UK AI for Turbulence Workshop
Knowledge Center at the British Library, London
26-27 January 2026
The aim of this workshop is to bring together multidisciplinary stakeholders from industry and academia to establish the state-of-the-art in AI applications to turbulence, to showcase UK expertise and capabilities, and to identify key research priorities and collaborative opportunities. The workshop will feature a mix of presentation formats, including keynote lectures from leading researchers, interactive panel discussions, and e-posters for young academics in order to encourage deep engagement between participants from different backgrounds. The events will be designed to maximise networking opportunities and facilitate new collaborations. This workshop will directly inform the development of a strategic white paper around AI for Turbulence.
This event is sponsored by Cambridge University Press, Data-Centric Engineering, the UK Turbulence Consortium and the CCP Turbulence (thanks to funding from UKRI and the Digital Research Infrastructure (DRI) Programme.
This event is sponsored by Cambridge University Press, Data-Centric Engineering, the UK Turbulence Consortium and the CCP Turbulence (thanks to funding from UKRI and the Digital Research Infrastructure (DRI) Programme.
Organising Committee:
Registration:
Registration for this workshop is now closed.
Location:
British Library, Knowledge Centre
The Knowledge Centre is located on the main forecourt outside the main British Library building, at 96 Euston Road, London, NW1 2DB.
Overview of the programme: PDF
All the talks and panel sessions will be held in the main Theatre. The poster session will be held in Bronte/Chaucer rooms. Lunches and breaks will be in the Foyer. A map of the Knowledge Center can be found here.
The drinks reception will be held in the Terrace café of the British Library.
Accommodations:
You will find plenty of hotels within walking distance from the British Library. An affordable option is the Premier Inn hotel near King's Cross.
Feel free to book your accommodation as soon as possible!
Invited Keynote Speakers:
Heng Xiao (University of Stuttgart): Towards a Unified Turbulence Model through Multi-Objective Learning
Andrea Beck (University of Stuttgart): Towards discretization-consistent closure models via reinforcement learning
Invited presentations:
Antonio Attili (Edinburgh): Hybrid generative-AI/physics-based models in LES
Miguel Beneitez (Manchester): Improving turbulence control through explainable deep learning
Xu Chu (Exeter): AI Engineer and AI Scientist based on Agentic-AI
Bharath Ganapathisubramani (Southampton): Data driven predictions for pressure gradient flows
Temistocle Grenga (Southampton): Impact of Adversarial Training on Generative AI for Super-Resolution Turbulence Reconstruction
Luca Magri (Imperial College): Real time modelling and prediction
Olaf Marxen (Surrey): Machine learning applied to laminar-turbulent boundary-layer transition in high-speed flows
Jacob Page (Edinburgh): Online learning for state estimation and orbit continuation, with applications to turbulence
George Papadakis (Imperial College): A scalable data-driven algorithm for forecasting the evolution of turbulent flows from sparse sensor data
Alfredo Pinelli (City St George's): From DNS to wind tunnels: Developing practical ML-based flow control for wall turbulence
Graham Pullan (Cambridge): Some applications of AI in CFD visualisation
George Rigas (Imperial College): Agentic AI for Autonomous Flow Control in Turbulent Environments
Justin Sirignano (Oxford): Online Gradient Flow Methods for Optimizing over the Statistical Steady-State of Turbulent Flows with Applications to Closure Modeling
Sean Symon (Southampton): Assimilation of time-averaged experimental data to infer unknown parameters in separated and wall-bounded flows
Saleh Rezaeiravesh (Manchester): Some Information-theoretic Insights into Turbulence
