Real-time digital optimisation and decision making for energy and transport systems
Lead Research Organisation:
Imperial College London
Department Name: Aeronautics
Abstract
In this project, we will seamlessly combine two disciplines that have been historically received continuous government and industrial funding: physics-based modelling, which is generalisable and robust but may require tremendous computational cost, and machine learning, which is adaptive and fast to be evaluated but not easily generalisable and robust. The intersection of the two spawns scientific machine learning, which maximises the strengths and minimises the weaknesses of the two approaches.
The data will be provided by high-fidelity simulations and experiments, from the UK state-of-the-art facilities and software. The efficiency of the machine learning training will be maximised for the algorithms to require minimal energy (thereby, producing minimal emissions by minimising electricity consumption). This project builds upon large UK and EU funded expertise in scientific machine learning and simulation, which will be generalised to fast, real-time decision making. The most significant bottleneck of most scientific machine learning is that they need time to be re-trained offline when new data becomes available. We will transform offline paradigms into real-time approaches for the models to re-adapt and provide accurate estimates on the fly. This project will culminate into the delivery of practical digital twins (defined as digital counterparts of real world physical systems or processes that can be used for simulation, prediction of behaviour to inputs, monitoring, maintenance, planning and optimisation) to solve currently intractable problems in wind energy, hydrogen, and road transportation. This project will transfer the technical achievements and real-time digital twin to policy-making.
The data will be provided by high-fidelity simulations and experiments, from the UK state-of-the-art facilities and software. The efficiency of the machine learning training will be maximised for the algorithms to require minimal energy (thereby, producing minimal emissions by minimising electricity consumption). This project builds upon large UK and EU funded expertise in scientific machine learning and simulation, which will be generalised to fast, real-time decision making. The most significant bottleneck of most scientific machine learning is that they need time to be re-trained offline when new data becomes available. We will transform offline paradigms into real-time approaches for the models to re-adapt and provide accurate estimates on the fly. This project will culminate into the delivery of practical digital twins (defined as digital counterparts of real world physical systems or processes that can be used for simulation, prediction of behaviour to inputs, monitoring, maintenance, planning and optimisation) to solve currently intractable problems in wind energy, hydrogen, and road transportation. This project will transfer the technical achievements and real-time digital twin to policy-making.
Organisations
- Imperial College London (Lead Research Organisation)
- University of Oxford (Collaboration)
- University of Cambridge (Collaboration)
- WS Atkins (Collaboration)
- UNIVERSITY OF EDINBURGH (Collaboration)
- nVIDIA (Collaboration, Project Partner)
- Engys Ltd (UK) (Project Partner)
- Atkins Ltd (Project Partner)
- Catesby Projects (Project Partner)
Publications
Bempedelis N
(2024)
Data-driven optimisation of wind farm layout and wake steering with large-eddy simulations
in Wind Energy Science
Mole A
(2024)
Multi-fidelity Bayesian Optimisation of Wind Farm Wake Steering using Wake Models and Large Eddy Simulations
in Flow, Turbulence and Combustion
Nóvoa A
(2024)
A real-time digital twin of azimuthal thermoacoustic instabilities
in Journal of Fluid Mechanics
Nóvoa A
(2024)
Inferring unknown unknowns: Regularized bias-aware ensemble Kalman filter
in Computer Methods in Applied Mechanics and Engineering
Ozan D
(2024)
Data-driven computation of adjoint sensitivities without adjoint solvers: An application to thermoacoustics
in Physical Review Fluids
Traverso T
(2023)
Data-driven modeling for drop size distributions
in Physical Review Fluids
Weissenbacher M
(2025)
Reinforcement Learning of Chaotic Systems Control in Partially Observable Environments
in Flow, Turbulence and Combustion
Xia C
(2024)
Active flow control for bluff body drag reduction using reinforcement learning with partial measurements
in Journal of Fluid Mechanics
