PhD Studentship in Aeronautics: Scientific Machine Learning to Support Aviation Sustainability (AE0062)

Start Date: Between 1 August 2025 and 1 July 2026

Introduction: Recent scientific machine-learning methods enable automated model discovery directly from data, with great potential to drive progress in fields such as aerospace engineering and atmospheric science. However, most such research in these fields remains relatively immature due to the interdisciplinary nature of the challenge. For example, efficiently leveraging satellite observations of aircraft condensation trails (contrails) using machine learning methods requires close collaboration between specialists in machine learning, atmospheric science, and aerospace engineering. Researchers who can use model discovery techniques with integrated understanding of multiple domains can achieve breakthroughs impossible in single-discipline research.

Objectives: Develop and apply scientific machine learning methods to challenges bridging aerospace engineering and atmospheric science, including (1) identifying accurate meteorological predictors for contrail formation and (2) resolving a problem in the modelling of atmospheric dynamics – long considered unsolvable – which is limiting progress in pollution control. You will develop and extend automated model discovery methods (such as Sparse Identification of Nonlinear Dynamics, SINDy) and apply them to databases of real-world observations and model error statistics. In so doing you will enable the governing equations to be efficiently ‘learned’ from observations alone.

Supervisors: Dr. Sebastian Eastham on aircraft condensation trails and atmospheric modelling; and Dr. Urban Fasel on developing scientific machine learning methods for automated model discovery.

Learning Outcomes: You will develop expertise in scientific machine learning, numerical modelling, and atmospheric science.

Professional Development: You will interact with researchers across multiple disciplines including satellite data acquisition, image processing, atmospheric science, global climate modelling and high performance computing, with opportunities for exchanges or internships at major modelling centers. You will also have access to engaging professional development workshops through our Early Career Researcher Institute.

Duration: 3.5 years.

Funding: Full coverage of tuition fees and an annual tax-free stipend of £21,237 for Home, EU and International students. Information on fee status can be found at: www.imperial.ac.uk/study/pg/fees-and-funding/tuition-fees/fee-status/.

Eligibility: You must possess (or expect to gain) a First class honours MEng/MSci or higher degree or equivalent in Aeronautics, Mechanical Engineering, Computing, Physics or related areas. In particular, we invite applications from candidates with a strong mathematical background and an interest in modelling and machine learning. A background in or experience with atmospheric science is desirable but not essential.

How to apply: Send a preliminary application to Dr Sebastian Eastham and Dr Urban Fasel citing ‘PhD studentship – Scientific ML to support aviation sustainability’ in the title. Please include a cover letter explaining how you meet the selection criteria, CV, university transcripts and, optionally, a piece of written work (i.e. a previous project report).

You will then submit your application at: www.imperial.ac.uk/study/apply/postgraduate-doctoral/application-process/ including the reference (AE0062) and address your application to Department of Aeronautics. When making your application, please type ‘Aeronautics Research (PhD)’ into the programme search bar.

For queries regarding the application process, email Lisa Kelly

Application deadline: 9 January 2025

For further information: email Dr Sebastian Eastham and Dr Urban Fasel. You can learn more about Imperial at www.imperial.ac.uk/study/pg

Equality, Diversity and Inclusion: Imperial is committed to equality and valuing diversity. We are an Athena SWAN Silver Award winner, a Stonewall Diversity Champion, a Disability Confident Employer and are working in partnership with GIRES to promote respect for trans people.

Advert information