INFINITY: Neural Field Modeling for Reynolds-Averaged Navier-Stokes Equations

Louis Serrano, Leon Migus, Yuan Yin, Jocelyn Ahmed Mazari, Patrick Gallinari

International Conference on Machine Learning (ICML), 1st workshop on Synergy of Scientific and Machine Learning Modeling, SynS & ML ICML, Honolulu, Hawaii, USA. July, 2023.


For numerical design, the development of efficient and accurate surrogate models is paramount. They allow us to approximate complex physical phenomena, thereby reducing the computational burden of direct numerical simulations. We propose INFINITY, a deep learning model that utilizes implicit neural representations (INRs) to address this challenge. Our framework encodes geometric information and physical fields into compact representations and learns a mapping between them to infer the physical fields. We use an airfoil design optimization problem as an example task and we evaluate our approach on the challenging AirfRANS dataset, which closely resembles real-world industrial use-cases. The experimental results demonstrate that our framework achieves state-of-the-art performance by accurately inferring physical fields throughout the volume and surface. Additionally we demonstrate its applicability in contexts such as design exploration and shape optimization: our model can correctly predict drag and lift coefficients while adhering to the equations.


1/ Sorbonne Université, CNRS, ISIR, 75005 Paris, France
2/ Sorbonne Université, CNRS, Laboratoire Jacques-Louis Lions, 75005 Paris, France
3/ Extrality, 75002 Paris, France
4/ Criteo AI Lab, Paris, France


/ Other published papers

Speed up Aerodynamic Optimization Thanks to Deep Learning Physics: Stellantis RAM Truck Example
Learn more
Multi-Objective Hull Form Optimization with CAD Engine-based Deep Learning Physics for 3D Flow Prediction
Jocelyn Ahmed Mazari, Antoine Reverberi, Pierre Yser, Sebastian Sigmund
Learn more
Deep Learning Physics for the Hydrodynamics of Trading Vessels
Jonas Verrière, Jocelyn Ahmed Mazari, Antoine Reverberi, Francis Hueber
Learn more
AirfoilRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged-Navier–Stokes Solutions
Florent Bonnet, Jocelyn Ahmed Mazari, Paola Cinnella, Patrick Gallinari
Learn more
An extensible Benchmarking Graph-Mesh dataset for studying Steady-State Incompressible Navier-Stokes Equations
Florent Bonnet, Jocelyn Ahmed Mazari, Thibaut Munzer, Pierre Yser, Patrick Gallinari
Learn more
Multi-scale Physical Representations for Approximating PDE Solutions with Graph Neural Operators
Léon Migus, Yuan Yin, Jocelyn Ahmed Mazari, Patrick Gallinari
Learn more
Need to hit production with short go-to-market and better control?
Cookie Consent

By clicking “Accept”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts.