Physics: Fully Funded UKRI CDT AIMLAC PhD Scholarship: Application of Machine Learning for non-destructive beam profile measurements at CERN’s Large Hadron Collider (LHC)

Funding provider: UK Research and Innovation (UKRI)

Subject areas: Physics

Project start date: 1 October 2023 (Enrolment open from mid-September)

Aligned programme of study: PhD in Physics

Mode of study: Full-time only

Project supervisor: 

• Professor Niels Madsen

Project description:

Artificial Intelligence, Machine Learning and Advance 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.

Research theme: T1 - data from large science facilities

Beam instrumentation concerns the technologies needed to make direct measurements of beam observables such as beam position, intensity and size. These observations provide the diagnostic information to operate and improve the performance of accelerators and the associated transfer lines. For example, in order to maximize the collision rate at colliders - accelerator operators & physicists need measurements of the beam size throughout the acceleration cycle. Development of such an instrument for the LHC has proven to be particularly challenging, since the energy of the beam is too high to measure the profile by interacting directly with the beam itself. The aim of this project will be to develop a beam profile monitor for the LHC which is based on an idea first proposed in the 1960’s that allows to measure the beam profile (& other beam parameters) without interacting directly with the beam - but updated with cutting edge Timepix4 hybrid pixel detector technology that has been developed recently at CERN. A Beam Gas Ionisation (BGI) beam profile monitor is based on the detection of the residual particles that inevitably pervade the beampipe’s vacuum and which undergo ionisation as the beam flies through the pipe. The charged particles are directed towards the monitor by electromagnetic fields and - in the case of the LHC devices - will be directly detected by Timepix4 hybrid pixel detectors, its core element. The beam size is then inferred from the distribution of the detected electrons in real time, and the data organised to create a footage of the beam size evolution. 

Specific goals of the project could include:

1. Optimisation of the electromagnetic field cage to transport ionisation electrons to the Timepix4 detector, including possible application of Machine Learning (ML) techniques to optimise the instrument performance;
2. Development of the Timepix4 based electron detector & associated data acquisition electronics, which must operate a few cm's from the LHC beam and acquire up to 160 GB/s of data;
3. Development of the real time data processing procedures to: i) extract the ionisation electron signal from various backgrounds (e.g. beam loss); ii) correct for known systematic effects and iii) publish the beam profiles of individual LHC bunches;
4. Study the potential to use Machine Learning (ML) techniques to i) optimise the accuracy of the measurement and ii) investigate possible applications of the BGI measurements for a real time beam orbit feedback system;
5. Study the potential to adapt the HL-LHC BGI design for transfer line applications, including medical accelerator facilities.

More information can be found at the UKRI CDT in Artificial Intelligence, Machine Learning & Advanced Computing (AIMLAC) website.  

Please quote the project code (e.g. RS275 - AIMLAC8) for queries and within the application. If you wish to apply for more than one AIMLAC project, please complete a separate application for each project.

Eligibility

Applicants for PhD must normally hold an undergraduate degree at 2.1 level or a master’s degree with a minimum overall grade at ‘Merit’ (or Non-UK equivalent as defined by Swansea University). 

English Language requirements: If applicable – IELTS 6.5 Overall (with no individual component below 6.0) or Swansea University recognised equivalent. 

This scholarship is open to candidates of any nationality.