FindAPhD Weekly PhD Newsletter | JOIN NOW FindAPhD Weekly PhD Newsletter | JOIN NOW

Machine learning and radio source multiplicity

   School of Physics

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

Click here to search for PhD studentship opportunities
  Prof Mark Birkinshaw, Prof Henning Flaecher  No more applications being accepted  Funded PhD Project (Students Worldwide)

About the Project

UKRI Artificial Intelligence, Machine Learning and Advanced Computing (AIMLAC) CDT

The project:

The UKRI CDT in Artificial Intelligence, Machine Learning and Advanced Computing (AIMLAC) aims at forming the next generation of AI innovators across a broad range of STEMM disciplines. The CDT provides advanced multi-disciplinary training in an inclusive, caring and open environment that nurture each individual student to achieve their full potential. Applications are encouraged from candidates from a diverse background that can positively contribute to the future of our society.

This project aims to study the long-standing problem of how to associate distinct source components in radio sources with one another in the presence of a wider population of radio sources. Many radio sources found in interferometric surveys are composed of several distinct bright components (the "hot spots" and "central component" among others) within a low surface brightness envelope. Towards the flux density limit of a survey these bright components can appear without the envelope, and can be hard to associate as parts of a single source. Eye-based techniques have been used to make this association since the very early days of radio surveys, basing the association on such things as component linearity, or brightness similarity, or symmetry, or asymmetric component structures pointing towards a common centre. But these techniques are hopelessly inadequate in the era of large-scale surveys and will become completely untenable once the SKA comes into operation. Further difficulty arises at high redshift where many of the distinguishing features of multi-component sources cease to be valid - because of strong Compton losses, interactions with a clumpy intergalactic medium, and source youth. Progress should be possible through using a well-studied survey field as a training set to develop a machine learning algorithm that combines radio morphological and spectral information to develop a high-speed source-finder. Work would start using one of the deep VLA fields at L and S band, and, if successful, would attempt to extend to surveys at other frequencies. Similar techniques might be applicable at other wavebands, for example in identifying clumpy galaxies in the optical or protoclusters in the X-ray. 

Candidate requirements: 

Candidates should have completed an undergraduate degree (minimum 2(i) honours or equivalent) in a relevant subject, such as physics and astronomy, computer science, or mathematics.

Candidates should be interested in AI and big data challenges, and in the data from large science facilities research theme. You should have an aptitude and ability in computational thinking and methods including the ability to write software (or willingness to learn it).

How to apply:

To apply, and for further details please visit the CDT website and follow the instructions to apply online. This includes an online application for this project at Please select Physics (PhD) on the Programme Choice page. You will be prompted to enter details of the studentship in the Funding and Research Details sections of the form. Please make sure you include “AIMLAC CDT”, the title of studentship and the contact supervisor in your Personal Statement.


Prof. Mark Birkinshaw ([Email Address Removed]), Prof. Henning Flaecher ([Email Address Removed])

Funding Notes

The UK Research and Innovation (UKRI) fully-funded scholarships cover the full cost of 4 years tuition fees, a UKRI standard stipend of currently £15,921 per annum and additional funding for training, research and conference expenses. The scholarships are open to UK and international candidates.
Search Suggestions
Search suggestions

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

PhD saved successfully
View saved PhDs