Zhong-Nan Wang (Birmingham): Data-driven modelling of nonlinear dynamics of sound generation in a mixing layer
e-Posters:
1-Priyam Gupta (Imperial College London): Data driven closure for Koopman control of non-linear systems
2-Osama Ahmed (Imperial College London): Solving nonlinear differential equations with quantum computers and a Fokker-Planck embedding
3-Kaixin Zhu (Imperial College London): Extracting self-similarity from data
4-Omid Bidar (Sheffield): Uncertainty-guided deep learning for sensor placement in data assimilation of turbulent flows
5-Tao Yang (City University Hong Kong): Latent-Space Modeling and Dynamic Mode Identification of Complex Flame Systems
6-Giorgio Maria Cavallazzi (City St. George's): Towards the development of practical tools for ML-based flow control of wall-bounded turbulence
7-Miguel Perez Cuadrado (City St Georges): ML based transition of control of boundary layers
8-Dibyakanti Kumar (Manchester): Generalization Bounds for Solving Navier-Stokes PDE by Neural Nets
9-Kwame Agyei-Baah (Brunel): A CNN Based Framework for Fluid Dynamics
10-Zecai Zhou (Helmholtz-Zentrum Dresden-Rossendorf): Deep Learning Flow Reconstruction from Lagrangian Particle Tracking in Bubble-Induced Turbulence
11-Osama Maklad (Greenwich): Corneal material characterisation via PINNs-based modelling of impinging jets
12-Tobias Flynn (Imperial College London): A Route to High Throughput Direct Numerical Simulations of Turbomachinery Flows for AI Training
13-Andrew Mole (Imperial College London): Turbulence Control in Wind Farms using Reinforcement Learning
14-Ananthu J P( Sheffield): Data-Driven and Physics-Informed Modelling of Axisymmetric Spherical Couette Flow
15-Andrea Nóvoa (Imperial College London): Towards real-time digital turbulence
16-Peter Cassidy (von Karman Institute for Fluid Dynamics): POD analysis of transitional high-lift low-pressure turbine flows
17-Chandan Bose (Birmingham): Data-driven optimisation of flexible nozzles subjected to turbulent rotary wakes
18-Miquel Miravet-Tenés (Southampton): Modelling MRI-driven turbulence in neutron stars
19-Arun Soman Pillai (STFC Hartree Centre): Practicality of Reinforcement Learning for Adaptive Mesh Refinement
20-Michael Mays (Manchester): Surrogate Modelling of Industry-Relevant flows using POD and multi-fidelity Gaussian Process regression
21-Elise Özalp (Imperial College London): Real-time forecasting of chaotic dynamics from sparse data and autoencoders
22-Aan Yudianto (Manchester): Development of Multi-Fidelity Data-Driven Shape Optimisation Framework for Drag Reduction over a Wall-Mounted Hemisphere
23-Daniel Dehtyriov (Oxford): oRANS: Online optimisation of RANS machine learning models with embedded data generation
Panel Sessions:
Neil Ashton (NVIDIA)
Ligang He (Warwick)
Richard Gilham (Bristol HPC)
David Standingford (Zenotech & ERCOFTAC)
Ryan Tunstall (Rolls Royce)
Małgorzata Zimoń (IBM)
Osama Ahmed (Qronon)
+ some academics
- Luca Magri & Sylvain Laizet, Imperial College London
- Andrew Wheeler, University of Cambridge
- Umair Ahmed, University of Newcastle
- Julia Handl & Alistair Revell, University of Manchester
- Dave Emerson & Jeyan Thiyagalingam, SFTC
Registration:
Registration for this workshop is now closed.
Location:
British Library, Knowledge Centre
The Knowledge Centre is located on the main forecourt outside the main British Library building, at 96 Euston Road, London, NW1 2DB.
Overview of the programme: PDF
All the talks and panel sessions will be held in the main Theatre. The poster session will be held in Bronte/Chaucer rooms. Lunches and breaks will be in the Foyer. A map of the Knowledge Center can be found here.
The drinks reception will be held in the Terrace café of the British Library.
Accommodations:
You will find plenty of hotels within walking distance from the British Library. An affordable option is the Premier Inn hotel near King's Cross.
Feel free to book your accommodation as soon as possible!
