Computational Fluid Dynamics

Also known as CFD

Computational fluid dynamics (CFD) uses numerical methods to solve equations describing fluid motion, turbulence, heat transfer, and related processes. Finite-volume and finite-element solvers, alongside RANS, LES, and DNS, provide established ways to simulate flows; neural operators, graph networks, physics-informed neural networks, and generative models are increasingly used as surrogates or for reconstruction. These approaches can reduce the cost of simulation, support design and flow control, and infer fields from sparse measurements. A central challenge is balancing speed with physical consistency and reliable generalization across geometries and regimes, especially over long predictions; learned models still need validation against trusted simulations and experiments.

Latest papers

279 papers37 papers in the last four weeks, up 9% on the four weeks before. 0.2% of all new papers.

Addressing A Posteriori Performance Degradation in Neural Network Subgrid Stress Models
Nov 21, 2025Andy Wu, Sanjiva K. LeleNeural Network Generalization Data Augmentation
Department of Aeronautics and Astronautics, Stanford University, Stanford, California, USA · Department of Mechanical Engineering, Stanford University, Stanford, California, USA
Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
Nov 19, 2025Michael McCabe, Payel Mukhopadhyay, Tanya Marwah +22Physics-Based Simulation Computational Fluid Dynamics
Polymathic AI · Flatiron Institute · New York University +9
RheOFormer: A generative transformer model for simulation of complex fluids and flows
Oct 1, 2025Maedeh Saberi, Amir Barati Farimani, Safa JamaliNeural Surrogate Modeling Transformer
Department of Mechanical and Industrial Engineering, Northeastern University, Boston, MA 02115, USA · Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA
A Flow-rate-conserving CNN-based Domain Decomposition Method for Blood Flow Simulations
Sep 19, 2025Simon Klaes, Axel Klawonn, Natalie Kubicki +4PDE Solving PDE Surrogate Modeling
Department of Mathematics and Computer Science, University of Cologne, Germany · Center for Data and Simulation Science, University of Cologne, Germany · Institute for Advanced Simulation (IAS-2), Forschungszentrum Jülich, Germany +1
Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
Jul 1, 2025Anantha Narayanan Suresh Babu, Akhil Sadam, Pierre F. J. LermusiauxDiffusion Model Guidance Data Assimilation
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, USA · Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, USA
Diff-SPORT: Diffusion-based Sensor Placement Optimization and Reconstruction of Turbulent flows in urban environments
May 30, 2025Abhijeet Vishwasrao, Sai Bharath Chandra Gutha, Andres Cremades +8Diffusion-Based Inverse Problems Inverse Problems
Department of Aerospace Engineering, University of Michigan, Ann Arbor, USA · FLOW, Engineering Mechanics, KTH Royal Institute of Technology, Stockholm, Sweden · Division of Robotics, Perception and Learning, School of EECS, KTH Royal Institute of Technology, Stockholm, Sweden +7
Surrogate Modeling of 3D Rayleigh-Benard Convection with Equivariant Autoencoders
May 19, 2025Fynn Fromme, Hans Harder, Christine Allen-Blanchette +1Autoencoders PDE Surrogate Modeling
Lamarr Institute for Machine Learning and Artificial Intelligence and Karlsruhe Institute of Technology · Lamarr Institute for Machine Learning and Artificial Intelligence and Department of Computer Science at Paderborn University · Department of Mechanical and Aerospace Engineering Center for Statistics and Machine Learning Princeton University +1
AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD
May 19, 2025Xigui Li, Yuanye Zhou, Feiyang Xiao +16Neural Surrogate Modeling Synthetic Data Pretraining
Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China · Shanghai Academy of Artificial Intelligence for Science, Shanghai, China · Human Phenome Institute, Fudan University, Shanghai, China +1
Fast localized urban microclimate emulator: wind and temperatures in unseen urban morphologies
Mar 25, 2025Shaoxiang Qin, Theodore Potsis, Dongxue Zhan +3PDE Surrogate Modeling Computational Fluid Dynamics
Department of Building, Civil and Environmental Engineering, Cetner Zero Energy Building Studies, Concordia University, Montreal, Canada · School of Computer Science, McGill University, Montreal, Canada · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

Nov 21, 2025J/K move · Enter open · S save

Addressing A Posteriori Performance Degradation in Neural Network Subgrid Stress Models

Andy Wu, Sanjiva K. Lele

Department of Aeronautics and Astronautics, Stanford University, Stanford, California, USA · Department of Mechanical Engineering, Stanford University, Stanford, California, USA

Neural Network Generalization Data Augmentation Computational Fluid Dynamics

Open paper AskPDF arXiv

Neural network subgrid stress models often have a priori performance that is far better than the a posteriori performance, leading to neural network models that look very promising a priori completely failing in a posteriori Large Eddy Simulations (LES). This performance gap can be decreased by combining two different methods, training data augmentation and reducing input complexity to the neural network. Augmenting the training data with two different filters before training the neural networks has no performance degradation a priori as compared to a neural network trained with one filter. A posteriori, neural networks trained with two different filters are far more robust across two different LES codes with different numerical schemes. In addition, by ablating away the higher order terms input into the neural network, the a priori versus a posteriori performance changes become less apparent. When combined, neural networks that use both training data augmentation and a less complex set of inputs have a posteriori performance far more reflective of their a priori evaluation.