📣 Help Shape the Future of UKRI's Gateway to Research (GtR)

We're improving UKRI's Gateway to Research and are seeking your input! If you would be interested in being interviewed about the improvements we're making and to have your say about how we can make GtR more user-friendly, impactful, and effective for the Research and Innovation community, please email gateway@ukri.org.

Real-time digital optimisation and decision making for energy and transport systems

Lead Research Organisation: University of Oxford
Department Name: Engineering Science

Abstract

Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.

Publications

10 25 50
 
Description This research has led to two important breakthroughs:
1. A New Tool for Simulating Hydrogen Leaks: The team has developed a unique CFD-based model that can accurately simulate complex hydrogen leak scenarios. This tool allows scientists and engineers to study how hydrogen behaves when it escapes from storage under different conditions. As part of this work, we have also compiled a dataset that helps predict how storage conditions affect hydrogen leaks.

2. Using Machine Learning to Identify Risk Factors: our team has shown that it's possible to identify key risk factors related to hydrogen storage by monitoring pressure levels and applying advanced Machine Learning techniques. This means that potential risks could be detected earlier and more accurately, improving safety in hydrogen storage and transportation.

Overall, this research provides powerful new tools for improving hydrogen safety, making it easier to predict and prevent dangerous leaks.
Exploitation Route We are currently looking at exploring the outcomes in two directions
1. Use the undertanding gained by our simulations in order to predict and prevent risks. We plan to extend our simulaiton manifold to imulate potential failure scenarios, such as leaks or equipment malfunctions, under varying conditions to identify vulnerabilities before they occur.

2. Use the Machine Learning based framework we have developed to enable Real-Time Monitoring. As a next step we plan to Integrate sensors to provide live data, allowing immediate detection of anomalies and facilitating rapid response strategies in cases of potential leaks.
Sectors Aerospace

Defence and Marine

Chemicals

Energy

Environment

Transport

URL https://aifornetzero.co.uk/case-study/revolutionising-hydrogen-research-for-a-sustainable-future/
 
Description The findings from this research have been valuable in multiple ways. First, they have advanced scientific understanding of cryogenic fluid dynamics, particularly in the context of hydrogen leaks. Additionally, the work has the potential to improve commercially available leak detection methods, making them more accurate and reliable. Finally, the insights gained can help shape future policies and regulations related to hydrogen safety, ensuring safer storage and transport of hydrogen in various industries.
First Year Of Impact 2025
Sector Aerospace, Defence and Marine,Energy,Transport
Impact Types Societal

Economic

Policy & public services

 
Description Establishment of interdisciplinary links with the University of Cambridge
Geographic Reach Local/Municipal/Regional 
Policy Influence Type Contribution to new or improved professional practice
 
Description Making Hydrogen Work in Zero Carbon Jet Engines
Amount £5,000,000 (GBP)
Funding ID APP21976: 
Organisation United Kingdom Research and Innovation 
Sector Public
Country United Kingdom
Start 03/2025 
End 04/2030
 
Title Linking CFD data and ML alogirthms 
Description We have created a post processing tool in order to create ready to use in ML algorithms databases relvant to hydrogen jet dynamics produced from CFD simulations 
Type Of Material Improvements to research infrastructure 
Year Produced 2024 
Provided To Others? No  
Impact This is the first tool that allows linking data coming from CFD simulations to the input of Machine Learning Algorithms specifically tailored for hydrogen safety scenarios. The tool can be fundamental in order to automate predicitons for hydrogen leaks and improve hydrogen safety protocols 
 
Title Dataset - Compressed Hydrogen Release 
Description We are in the process of generating a comprehensice dataset that will include simulaiton data for various storage conditions and the resulting pressure signals near a leackage point 
Type Of Material Database/Collection of data 
Year Produced 2024 
Provided To Others? No  
Impact This dataset when complete can be used to provide synthetic data to machine learning algorithms 
 