Invited Keynote Speakers:
Heng Xiao (University of Stuttgart): Towards a Unified Turbulence Model through Multi-Objective Learning
Andrea Beck (University of Stuttgart): Towards discretization-consistent closure models via reinforcement learning
Invited presentations:
Antonio Attili (Edinburgh): Hybrid generative-AI/physics-based models in LES
Miguel Beneitez (Manchester): Improving turbulence control through explainable deep learning
Xu Chu (Exeter): AI Engineer and AI Scientist based on Agentic-AI
Bharath Ganapathisubramani (Southampton): Data driven predictions for pressure gradient flows
Temistocle Grenga (Southampton): Impact of Adversarial Training on Generative AI for Super-Resolution Turbulence Reconstruction
Luca Magri (Imperial College): Real time modelling and prediction
Olaf Marxen (Surrey): Machine learning applied to laminar-turbulent boundary-layer transition in high-speed flows
Jacob Page (Edinburgh): Online learning for state estimation and orbit continuation, with applications to turbulence
George Papadakis (Imperial College): A scalable data-driven algorithm for forecasting the evolution of turbulent flows from sparse sensor data
Alfredo Pinelli (City St George's): From DNS to wind tunnels: Developing practical ML-based flow control for wall turbulence
Graham Pullan (Cambridge): Some applications of AI in CFD visualisation
George Rigas (Imperial College): Agentic AI for Autonomous Flow Control in Turbulent Environments
Justin Sirignano (Oxford): Online Gradient Flow Methods for Optimizing over the Statistical Steady-State of Turbulent Flows with Applications to Closure Modeling
Sean Symon (Southampton): Assimilation of time-averaged experimental data to infer unknown parameters in separated and wall-bounded flows
Saleh Rezaeiravesh (Manchester): Some Information-theoretic Insights into Turbulence
Zhong-Nan Wang (Birmingham): Data-driven modelling of nonlinear dynamics of sound generation in a mixing layer
e-Posters:
1-Priyam Gupta (Imperial College London): Data driven closure for Koopman control of non-linear systems
2-Osama Ahmed (Imperial College London): Solving nonlinear differential equations with quantum computers and a Fokker-Planck embedding
3-Kaixin Zhu (Imperial College London): Extracting self-similarity from data
4-Omid Bidar (Sheffield): Uncertainty-guided deep learning for sensor placement in data assimilation of turbulent flows
5-Tao Yang (City University Hong Kong): Latent-Space Modeling and Dynamic Mode Identification of Complex Flame Systems
6-Giorgio Maria Cavallazzi (City St. George's): Towards the development of practical tools for ML-based flow control of wall-bounded turbulence
7-Miguel Perez Cuadrado (City St Georges): ML based transition of control of boundary layers
8-Dibyakanti Kumar (Manchester): Generalization Bounds for Solving Navier-Stokes PDE by Neural Nets
9-Kwame Agyei-Baah (Brunel): A CNN Based Framework for Fluid Dynamics
10-Zecai Zhou (Helmholtz-Zentrum Dresden-Rossendorf): Deep Learning Flow Reconstruction from Lagrangian Particle Tracking in Bubble-Induced Turbulence
11-Osama Maklad (Greenwich): Corneal material characterisation via PINNs-based modelling of impinging jets
12-Tobias Flynn (Imperial College London): A Route to High Throughput Direct Numerical Simulations of Turbomachinery Flows for AI Training
13-Andrew Mole (Imperial College London): Turbulence Control in Wind Farms using Reinforcement Learning
14-Ananthu J P( Sheffield): Data-Driven and Physics-Informed Modelling of Axisymmetric Spherical Couette Flow
15-Andrea Nóvoa (Imperial College London): Towards real-time digital turbulence
16-Peter Cassidy (von Karman Institute for Fluid Dynamics): POD analysis of transitional high-lift low-pressure turbine flows
17-Chandan Bose (Birmingham): Data-driven optimisation of flexible nozzles subjected to turbulent rotary wakes
18-Miquel Miravet-Tenés (Southampton): Modelling MRI-driven turbulence in neutron stars
19-Arun Soman Pillai (STFC Hartree Centre): Practicality of Reinforcement Learning for Adaptive Mesh Refinement
20-Michael Mays (Manchester): Surrogate Modelling of Industry-Relevant flows using POD and multi-fidelity Gaussian Process regression
21-Elise Özalp (Imperial College London): Real-time forecasting of chaotic dynamics from sparse data and autoencoders
22-Aan Yudianto (Manchester): Development of Multi-Fidelity Data-Driven Shape Optimisation Framework for Drag Reduction over a Wall-Mounted Hemisphere
23-Daniel Dehtyriov (Oxford): oRANS: Online optimisation of RANS machine learning models with embedded data generation
Panel Sessions:
Neil Ashton (NVIDIA)
Ligang He (Warwick)
Richard Gilham (Bristol HPC)
David Standingford (Zenotech & ERCOFTAC)
Ryan Tunstall (Rolls Royce)
Małgorzata Zimoń (IBM)
Osama Ahmed (Qronon)
+ some academics