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

  A Deep Learning Framework for Enhanced Predictive Modelling of Geomagnetic Activities (Ref: NUDATA24/EE/CIS/YI)

   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 Qiuyi Yi, Dr Andy Smith  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

Overview of the CDT

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 for full information.

Project Description

Background: Geomagnetically Induced Currents (GICs) emerge from the spatio-temporal alterations in Earth's magnetic field, primarily driven by the interaction of the solar wind with Earth's magnetosphere. These currents can lead to catastrophic disruptions in our technologically reliant society[1]. The need for computational models that can forecast GICs globally, with a vast forecast horizon, high spatial resolution, and temporal cadence, is becoming increasingly paramount[2]. Given that GIC data is proprietary, the time variability of the horizontal component of the magnetic field perturbation serves as a proxy for GICs[3,4].

Research Aims: The primary objective is to build opon NASA DAGGER model to develop a global forecasting model for geomagnetic disturbances. By coupling deep learning with spherical harmonic basis, the model will be taking solar wind parameters, the Interplanetary Magnetic Field (IMF) measurements, and the solar radio flux measurements as inputs. This model will aim to provide real-time predictions with high accuracy across various regions. And optimized the model for real-time predictions at scale, especially during peak solar activities.

Proposed approaches:

Data: Collect pertinent data from global monitoring networks that observe geomagnetic activities. Additionally, procure data associated with solar activities from reputable space research institutions, utilising NASA/GSFC’s OMNI dataset. Address any discrepancies or gaps in the data, ensuring it is standardised to maintain uniformity and accuracy.

Model Development and Improvement: Explore architectures that are apt for accommodating multiple time scales, building upon the foundation of the DAGGER model developed by NASA for geomagnetic disturbances. The incorporation of attention mechanisms could enhance the model’s focus on highly correlated input data, particularly when forecasting significant geomagnetic disturbances.

Evaluation and Validation: Conduct a thorough assessment of the model's performance using established evaluation metrics to ascertain its accuracy and reliability. Implement techniques aimed at enhancing model interpretability, yielding insights instrumental in further refining the model.

Conclusion: By merging advanced computational techniques with available data, this research seeks to lead the way in predicting geomagnetic disturbances. The ultimate goal is not just to advance our understanding but also to offer practical tools that can help society prepare for and mitigate the impacts of space weather events.

Academic Enquiries

This project is supervised by Dr Qiuji YI. For informal queries, please contact [Email Address Removed]. For all other enquiries relating to eligibility or application process please contact Admissions at [Email Address Removed]. 

Recruitment Event

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 15th January 2024. 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.

Eligibility Requirements:

  • Academic excellence i.e. 2:1 (or equivalent GPA from non-UK universities with 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 if they are already a PhD holder or if currently engaged in Doctoral study at Northumbria or elsewhere.

To be classed as a Home student, candidates must:

  • 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
  • If you need to apply for a Student Visa to enter the UK, please refer to It is important that you read this information 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.
  • Costs associated with English Language requirements which may be required for students not having completed a first degree in English, will not be paid by the University.

For further details on how to apply see  

You must include the relevant advert reference/studentship code (e.g. NUDATA24/…) 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 all the projects you are interested in (e.g. 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).

Deadline for applications : 31st January 2024

Start date of course :  23rd September 2024

Northumbria University is committed to creating an inclusive culture where we take pride in, and value, the diversity of our postgraduate research students. We encourage and welcome applications from all members of the community. The University holds a bronze Athena Swan award in recognition of our commitment to advancing gender equality, we are a Disability Confident Leader, a member of the Race Equality Charter and are participating in the Stonewall Diversity Champion Programme. We also hold the HR Excellence in Research award for implementing the concordat supporting the career Development of Researchers and are members of the Euraxess initiative to deliver information and support to professional researchers.

Computer Science (8) Physics (29)

Funding Notes

The 4-year studentship is available to Home and international (including EU) students and includes a full stipend at UKRI rates (for 2023/24 full-time study this was £18,622 per year) and full tuition fees. Studentships are also available for applicants who wish to study on a part-time basis in combination with work or personal responsibilities.


[1] Gleisner, H., H. Lundstedt, and P. Wintoft. "Predicting geomagnetic storms from solar-wind data using time-delay neural networks." Annales geophysicae. Vol. 14. No. 7. 1996.
[2] Keesee, Amy M., et al. "Comparison of deep learning techniques to model connections between solar wind and ground magnetic perturbations." Frontiers in Astronomy and Space Sciences 7 (2020): 550874.
[3] Smith, A. W., et al. "Forecasting the probability of large rates of change of the geomagnetic field in the UK: Timescales, horizons, and thresholds." Space weather 19.9 (2021): e2021SW002788.
[4] Collado‐Villaverde, Armando, Pablo Muñoz, and Consuelo Cid. "Deep neural networks with convolutional and LSTM layers for SYM‐H and ASY‐H forecasting." Space Weather 19.6 (2021): e2021SW002748.
[5] Upendran, Vishal, et al. "Global geomagnetic perturbation forecasting using Deep Learning." Space Weather 20.6 (2022): e2022SW003045.

How good is research at Northumbria University in Computer Science and Informatics?

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities

Where will I study?