| Description | Digital twins - the project has achieved the development of digital twins and decision making algorithms that require less computing power than existing alternatives, while achieving state-of-the-art accuracy and superior robustness to sensor noise. By combining real-world data from sensors with physics-informed data assimilation methods, these tools offer a deeper insight into real-world physical systems. Wake steering - during this research the already state-of-the-art high-fidelity simulator, XCOMPACT3D, has been developed even further to accelerate the solution of the unsteady incompressible Navier-Stokes equations. It continues to be one of the four flagship solvers in the UK Turbulence Consortium (UKTC). Road transport - In laboratory realistic conditions the project has proven that by installing novel autonomous, dynamically adjustable flaps on the rear of heavy road vehicles drag reduction can improved threefold. A cutting-edge AI controller-based on a reinforcement learning technique-has been integrated into the flap system which allows the flaps to adapt in real time to turbulence and changing external conditions. The algorithm learns from limited observations to continually fine-tune the flap positioning and respond optimally to the complex, turbulent flow. Consequently, the flaps autonomously adjust their movement for maximum drag reduction and enhanced vehicle efficiency. This is the first time that AI has been used in this type of drag reduction scenario. Further funding - building on the bench marking research carried out in the HPC work package, EPCC and Imperial have received further funding to continue this important work in a new research project: Towards a more sustainable High Performance Computing sector: a hardware/software co-design proof-of- concept. |
| Exploitation Route | Digital Twins - the outcomes of this research will be taken forward in further research, specifically conducted by Andrea Novoa, who has been awarded a prestigious research fellowship to continue advancing this field of research. Wake steering - the outcomes of this research will be taken forward in the form of further research with the long-term goal of approaching offshore wind farm operators to trail the software in this field. Road Transport optimisation - the outcomes of this research will be taken forward in the form of further research with the long-term goal of working with haulage companies to trial the automated trailer flaps in a real world environment. |
| Sectors | Communities and Social Services/Policy Digital/Communication/Information Technologies (including Software) Energy Environment Transport |
| URL | https://aifornetzero.co.uk/about/ |
| Description | Dr Georgios Rigas - part of the AI for Decarbonisation's Virtual Centre of Excellence's Expert Working Group |
| Geographic Reach | National |
| Policy Influence Type | Participation in a guidance/advisory committee |
| URL | https://www.digicatapult.org.uk/programmes/programme/advice/ |
| Description | Dr Georgios Rigas presented in Evidence Week 2022 |
| Geographic Reach | National |
| Policy Influence Type | Participation in a guidance/advisory committee |
| Impact | Using novel audio-visual displays to demonstrate the way that air flows over road vehicles and aeroplane wings, Dr Rigas explained to MPs the huge savings that better aerodynamic design will mean for vehicles - both in terms of savings on fuel costs, and on the associated reductions in harmful emissions. Reviewing evidence from the US state of California, where aerodynamic improvements to vehicles have been mandated by state legislation, Dr Rigas showed that fuel savings of billions of dollars over the last few years and almost one million tonnes of CO2 reductions have resulted from the real-world applications of novel aerodynamic technologies. Dr Rigas was also able to demonstrate how new technologies developed at Imperial College will deliver even greater efficiencies. By replacing the current physical modifications to freight vehicles with jets of air capable of replicating their drag-reducing effects, these new improvements are calculated to drive fuel savings up from around 5% (in the Californian example) to nearer 20%. |
| URL | https://www.imperial.ac.uk/news/241916/imperial-aerodynamics-expert-briefs-mps-future/ |
| Description | Imperial Policy Forum |
| Geographic Reach | Local/Municipal/Regional |
| Policy Influence Type | Participation in a guidance/advisory committee |
| Impact | Merging the digital world with the physical world to increase efficiencies in existing road transport and wind energy technologies and the use of AI in delivering carbon neutral digital research infrastructure (DRI). |
| URL | https://aifornetzero.co.uk/ai-for-net-zero-work-presented-to-the-uk-department-for-energy-security-n... |
| Description | Submission to Environmental Audit Committee - Sustainable electrification of the UK economy |
