University of Southampton
Top university
Just Landed
New Today
PhD in Deep Learning Latent Dynamics for Complex Aerospace Systems University of Southampton in United Kingdom
Degree Level
PhD
Field of study
Computer Science
Funding
The project is competition funded. No specific stipend amount or detailed tuition-fee coverage is stated in the advert; applicants are directed to the University's fees and funding information.
Deadline
Jan 31, 2027
Country
United Kingdom
University
University of Southampton
Apply for this position
Keywords
Suggested positions
About this position
This PhD project investigates whether artificial intelligence can understand, rather than simply predict, complex engineering dynamical systems. The research will combine deep learning with the mathematics of nonlinear dynamics to uncover hidden low-dimensional structures underlying vibrations, flutter, instabilities, multiple stable states, internal resonances and sudden bifurcations in aerospace systems.
Working within the University of Southampton’s Computational Engineering and Design group, the student will develop interpretable, data-driven reduced order models for systems such as aero-engine structures, flexible wings, aeroelastic systems and electrified propulsion. The project will connect latent-dynamics learning with invariant manifold and normal form theory in two directions: embedding mathematical theory into deep learning architectures so latent spaces have physical meaning, and using deep learning to discover invariant manifolds and nonlinear behaviour from sparse, high-dimensional data.
A further focus is uncertainty quantification, enabling reliable predictions under noise, sparse sensing and real-world variability. The resulting modelling framework will be validated across nonlinear aero-engine, aeroelastic and electromechanical systems and released as open-source software, supporting faster and more trustworthy design of safer, lighter and more efficient aircraft for net-zero aviation.
The research environment includes the University’s high-performance computing facilities and Iridis supercomputer, together with doctoral training in scientific machine learning, nonlinear dynamics and reduced order modelling. The student will benefit from one-to-one supervision, group meetings, research seminars, the Doctoral College researcher development programme, and opportunities for conference presentations, journal publication and teaching as a demonstrator.
Funding details
The project is competition funded. No specific stipend amount or detailed tuition-fee coverage is stated in the advert; applicants are directed to the University's fees and funding information.
What's required
Applicants require at least a 2:1 honours degree. The project is suited to applicants interested in scientific machine learning, deep learning, nonlinear dynamics, reduced order modelling, aerospace or engineering systems; the advert does not specify additional mandatory qualifications.
How to apply
Review the project and full entry requirements on the University of Southampton webpage, then submit an application through the University's postgraduate research application process before 31 January 2027.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.