to education and healthcare). Final project directions could focus on either the mathematics of these techniques or the underlying space physics.
Dr Sarah Bentley (primary supervisor) and Prof Jonathan Rae (second supervisor)
In addition to regular supervisor meetings, students are encouraged to participate in group activities, including our seminar series with national and international experts. We offer Masters-level modules to provide necessary subject-specific knowledge or skills, and you are encouraged to attend national summer schools and apply to competitive international summer schools. We will help you choose conferences and workshops to discuss your results with the scientific community.
Candidates should have:
- A strong numerate background, e.g. a degree in maths, computer science or physics (essential);
- motivation to explore challenging open questions (essential);
- an ability to work alone or in a team (essential);
- knowledge of electromagnetism, especially of plasma environments (desirable)
- an interest in machine learning / causal science (desirable);
- prior programming knowledge (desirable)
You will join a strong and supportive research team. To help better understand the aims of the CDT and to meet the PhD supervisors, we are hosting a day-long event on campus on Monday 9th January 2023.
At that event, there will be an opportunity to discuss your research ideas, meet potential PhD supervisors, as well as hear from speakers from a variety of backgrounds (academia, industry, government, charity) discussing both STFC and data science as well as their personal paths and backgrounds. Click here for details.
- Academic excellence of the proposed student i.e. 2:1 (or equivalent GPA from non-UK universities [preference for 1st class honours]); or a Masters (preference for Merit or above); or APEL evidence of substantial practitioner achievement.
- Appropriate IELTS score, if required.
- Applicants cannot apply for this funding if they are already a PhD holder or if currently engaged in Doctoral study at Northumbria or elsewhere.
Please note: to be classed as a Home student, candidates must meet the following criteria:
- Be a UK National (meeting residency requirements), or
- have settled status, or
- have pre-settled status (meeting residency requirements), or
- have indefinite leave to remain or enter.
If a candidate does not meet the criteria above, they would be classed as an International student. Applicants will need to be in the UK and fully enrolled before stipend payments can commence, and be aware of the following additional costs that may be incurred, as these are not covered by the studentship.
- Immigration Health Surcharge https://www.gov.uk/healthcare-immigration-application
- If you need to apply for a Student Visa to enter the UK, please refer to the information on https://www.gov.uk/student-visa. It is important that you read this information very carefully as it is your responsibility to ensure that you hold the correct funds required for your visa application otherwise your visa may be refused.
- Check what COVID-19 tests you need to take and the quarantine rules for travel to England https://www.gov.uk/guidance/travel-to-england-from-another-country-during-coronavirus-covid-19
- Costs associated with English Language requirements which may be required for students not having completed a first degree in English, will not be borne by the university. Please see individual adverts for further details of the English Language requirements for the university you are applying to.
For further details of how to apply, entry requirements and the application form, see
You must include the relevant advert reference/studentship code (e.g. NUDATA23/…) in your application.
If you are interested in more than one of the Northumbria-hosted NUdata research projects, then you can say this in the cover letter of your application and you can rank up to three projects you are interested in (i.e. first choice, second choice, third choice). You are strongly encouraged to do this, since some projects are more popular than others. You only need to submit one application even if you are interested in multiple projects (we recommend you submit your application to your first choice).
We offer all applicants full guidance on the application process and on details of the CDT. For informal enquiries, email Professor James McLaughlin ([Email Address Removed]). Please contact the Principal Supervisor of the project(s) [Email Address Removed] for project-specific enquiries.
Deadline for applications: 31st January 2023
Start Date: 25th September 2023