| Geographic Reach | National |
| Policy Influence Type | Contribution to a national consultation/review |
| URL | https://committees.parliament.uk/writtenevidence/121655/html/ |
| Description | Towards a more sustainable High Performance Computing sector: a hardware/software co-design proof-of-concept |
| Amount | £1,361,662 (GBP) |
| Funding ID | EP/Z533701/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 01/2025 |
| End | 06/2027 |
| Title | CHAROT: ROBUSTLY CONTROLLING CHAOTIC PDES WITH PARTIAL OBSERVATIONS |
| Description | CHAROT, an attention based memory architecture designed to augment actor-critic reinforcement learning algorithms. |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2024 |
| Provided To Others? | Yes |
| Impact | In the control of chaotic systems, small changes of the controller output may incur large changes in dynamics and the resulting observations. These small errors may accumulate quickly in the hidden state of an LSTM and prevent it from extracting a relevant latent state. The attention mechanism used to update the memory of CHAROT is more robust to small changes in observations, due to the averaging over past memories and new observations in the Transformer block. We therefore conclude that attention mechanisms such as Transformers are better suited to the control of chaotic systems than recurrent architectures such as LSTMs (hence CHAROT = Chaos-Robust-Transformers). This is unexpected as RNNs are typically the architecture of choice for enhancing controllers with memory. |
| URL | https://github.com/maxweissenbacher/charot?tab=readme-ov-file |
| Title | Real Time Bias-aware data assimilation |
| Description | Real-time digital twin of azimuthal thermoacoustics of a hydrogen-based annular combustor. The digital twin seamlessly combines two sources of information about the system (i) a physics-based low-order model; and (ii) raw and sparse experimental data from microphones, which contain both aleatoric noise and turbulent fluctuations. |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2024 |
| Provided To Others? | Yes |
| Impact | The digital twin generalizes to all equivalence ratios, which bridges the gap of existing models. This work opens new opportunities for real-time digital twinning of multi-physics problems. |
| URL | https://github.com/AI-for-Net-Zero/real-time-bias-aware-DA?tab=readme-ov-file |
| Title | Square2DFlowControlDRL-PM-NARX-SB3 |
| Description | This repository contains the code corresponding to our manuscript "Active Flow Control for Bluff Body Drag Reduction Using Reinforcement Learning with Partial Measurements", preprint accessible at https://arxiv.org/abs/2307.12650. This code implements reinforcement learning control with a NARX-modelled controller with Soft Actor-Critic, to reduce the drag due to vortex shedding in the wake of a 2D square body. |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2024 |
| Provided To Others? | Yes |
| Impact | Active flow control for drag reduction with reinforcement learning (RL) is performed in the wake of a 2D square bluff body at laminar regimes with vortex shedding. Controllers parameterised by neural networks are trained to drive two blowing and suction jets that manipulate the unsteady flow. RL with full observability (sensors in the wake) successfully discovers a control policy which reduces the drag by suppressing the vortex shedding in the wake. However, a non-negligible performance degradation (~50% less drag reduction) is observed when the controller is trained with partial measurements (sensors on the body). To mitigate this effect, we propose an energy-efficient, dynamic, maximum entropy RL control scheme. First, an energy-efficiency-based reward function is proposed to optimise the energy consumption of the controller while maximising drag reduction. Second, the controller is trained with an augmented state consisting of both current and past measurements and actions, which can be formulated as a nonlinear autoregressive exogenous model, to alleviate the partial observability problem. Third, maximum entropy RL algorithms (Soft Actor Critic and Truncated Quantile Critics) which promote exploration and exploitation in a sample efficient way are used and discover near-optimal policies in the challenging case of partial measurements. Stabilisation of the vortex shedding is achieved in the near wake using only surface pressure measurements on the rear of the body, resulting in similar drag reduction as in the case with wake sensors. The proposed approach opens new avenues for dynamic flow control using partial measurements for realistic configurations. |
