or
Looking to list your PhD opportunities? Log in here.
Large Language Models for Explainable and Scalable Radio Galaxy Classification
Anticipated start date: September 2025.
Note: Subject to funding via https://www.liverpool.ac.uk/centre-for-doctoral-training-for-innovation-in-data-intensive-science/ (LIV.INNO).
Modern telescopes are capturing vast amounts of detailed image data from galaxies across the universe, revealing intricate structures such as jets, lobes, and diffuse emissions. These features offer critical insights into galaxy evolution, the behaviour of supermassive black holes, and the distribution of dark matter. However, interpreting and labelling such complex features manually is time-consuming and inconsistent, especially as upcoming surveys like Euclid and the Vera Rubin Observatory’s Legacy Survey of Space and Time (LSST) will produce massive datasets containing billions of galaxies.
In this interdisciplinary project, you will develop state-of-the-art AI tools to automatically analyse and describe galaxy structures in images, generating both standardised tags and plain-language summaries. You will apply advanced machine learning techniques, including Large Language Models (LLMs), to automate the interpretation and annotation of astronomical data, focusing primarily on images from the ASKAP EMU survey—which aims to detect over 40 million galaxies. Additionally, you will build upon and utilise existing human annotations from Radio Galaxy Zoo: EMU, actively contributing to this important Zooniverse project. You will have the opportunity to develop AI methods that integrate crucial model interpretability techniques, creating a system that not only accurately labels galaxy features, but also provides clear explanations for its reasoning. This will offer astronomers a reliable tool capable of uncovering new insights and accelerating discovery.
As a student at https://www.ljmu.ac.uk/ (LJMU), you will work closely with researchers in the https://www.ljmu.ac.uk/about-us/faculties/faculty-of-engineering-and-technology/school-of-computer-science-and-mathematics (CSM) and https://www.ljmu.ac.uk/research/centres-and-institutes/astrophysics-research-institute (ARI), participate in the Radio Galaxy Zoo: EMU project, and benefit from a collaborative visit to China, where you will explore the latest advances in AI explainability. Your work will provide astronomers with powerful tools for handling the immense data volumes generated by new telescopes. The skills you acquire in explainable AI, large-scale data processing, and cross-domain applications will be highly transferable, enhancing your employability in fields such as medical imaging, remote sensing, and computer vision.
Throughout the project, you will have access to data science training provided by the LIV.INNO doctoral training centre. You’ll also gain specialised skills through Nvidia DLI training, which will help you make the most of high-performance computing resources at LJMU. Additionally, a six-month industry placement will give you the opportunity to broaden your research experience and career skills, making this an exceptional opportunity to contribute to both astrophysics and the broader field of machine learning.
The project will be carried out over 48 months and is fully funded (tuition fees + stipend set by UKRI guidelines + a research/training budget), inclusive of the 6-month industry placement. Applications are welcomed from those with a either a physics, astrophysics or computer science background.
Please note the project tis also advertised here.
Supervisors:
● https://www.ljmu.ac.uk/about-us/staff-profiles/faculty-of-engineering-and-technology/school-of-computer-science-and-mathematics/rob-lyon School of Computer Science and Mathematics, Liverpool John Moores University (LJMU)
● https://www.hongmingastro.com/, Department of Astronomy, Tsinghua University
● https://www.ljmu.ac.uk/about-us/staff-profiles/faculty-of-engineering-and-technology/astrophysics-research-institute/andreea-font, Astrophysics Research Institute (ARI), Liverpool John Moores University (LJMU)
Equality, diversity & inclusion
We are committed to fostering a diverse, inclusive, and equitable research community. We therefore strongly encourage applications from individuals belonging to underrepresented groups. Whilst if you have faced circumstances that have impacted your educational journey, you are welcome to share this in your application. A brief paragraph at the end of your personal statement (part of the application form) is an excellent way to provide this context, though this is entirely optional.
Eligibility
Applicants should have or expect to gain, a MPhys or MSc degree in an appropriate subject (for example, physics, astronomy, mathematics, computer science) by the time they start their PhD. A First or Upper Second Class Bachelor’s degree in a similarly relevant field would be beneficial. We welcome and encourage applications from the UK, EU and other parts of the world.
How to apply
Applicants may contact Dr Lyon before applying to find out more, or to discuss their suitability for the project. When ready to apply, please send the following documents to Dr Lyon at R.Lyon@ljmu.ac.uk:
· Cover letter: A one-page letter explaining your interest in the project and its alignment with your aspirations/goals.
· Curriculum Vitae (CV): Ensure it is up-to-date and highlights relevant experience.
· Academic transcripts: Official transcripts for your Bachelor’s and Master’s degrees.
· Reference letters: Two letters, with at least one referee able to comment on your research experience and skills. Referees should send their reference letters directly to the email address above.
· Application form: A brief application form that collects important details which is attached to this advert (or can be requested via email).
Review Process
We’ll use a holistic review process to evaluate applications for this project. Our assessment will consider:
· Academic preparation: Your background in areas like astrophysics, mathematics, computer science, or machine learning, along with practical skills.
· Research experience: The quality and relevance of any research you’ve undertaken, the technical skills you possess, your enthusiasm for research and understanding of the research process.
· Personal attributes: Qualities like perseverance, initiative, and conscientiousness.
· Fit with our research environment: Your motivation for joining us, contributions to your community, and efforts to enhance diversity in the field.
We understand no applicant will excel in every area, yet this process aims to provide a fair and comprehensive evaluation.
After the application deadline, we will review all submissions and shortlist candidates for interviews. We expect to conduct interviews in March 2025. All applicants will be notified of the outcome of their application as soon as possible, whether or not they are selected for an interview.
Closing Date
February 18th 2025.
Application
Please fill out the below document (Needs converting from PDF to Word for editing- or email R.Lyon@ljmu.ac.uk for a Word copy).
PhDapplicationLIV.Inno2025.pdf
Then email this to Dr Rob Lyon directly R.Lyon@ljmu.ac.uk , including the added information featured in the 'How to apply' section.
Subject to funding via View Website" rel="nofollow" target="_blank">The Liverpool Centre for Doctoral Training for Innovation in Data Intensive Science (LIV.INNO).
The university will respond to you directly. You will have a FindAPhD account to view your sent enquiries and receive email alerts with new PhD opportunities and guidance to help you choose the right programme.
Log in to save time sending your enquiry and view previously sent enquiries
The information you submit to Liverpool John Moores University will only be used by them or their data partners to deal with your enquiry, according to their privacy notice. For more information on how we use and store your data, please read our privacy statement.
Based on your current searches we recommend the following search filters.
Check out our other PhDs in Liverpool, United Kingdom
Start a New search with our database of over 4,000 PhDs
Based on your current search criteria we thought you might be interested in these.
Differential Privacy (DP) mechanisms for Large Language Models (LLMs)
Kingston University
Large-Scale Digital AI systems for Large Language Models (LLMs)
University of Edinburgh
Large Language Models for Biologics Manufacturing Challenges
Durham University