Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

Causality pathways in space: Extracting the storm-time bias of space weather forecasting (Advert Reference: MRDF22/EE/ExEnv/BENTLEY)

   Faculty of Engineering and Environment

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr Sarah Bentley, Prof Jonathan Rae  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

We want to work with a student to discover, extract and analyse the storm-time bias of space weather predictions of Earth’s radiation belts using machine learning and causal inference techniques.


Machine learning and artificial intelligence techniques are increasingly used to understand phenomena in near-Earth space. This question will help us understand the radiation belt environment, a region of space where high-energy particles orbit the Earth. Space weather forecasting is necessary to protect satellites from these high-energy particles. Our predictions here are strongly biased towards “quiet” conditions, which are observed more frequently. Unfortunately, we are most interested in predicting extreme (storm) conditions. We know that 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 go to the heart of the difficulty in using AI for space physics investigations: how interconnected are all the phenomena and how do we get physics back out?

Project outline:

The successful student will begin by identifying the causal pathway behind observations of the particle population in Earth’s radiation belts and comparing this to our current understanding of physics. This initial project will allow the student to develop background knowledge in space weather, causal inference and applications of machine learning, and will inform further project directions. 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. a protected characteristic (class/gender/race) which impacts multiple variables in a dataset (access to education and healthcare). The student will use these techniques to extract the impact of storm vs non-storm times. Further research will be determined by the student’s results and interests and is likely to focus on the techniques or the underlying physics.

The project supervisors have expertise in space physics and using machine learning techniques to improve radiation belt modelling.

Training opportunities:

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 any 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.

The Principal Supervisor for this project is Dr. Sarah Bentley (E-mail: [Email Address Removed]).

Eligibility and How to Apply:

Please note eligibility requirement:

  • 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 currently engaged in Doctoral study at Northumbria or elsewhere or if they have previously been awarded a PhD.

This project would particularly suit either a mathematics/ computer science student with an interest in space physics, or a student with a physics background and an interest in machine learning. A numerate background and some physics knowledge are essential. Prior programming knowledge is desirable.

For further details of how to apply, entry requirements and the application form, see

Please note: Applications that do not include a research proposal of approximately 1,000 words (not a copy of the advert), or that do not include the advert reference (e.g. MRDF22/…) will not be considered.

Deadline for applications: 18 February 2022

Start Date: 1 October 2022

Northumbria University takes pride in, and values, the quality and diversity of our staff and students. We welcome applications from all members of the community.

Computer Science (8) Geology (18) Mathematics (25) Physics (29)

Funding Notes

Each studentship supports a full stipend, paid for three years at RCUK rates (for 2021/22 full-time study this is £15,609 per year) and full tuition fees. UK and international (including EU) candidates may apply.
Studentships are available for applicants who wish to study on a part-time basis over 5 years (0.6 FTE, stipend £9,365 per year and full tuition fees) in combination with work or personal responsibilities.
Please also read the full funding notes which include advice for international and part-time applicants.
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.