| URL | https://github.com/AI-for-Net-Zero/Square2DFlowControlDRL-PM-NARX-SB3?tab=readme-ov-file |
| Title | Wind-RL: Reinforcement Learning for Wind Farm Control |
| Description | Multi-fidelity Bayesian Optimisation of Wind Farm Wake Steering using Wake Models and Large Eddy Simulations. As large eddy simulations are much more expensive to run than analytical wake models, a multi-fidelity Bayesian optimisation framework is introduced. |
| Type Of Material | Computer model/algorithm |
| Year Produced | 2024 |
| Provided To Others? | No |
| Impact | This implements a multi-fidelity surrogate model, that is able to capture the non-linear relationship between the analytical wake models and the large eddy simulations, and a multi-fidelity acquisition function to determine the configuration and fidelity of each optimisation iteration. This allows for fewer configurations to be evaluated with the more expensive large eddy simulations than a single-fidelity optimisation, whilst producing comparable optimisation results. The same total wind farm power improvements can then be found for a reduced computational cost. |
| URL | https://github.com/AI-for-Net-Zero/Wind-RL |
| Description | Atkins advisory services. |
| Organisation | WS Atkins |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | invitation and inclusion of advisory board meetings and continuous project updates. |
| Collaborator Contribution | 4 days of aggregate monthly support from technical specialists across our business. This support could be utilised across a number of activities potentially including: • Inputs to technical meetings and brainstorming sessions on digital twins • Engaging in collaborative projects on a case-by-case basis • Engaging in seminars and/or workshops on technical topics of mutual interest • Market analysis • Participation in the advisory board • Contributing to the long-term strategy for sustainable development and technology exploitation |
| Impact | Inputs to technical meetings and brainstorming sessions on digital twins Engaging in collaborative projects on a case-by-case basis Engaging in seminars and/or workshops on technical topics of mutual interest |
| Start Year | 2023 |
| Description | EPPC (The University of Edinburgh) |
| Organisation | University of Edinburgh |
| Department | Edinburgh Parallel Computing Centre (EPCC) |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | Collaboratively working on WP2 of the project. |
| Collaborator Contribution | Collaboratively working on WP2 of the project. |
| Impact | Ensuring the use of AI for net zero solutions is net beneficial. Assess and explore the energy efficiency of AI applications and propose recommendations that will improve and encourage best practices around sustainable AI workloads on HPC systems. |
| Start Year | 2023 |
| Description | NVIDIA |
| Organisation | NVIDIA |
| Country | Global |
| Sector | Private |
| PI Contribution | --> discussion with NVIDIA with the aim to prepare a proposal for the ExCALIBUR project (software development) |
| Collaborator Contribution | --> discussion with NVIDIA with the aim to prepare a proposal for the ExCALIBUR project (software development) |
| Impact | --> preparation of a proposal for the ExCALIBUR project (software development) |
| Start Year | 2020 |
| Description | University of Cambridge |
| Organisation | University of Cambridge |
| Department | Department of Pure Mathematics and Mathematical Statistics |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | Translating our research into effective evidence which policymakers can use to work towards a net zero society. |
| Collaborator Contribution | Collaborating across the policy landscape, working with our team, the wider scientific community, members of the public, government and other organisations. Ensure that multiple stakeholders are simultaneously involved in the communication of our research, allowing policies to make use of, and even drive, high-quality and impactful research. |
| Impact | Ensure that multiple stakeholders are simultaneously involved in the communication of our research, allowing policies to make use of, and even drive, high-quality and impactful research. |
| Start Year | 2023 |
| Description | University of Oxford |
| Organisation | University of Oxford |
| Department | Somerville College |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | Applying our AI technologies and framework to hydrogen energy test case to demonstrate their potential to help achieve carbon net zero. |
| Collaborator Contribution | We will practically address key design questions for modelling and control of hydrogen-based systems to make them operate in safe conditions. |
| Impact | Addressing key design questions for modelling and control of hydrogen-based systems to make them operate in safe conditions. |
