PhD Studentship - Physics-Informed Machine Learning Algorithms for the Prediction of Turbulent Flows and Turbulence Modeling

Imperial College London - Department of Aeronautics

Applications are invited for a PhD studentship in Machine Learning applied to Computational Fluid Dynamics in the Department of Aeronautics at Imperial College London.

The prediction of turbulent flows is a long standing problem in science and engineering. Simulations of turbulent flows can be grouped (in decreasing order of fidelity) into 4 categories: Direct Numerical Simulations (DNS, all scales are computed); Large Eddy Simulations (LES, large scales are computed, small scales are modeled); Reynolds Averaged Navier–Stokes models (RANS, all scales are modeled) and hybrid approaches that combine RANS and LES. DNS and LES are often not possible for practical flows (high Reynolds number flows with near-wall phenomena). It is therefore crucial to improve near-wall turbulence models for both RANS and LES to get relevant predictions of practical flows. The main goal of the PhD is to improve low fidelity (RANS and wall-modeled LES) methods using deep learning algorithms and new methods of information extraction from high fidelity simulation data (wall-resolved LES or DNS). The research will focus in particular on flows with separation, strong pressure gradients and mean flow curvature, which are quite challenging to model with low fidelity approaches.

Imperial College is consistently ranked as one of top universities in the world and top 3 universities within the UK. In 2016/17 Imperial ranked 9th in the world in the QS and 8th in the world in the THE rankings. It has been ranked as the most innovative university in Europe. Imperial staff and alumni include 15 Nobel laureates, 2 Fields Medalists, 70 Fellows of the Royal Society, 82 Fellows of the Royal Academy of Engineering and 78 Fellows of the Academy of Medical Sciences.

Applicants should have a keen interest and solid background in Machine Learning, Computational Fluid Dynamics, Programming and in High Performance Computing.

Applications are invited from candidates with (or who expect to gain) a first-class honours degree or an equivalent degree in Engineering, Mathematics, Computing or a related discipline (for more details, see www.imperial.ac.uk/study/pg/apply/requirements/pgacademic).

Funding is available for UK citizens and EU citizens who have resided in the UK for the past three years. The studentship is for 3.5 years and will provide full coverage of tuition fees and an annual tax-free stipend of approximately £16,553. Applications will be assessed as received and all applicants should follow the standard College application procedure: www.imperial.ac.uk/study/pg/apply

Informal enquiries and requests for additional information for this position can be made to:

Dr Sylvain Laizet via email: s.laizet@imperial.ac.uk. Any queries regarding the application process should be directed to Ms Lisa Kelly by email at l.kelly@imperial.ac.uk.

Closing date for applications: Open until 29th June 2018

Start Date: 01 October 2018

Committed to equality and valuing diversity. We are also an Athena Bronze SWAN Award winner, a Stonewall Diversity Champion and a Two Ticks Employer.

Share this PhD
     
  Share by Email   Print this job   More sharing options
We value your feedback on the quality of our adverts. If you have a comment to make about the overall quality of this advert, or its categorisation then please send us your feedback
Advert information

Type / Role:

PhD

Location(s):

London