UCL’s Energy Institute and Institute for Environmental Design and Engineering are seeking applications for a fully funded Studentship on topic in “Physics-informed Machine Learning Modelling for Multi-scale Building Energy Systems with Enhanced Accuracy and Interpretability”
Making buildings energy-efficient and grid-interactive is essential for the low-carbon transformation of the energy system. The ability to accurately model energy systems from a single building to neighbourhood, district, and even larger scales is pivotal to assessing innovative technologies’ energy, environmental, and economic implications before implementation.
Funding: The studentship will cover UK course fees and an enhanced tax-free stipend of approx. £19,000 per year for 4 years along with a substantial budget for research, travel, and centre activities.
Fees: ERBE CDT has very limited funding for applicants requiring coverage of overseas fees. We advise all interested applicants to be familiar with the changes to EU and International Eligibility for EPSRC/UKRI funded studentships
Dates: 4 years from September 2022
Context and Project description:
Buildings significantly contribute to global energy consumption and carbon emissions and play an important role in accelerating the transformation of a low-carbon energy system. Accurate and transparent modelling is essential for developing energy-flexible and resilient buildings, characterising building demand flexibility, and comprehensively assessing different control strategies before implementation. In practice, physics-based building modelling requires many inputs, some uncertain; this often leads to overly simplistic or inaccurate approaches, especially in large-scale multi-building contexts. Pure data-driven modelling approaches are attractive but lack interpretability, and model predictions are not fully explainable or trustable.
This PhD aims to develop a hybrid physics-informed machine learning approach to reconcile the shortcomings of each method. The approach to be developed will be evaluated on actual UCL buildings, with model predictions contrasted against actual measurements.
The successful candidate will work with internationally respected researchers, supported by their supervisors and by the vibrant and skilled research teams undertaking cutting-edge research in this area. They will also join the wider ERBE cohort (Energy Resilience and the Built Environment Centre) to benefit from high-quality training and support throughout their PhD study.
This project aims to develop a hybrid physics-informed machine learning approach to overcome the shortcomings of conventional physics-based and data-driven modelling approaches. The developed hybrid modelling approach will be capable to reveal the causality of model predictions providing information on why the prediction is made and the most supporting and conflicting evidence towards each prediction, enabling resulting models explainable at each prediction. The discrepancies of physics-based models’ predictions from actual measurements caused by intangible inputs and inevitable simplifications will be effectively addressed.
The ideal candidate will have a science, engineering or data analysis background. Experience or qualifications in a subject associated with the built environment or mathematical modelling and machine learning are welcome but not required, as training and support will be provided to the successful candidate.
A minimum of an upper second-class UK Bachelor’s degree and a Master’s degree, or an overseas qualification of an equivalent standard, in a relevant subject, is essential. Exceptionally: where applicants have other suitable research or professional experience, they may be admitted without a Master’s degree; or where applicants have a lower second-class UK Honours Bachelor’s degree (2:2) (or equivalent) they must possess a relevant Master’s degree to be admitted.
Applicants must also meet the minimum language requirements of UCL
Applicants should be familiar with the changes to EU and International Eligibility for UKRI funded studentships.
How to apply
Please submit a pre-application by email to the UCL ERBE Centre Manager (firstname.lastname@example.org) with Subject Reference: 4 year PhD studentship in Physics-informed Machine Learning Modelling for Multi-scale Building Energy Systems with Enhanced Accuracy and Interpretability
The application should include all of the following:
1) A covering letter clearly stating why you are applying and how your interests and experience relate to this project, and your understanding of eligibility according to these guidelines: EU and International Eligibility for EPSRC/UKRI funded studentships
3) Complete the CDT EPSRC fees background and EDI questionnaire via the linked Microsoft Forms.
Only shortlisted applicants will be invited for an interview.
• For the interview shortlisted candidates will be asked to show proof of their degree certificate(s) and transcript(s) of degree(s), and proof of their fees eligibility.
• The interview panel will consist of consist of the project’s academic supervisors at UCL, and a representative of the ERBE CDT Academic management The interview will include a short presentation from the candidate on their ideas of how to approach this PhD project.
Following the interview, the successful candidate will be invited to make a formal application to the UCL Research Degree programme for ERBE CDT.
Deadline for applications: Sunday, 15th May 2022 @ 23:59 (UK time)
Interviews week commencing: TBC
For further details about the admission process, please contact: email@example.com
For any further details regarding the project, contact Dr Rui Tang, firstname.lastname@example.org
You will be undertaking this project:
- In UCL at the main (Bloomsbury) campus as part of the new EPSRC-SFI Centre for Doctoral Training in Energy Resilience and the Built Environment (ERBE CDT). This is a collaboration between UCL, Loughborough University and Marine and Renewable Energy Ireland (MaREI). For more information please see http://erbecdt.ac.uk