Acoustic Array and Physics-Informed AI for Hydrogen Leak Detection and Localisation

Supervisory Team: Dr Michal Kalkowski and Dr Chao Zheng

This project aims to merge state-of-the-art acoustics, physics-based modelling, and cutting-edge artificial intelligence (AI) to advance hydrogen leak detection in complex environments. It drives innovation at the intersection of applied mathematics, physics, machine learning, and clean energy.

Low-carbon hydrogen is positioned to play a key role in the energy transition, and its widespread adoption is supported by reliable, early leak detection. This project will develop new AI-driven acoustic array methods to detect, localise, and characterise hydrogen leaks in complex, noisy industrial environments.

You'll work at the interface of acoustic sensing, physics‑based modelling, and advanced machine learning, including the use of physics‑informed neural networks (PINNs). The project tackles real‑world challenges such as multiple leak sources, cluttered propagation paths, and environmental noise—conditions that require innovative approaches blending wave‑physics insight with modern data‑driven techniques.

The project aligns with national priorities in clean energy and advanced sensing technologies, reflecting the industrial impact and real‑world focus highlighted in major UK doctoral training initiatives. Key Research Areas are:

• ultrasonic array signal processing for gas‑leak acoustic signatures
• wave‑propagation modelling in cluttered, reflective environments
• AI‑driven leak localisation and characterisation (including PINNs)
• multi‑array sensor configurations for deployable industrial hydrogen monitoring systems

You'll join an interdisciplinary team spanning ultrasonics, applied mathematics, and AI, and you'll be involved in training and cohort-building activities through:

• industrial engagement with Shell, ensuring strong real‑world relevance
• centre for doctoral training (CDT) in the mathematics for our future climate
• research centre in non‑destructive evaluation (RCNDE)

Entry requirements

You must have a UK 2:1 honours degree, or its international equivalent, in one of the following:

• engineering
• physics
• mathematics
• computer science

Strong computational and analytical skills are essential, and an interest in acoustics, Artificial Intelligence (AI), or signal processing is highly desirable.

Fees and funding

This project is a collaboration between Shell Information Technology International Limited and the University of Southampton. It is funded by Shell and the Engineering and Physical Sciences Research Council (EPSRC) under the Industrial Doctoral Landscape Award scheme.

Funding is available to students from the UK and Horizon Europe countries.

How to apply

Apply now

You need to:

• choose programme type (Research), 2026/27, Faculty of Engineering and Physical Sciences
• select Full time or Part time
• search for programme PhD Engineering & the Environment (7175)
• add name of the supervisor in section 2

Applications should include:

• your CV (resumé)
• 2 academic references
• degree transcripts and certificates to date
• English language qualification (if applicable)

Contact us

Faculty of Engineering and Physical Sciences

If you have a general question, feps-pgr-apply@soton.ac.uk.

Project leader

For an initial conversation, M.Kalkowski@soton.ac.uk.