| Start Year | 2023 |
| Title | 2DECOMP&FFT |
| Description | The 2DECOMP&FFT library is a software framework written in modern Fortran to build large scale parallel applications. It is designed for applications using three-dimensional structured meshes with a particular focus on spatially implicit numerical algorithms. However, the library can be easily used with other discretisation schemes based on a structured layout and where pencil decomposition can apply. It is based on a general-purpose 2D pencil decomposition for data distribution and data Input Output (I/O). A 1D slab decomposition is also available as a special case of the 2D pencil decomposition. The library includes a highly scalable and efficient interface to perform three-dimensional Fast Fourier Transforms (FFTs). The library has been designed to be user-friendly, with a clean application programming interface hiding most communication details from application developers, and portable with support for modern CPUs and NVIDIA GPUs (support for AMD and Intel GPUs to follow). |
| Type Of Technology | Software |
| Year Produced | 2023 |
| Open Source License? | Yes |
| Impact | Possibility to use GPU hardware |
| URL | https://www.theoj.org/joss-papers/joss.05813/10.21105.joss.05813.pdf |
| Title | Xcompact3d |
| Description | Xcompact3d is a Fortran-based framework of high-order finite-difference flow solvers dedicated to the study of turbulent flows. Dedicated to Direct and Large Eddy Simulations (DNS/LES) for which the largest turbulent scales are simulated, it can combine the versatility of industrial codes with the accuracy of spectral codes. Its user-friendliness, simplicity, versatility, accuracy, scalability, portability and efficiency makes it an attractive tool for the Computational Fluid Dynamics community. XCompact3d is currently able to solve the incompressible and low-Mach number variable density Navier-Stokes equations using sixth-order compact finite-difference schemes with a spectral-like accuracy on a monobloc Cartesian mesh. It was initially designed in France in the mid-90's for serial processors and later converted to HPC systems. It can now be used efficiently on hundreds of thousands CPU cores to investigate turbulence and heat transfer problems thanks to the open-source library 2DECOMP&FFT (a Fortran-based 2D pencil decomposition framework to support building large-scale parallel applications on distributed memory systems using MPI; the library has a Fast Fourier Transform module). When dealing with incompressible flows, the fractional step method used to advance the simulation in time requires to solve a Poisson equation. This equation is fully solved in spectral space via the use of relevant 3D Fast Fourier transforms (FFTs), allowing the use of any kind of boundary conditions for the velocity field. Using the concept of the modified wavenumber (to allow for operations in the spectral space to have the same accuracy as if they were performed in the physical space), the divergence free condition is ensured up to machine accuracy. The pressure field is staggered from the velocity field by half a mesh to avoid spurious oscillations created by the implicit finite-difference schemes. The modelling of a fixed or moving solid body inside the computational domain is performed with a customised Immersed Boundary Method. It is based on a direct forcing term in the Navier-Stokes equations to ensure a no-slip boundary condition at the wall of the solid body while imposing non-zero velocities inside the solid body to avoid discontinuities on the velocity field. This customised IBM, fully compatible with the 2D domain decomposition and with a possible mesh refinement at the wall, is based on a 1D expansion of the velocity field from fluid regions into solid regions using Lagrange polynomials or spline reconstructions. In order to reach high velocities in a context of LES, it is possible to customise the coefficients of the second derivative schemes (used for the viscous term) to add extra numerical dissipation in the simulation as a substitute of the missing dissipation from the small turbulent scales that are not resolved. Xcompact3d is currently being used by many research groups worldwide to study gravity currents, wall-bounded turbulence, wake and jet flows, wind farms and active flow control solutions to mitigate turbulence. |
| Type Of Technology | Software |
| Year Produced | 2019 |
| Open Source License? | Yes |
| Impact | see list of publications |
| URL | http://www.incompact3d.com |
| Title | https://github.com/AI-for-Net-Zero |
