XClose

UCL Energy Institute

Home
Menu

New PhD studentship in Explainable AI for Energy Applications

10 May 2021

The new 4-year PhD studentship is funded by EPSRC and EDF (CASE), and starts Autumn 2021.

Aerial view of skyscrapers in city with blue lights

Funded PhD studentship in Explainable AI for Energy Applications

Funded by EPSRC and EDF (CASE).

Primary supervisor

Dr Aidan O’Sullivan, UCL Energy Institute

Secondary supervisor

Prof Tadj Oreszczyn, UCL Energy Institute

Stipend

The studentship will cover UK course fees and an enhanced tax-free stipend of approx. £17,285 per year for 4 years along with a substantial budget for research, travel, and centre activities. Applicants should meet the EPSRC eligibility criteria.

Dates

4 years starting Autumn 2021

Eligibility

In addition to UCL's academic requirements for admittance to Doctoral studies, see the following additional ones on the EPSRC website.

About the studentship

Artificial Intelligence promises to be one of the most transformative technologies of the modern century. Recent progress and breakthroughs in deep learning have enabled a host of new applications across a range of fields from protein folding to autonomous vehicles. However, in the energy system the adoption of these methods has been limited by their ‘black-box’ nature. Critical infrastructure, like energy systems, operate under stringent reliability and resilience requirements. Greater adoption of AI in this sector demands methods that can provide insights into how an algorithm is making decisions and predictions. This will give operators of these systems confidence in the reliability of these algorithms. 

Studentship aims

This PhD, will explore and develop Explainable AI (XAI) for energy systems. These methods will be able to provide insights into how the ‘black-box’ methods are functioning, approaching glass-box methods. Methods explored include but are not limited to; deep learning, ensemble learning and causal inference. The research contribution will cover a wide spectrum building theoretical foundations in this rapidly developing field while also contributing to real world applications such as wind turbine failure. The research will be conducted in collaboration with the EDF digital innovation team. 

Person specification

Candidates should have:

  • A bachelor’s degree with a minimum of upper second-class (2:1) honours, or an overseas qualification of an equivalent standard.
  • A Master’s degree in statistics, engineering, computer science or other relevant disciplines.  Candidates without a Master’s degree may be admitted where suitable experience is demonstrated.
  • Expert knowledge of machine learning and artificial intelligence methods.
  • An understanding of the energy system and the role of suppliers
  • Excellent numerical and computing skills.
  • Excellent interpersonal and communication skills (oral and written).

Application procedure

How to apply

Applicants should access the UCL SELECT portal.

Scroll to the bottom of the page and click the ‘Apply now’ button.

The deadline for applications is: 09.00 am (BST), Tuesday 8 June 2021

Please include:

  • A covering letter,
  • CV,
  • Names and addresses of two academic referees,
  • Copies of your degree certificate(s) and transcript(s),
  • A short research proposal (1000 words).

For informal enquiries on the research topic or your eligibility, email Dr Aidan O’Sullivan with ‘Explainable AI for Energy Applications’ in the subject field.

Interviews will be held online during the week of 28 June 2021.