Description BP spin off PhD project 
Organisation BP (British Petroleum)
Department BP Chemicals
Country United Kingdom 
Sector Private 
PI Contribution Within the current EPSRC project we use numerical tools developed in a previous EPSRc project to produce data that then can be used as input in ML algorithms. The focus is the ML part rather than the actual CFD tools BP has agreed to fund a PhD studetnship to develop further the CFD tools relevant to hydrogen jet dynamics
Collaborator Contribution BP will provide us with experimental data as well as input for the industrially relevant cases
Impact BP is currently funding a PhD studetnship whihc has has just started so currently there are no outputs
Start Year 2024
 
Title CoolFOAM - Hydrogen Libraries 
Description A new library has been created and coupled with OpneFOAM that can accurately simulate cryogenic Hydrogen Properties. The software developed account for real fluid themrodynamics through a) Tabulations b) relevant Equations of State. Appropreate thermophysical coeffcient have also been included 
Type Of Technology Software 
Year Produced 2024 
Open Source License? Yes  
Impact This is the first library of its kind for hydrogen simulations with real fluid thermodynamics 
 
Title ML based leak detection 
Description We are in the process of developing a new instrumentaiton technique for detection of hydrogen leaks based on pressure sensors and a pretrained machine leanring framework based on a datat set of synthetic datat genenrated through CoolFOAM 
Type Of Technology Detection Devices 
Year Produced 2025 
Impact Hydrogen, as a clean energy carrier, plays a critical role in the transition toward sustainable energy solutions. However, its high flammability and wide range of explosive concentrations necessitate highly reliable leak detection systems. Traditional detection methods, such as gas sensors and infrared imaging, often have limitations in terms of response time, sensitivity, and operational constraints. By leveraging machine learning with high-resolution pressure sensors, this framework enables rapid and accurate leak detection, thereby reducing the risk of hazardous incidents. 
 
Description 8th of December 2023 - Combustion Institute British Section (CIBS) and the Institute of Physics Hydrogen Meeting 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact Hydrogen is the trending green fuel for decarbonisation. Interest in hydrogen as a fuel for combustion applications has rapidly increased with the release of the government targets for net-zero by 2050. Low carbon hydrogen could be a versatile replacement for high-carbon fuels used today either with power generation gas turbines or civil aviation, helping to reduce pollutant emissions in vital UK industrial sectors and providing flexible energy for power, heat, and transport. Combustion Institute British Section (CIBS) and the Institute of Physics - Combustion Physics Group (IOP-CPG) jointly held their one-day meeting on 'Hydrogen Combustion - Current and Future Research' on the 8th December 2023.

The event was organised under the auspices of CIBS and IOP. The event was held at LT1, Inglis Building, Engineering Department, Cambridge University, Trumpington Street, Cambridge, CB2 1PZ.

The meeting brought together experts in the field of hydrogen combustion as a route to decarbonisation of energy production and sustainable transport. Researchers into the fundamental aspects of hydrogen combustion as well as those developing of solutions for industrial, energy storage, hydrogen safety and transport applications participated in this one-day meeting.

I was one of the keynote speakers talking about the challenges for storage and transportation of hydrogen
Year(s) Of Engagement Activity 2023
 
Description AI-UK 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact The project held a stand at the fifth edition of AI UK, the UK's national showcase of data science and artificial intelligence (AI) research and innovation. The UK's national showcase of data science and artificial intelligence (AI)
Hosted by The Alan Turing Institute and returning for its fifth year, AI UK is an in-depth exploration of how data science and AI can be used to solve real-world challenges. Our diverse programme is thematically structured around the latest innovations from across the AI ecosystem. With a broad range of interactive content, covering the latest thinking on fundamental AI, digital twins, algorithmic bias, AI ethics - and much more.
Year(s) Of Engagement Activity 2025
URL https://www.turing.ac.uk/events/ai-uk-2025
 
Description Animated explainer video 
Form Of Engagement Activity Engagement focused website, blog or social media channel
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact a 90 second animated video that explains the project objectives and desired outcomes
Year(s) Of Engagement Activity 2024
URL https://youtu.be/cPMpxML669I
 
Description Cryogenic Fluid Dynamics for Net Zero: Challenges and Opportunities 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact MIT Conference on Computation, Combustion, and Energy, Massachusetts Institute of Technology, USA
Year(s) Of Engagement Activity 2024
 