| Description | Software implementing the algorithmic outputs on Real Time optimisation and decision making for energy and transport systems. The algorithms can be accessed from the wider community here: https://github.com/AI-for-Net-Zero |
| Type Of Technology | Software |
| Year Produced | 2023 |
| Open Source License? | Yes |
| Impact | State of the art algorithms enabling the real-time optimisation and decision making for energy and transport systems. |
| URL | https://github.com/AI-for-Net-Zero |
| Description | AI for NetZero Webinars |
| 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 | Study participants or study members |
| Results and Impact | This webinar series is organised by Heriot-Watt University with the support of all the projects that are part the Net Zero call. Team members of our project have presented on five occasions. |
| Year(s) Of Engagement Activity | 2024,2025 |
| URL | https://www.youtube.com/@ai4netzero |
| Description | AI-UK |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| 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. |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://www.turing.ac.uk/events/ai-uk-2025 |
| Description | Aeronautics Research Showcase 2024 |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Postgraduate students |
| Results and Impact | The project PDRAs joined this event by presenting, sitting on discussion panels, and presenting posters. This event aimed to showcase all the the latest research in the department. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.imperial.ac.uk/events/178346/aeronautics-research-showcase-2024/#:~:text=A%20Research%20... |
| 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 | 2025 |
| URL | https://youtu.be/cPMpxML669I |
| 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 | New Scientist Live |
| 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 | On the 12th - 14th October 2024, the AI for Net Zero Project held a stand at New Scientist Live, the world's greatest festival of ideas and discoveries. The event was held at the ExCel centre in East London and included three days of activity packed fun! The crowd of over 20,000 people was hugely diverse, ranging from pre-school children to retired people, and all the sectors of society in between. More than half of the visitors said that they had come to learn something new and/or because they just love science. The AI for Net Zero Team certainly experienced this curiosity and love of science welcoming hundreds of visitors to the project stand. The team engaged with as many people as possible by demonstrating different parts of the project in easily understandable 'experiments' including, but not limited to, learning to balance a stick on your hand and explaining how we teach computers to learn in the same way, a simple computer app looking at the most efficient way to arrange wind farms, a model lorry demonstrating aero dynamics, and a hydrogen safety model demonstration. The event is thought to be a huge success for all of the research team, being the first time for many of them in which they have needed to explain their and others' research in simple terms, to such a varied and non-technical audience. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://live.newscientist.com/ |
| 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 | News article about the Road Transport work package |
| Form Of Engagement Activity | A press release, press conference or response to a media enquiry/interview |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | The road transport research team uses the National Wind Tunnel Facility (NWTF) at Imperial to characterize the dynamic air flow around a scale model truck, to inform the design of intelligent, adjustable flaps to reduce drag and cut fuel consumption. An independent news reporter interviewed the PDRAs involved with wind tunnel experiments and wrote a promotional article that has been published on the National Wind Tunnel Facilities website. |
| Year(s) Of Engagement Activity | 2025 |
| URL | https://www.nwtf.ac.uk/case-study/the-future-of-freight-nwtf-team-design-ai-assisted-moveable-flaps-... |
| 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 | National |
| 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/ |
| Description | Webinar to meet the project researchers |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Schools |
| Results and Impact | The PDRAs of the project hosted a webinar to prospective undergrad and postgrad students to promote the project and show potential students what you can do with a degree in aeronautics, and what a career in research could look like. |
| Year(s) Of Engagement Activity | 2024 |
| URL | https://www.imperial.ac.uk/events/183568/aeronautical-engineering-meet-our-researchers-ai-energy-tra... |