Description Harnessing Machine Learning and CFD for Advancing Hydrogen Safety: Predictive Insights and Real-Time Solutions 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact Online Seminar as part of the AI For Net Zero Webinar series
Year(s) Of Engagement Activity 2024
URL https://www.youtube.com/watch?v=FlLU0XbpiAo
 
Description Interview videos 
Form Of Engagement Activity A broadcast e.g. TV/radio/film/podcast (other than news/press)
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact An interview video of the team was filmed during the New Scientist Live fair and then edited into a 2 minute showcase of all the project team members to promote the research going on. This was a useful exercise for the team thinking of how best to promote the work they are doing.
Year(s) Of Engagement Activity 2024
URL https://youtu.be/2_4w4TYlxno?feature=shared
 
Description LinkedIn Page 
Form Of Engagement Activity Engagement focused website, blog or social media channel
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact LinkedIn Page to share to date information and news about the project, including conference appearances, and publication of scientific articles. since August 2024 the LinkedIn page has received more than 200 followers. Through LinkedIn the project has received a few requests to present at different science fairs.
Year(s) Of Engagement Activity 2023
URL https://www.linkedin.com/company/ai-for-net-zero
 
Description Lubbock Talk 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact The Maurice Lubbock Memorial Event is on of the most prestegious events of the Department of Engineering Science at the University of Oxford.

Engineers have always pushed the boundaries of the possible, and this year's event will showcase Engineering at the Extremes. The 2023 Lubbock lecturer was Sir Ian Chapman, CEO of the UK Atomic Energy Authority and world expert on the extreme engineering involved in making fusion power a reality, where the fusion material is as hot as the sun. Ian will discuss how engineering is creating solutions even in these most extreme environments, helping to bring us closer to the transformation fusion can bring about, providing abundant, cheap, clean power.

The Lubbock supporting lectures covered a breadth of Oxford Engineering Science:

Dr Chiara Falsetti will talk about challenges and opportunities related to sustainable aviation.
Professor Konstantina Vogiatzaki takes us to the other extreme of the temperature scale, talking about her work to understand the weird world of fluids at temperatures hundreds of degrees below zero.
Finally, Professor Dan Eakins will present research which explores the limits of a material's strength beyond the sound barrier.
Year(s) Of Engagement Activity 2023
URL https://www.youtube.com/watch?v=N6u55EJl0_8
 
Description New Scientist Live 2024 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Public/other audiences
Results and Impact premier science festival held from October 12 to 14, 2024, at ExCeL London and online. The event featured over 70 speakers, 80 exhibits, and five stages covering topics from the universe to the human mind. Highlights included interactive experiences like the "Hospital of the Future" by King's College London, showcasing advancements in healthcare technology. The final day was dedicated to schools, inspiring over 6,000 students with hands-on activities and talks.
Year(s) Of Engagement Activity 2024
URL https://live.newscientist.com/
 
Description Participation in the organization of the AI for NetZero Conference 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Study participants or study members
Results and Impact On behalf of the UKRI AI for Net Zero Programme, the first AI for Net Zero conference held on 16-19 December 2024. The conference, was hosted by the University of Exeter at the beautiful Streatham Campus brought together a community of researchers addressing the challenges of, and seeking ground breaking solutions to the delivery of UK NetZero by 2050. The conference was co-organised by the projects funded through the UKRI AI for NetZero Programme: Heriot-Watt University, Imperial College London, University of Surrey, University of Leicester, Durham University, Aberystwyth University, together with many more, including Universities of Edinburgh, Cambridge, Oxford, Lincoln, Southampton, UCL and Exeter. Our project team members made six presentations, and chaired two of the sessions.
Year(s) Of Engagement Activity 2024
URL https://netzeroplus.ac.uk/ai-for-net-zero-conference/
 
Description Project Website 
Form Of Engagement Activity Engagement focused website, blog or social media channel
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Public/other audiences
Results and Impact The purpose of creating a project specific website is to show case the digital twin capabilities, and promote the potential applications of the real time digital learning.
Year(s) Of Engagement Activity 2024
URL https://aifornetzero.co.uk/