Demystifying the Data Need of ML-surrogates for CFD Simulations

• URL: http://arxiv.org/abs/2205.08355v1
• Date: Thu, 5 May 2022 04:37:59 GMT
• Title: Demystifying the Data Need of ML-surrogates for CFD Simulations
• Abstract summary: We propose an ML-based surrogate model to predict the temperature distribution inside the cabin of a passenger vehicle. Our results show that the prediction accuracy is high and stable even when the training size is gradually reduced from 2000 to 200. Even when only 50 CFD simulations are used for training, the temperature trend predicted by the ML-surrogate matches quite well with the results from CFD simulations.
• Score: 3.0168882791480978
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Computational fluid dynamics (CFD) simulations, a critical tool in various engineering applications, often require significant time and compute power to predict flow properties. The high computational cost associated with CFD simulations significantly restricts the scope of design space exploration and limits their use in planning and operational control. To address this issue, machine learning (ML) based surrogate models have been proposed as a computationally efficient tool to accelerate CFD simulations. However, a lack of clarity about CFD data requirements often challenges the widespread adoption of ML-based surrogates among design engineers and CFD practitioners. In this work, we propose an ML-based surrogate model to predict the temperature distribution inside the cabin of a passenger vehicle under various operating conditions and use it to demonstrate the trade-off between prediction performance and training dataset size. Our results show that the prediction accuracy is high and stable even when the training size is gradually reduced from 2000 to 200. The ML-based surrogates also reduce the compute time from ~30 minutes to around ~9 milliseconds. Moreover, even when only 50 CFD simulations are used for training, the temperature trend (e.g., locations of hot/cold regions) predicted by the ML-surrogate matches quite well with the results from CFD simulations.

Related papers

• A Surrogate-Augmented Symbolic CFD-Driven Training Framework for Accelerating Multi-objective Physical Model Development [12.349699279273791]
  We propose an extended framework that integrates surrogate modeling into symbolic CFD-driven training in real time to reduce training cost.<n>The proposed surrogate-augmented CFD-driven training framework is demonstrated across a range of statistically one- and two-dimensional flows.<n>In all cases, the framework substantially reduces training cost while maintaining predictive accuracy comparable to that of the original CFD-driven approach.
  arXiv  Detail & Related papers  (2025-12-22T05:04:09Z)
• Differentiable multiphase flow model for physics-informed machine learning in reservoir pressure management [44.41703936689344]
  We introduce a physics-informed machine learning workflow that couples a fully differentiable multiphase flow simulator.<n>The CNN learns to predict fluid extraction rates from heterogeneous permeability fields to enforce pressure limits at critical reservoir locations.<n>We demonstrate that high-accuracy training can be achieved with fewer than three thousand full-physics multiphase flow simulations.
  arXiv  Detail & Related papers  (2025-08-26T20:38:02Z)
• BLIPs: Bayesian Learned Interatomic Potentials [47.73617239750485]
  Machine Learning Interatomic Potentials (MLIPs) are becoming a central tool in simulation-based chemistry.<n>MLIPs do not provide uncertainty estimates by construction, which are fundamental to guide active learning pipelines.<n>BLIP is a scalable, architecture-agnostic variational Bayesian framework for training or fine-tuning MLIPs.
  arXiv  Detail & Related papers  (2025-08-19T17:28:14Z)
• Component-Based Machine Learning for Indoor Flow and Temperature Fields Prediction Latent Feature Aggregation and Flow Interaction [22.85411632321514]
  This study proposes a component-based machine learning (CBML) surrogate modeling approach to replace conventional CFD simulation.<n>CBML consists of three neural networks: a convolutional autoencoder with residual connections (CAER), a multilayer perceptron (MLP) and a convolutional neural network (CNN)<n>Results show that the CBML model accurately and fast predicts two-dimensional aggregated velocity fields across both training and testing datasets.
  arXiv  Detail & Related papers  (2025-07-25T12:57:30Z)
• Data-efficient rapid prediction of urban airflow and temperature fields for complex building geometries [0.0]
  We propose a novel framework that leverages a multi-directional distance feature (MDDF) combined with localized training to achieve effective wind field predictions. We trained on only 24 CFD simulations, our localized Fourier neural operator (Local-FNO) model generates full 3D wind velocity and temperature predictions in under one minute. With mean absolute errors of 0.3 m/s for wind speed and 0.3 $circ$C for temperature on unseen urban configurations, our method demonstrates strong generalization capabilities and significant potential for practical urban applications.
  arXiv  Detail & Related papers  (2025-03-25T14:36:01Z)
• Accelerating Transient CFD through Machine Learning-Based Flow Initialization [0.9754425335596745]
  We present a machine learning-based initialization method that aims to reduce the cost of transient solve by providing more accurate initial fields.<n>We demonstrate 50% reductions in time-to-convergence compared to traditional uniform and potential flow-based initializations.
  arXiv  Detail & Related papers  (2025-03-20T00:51:59Z)
• Physically Interpretable Representation and Controlled Generation for Turbulence Data [39.42376941186934]
  This paper proposes a data-driven approach to encode high-dimensional scientific data into low-dimensional, physically meaningful representations.<n>We validate our approach using 2D Navier-Stokes simulations of flow past a cylinder over a range of Reynolds numbers.
  arXiv  Detail & Related papers  (2025-01-31T17:51:14Z)
• DoMINO: A Decomposable Multi-scale Iterative Neural Operator for Modeling Large Scale Engineering Simulations [2.300471499347615]
  DoMINO is a point cloudbased machine learning model that uses local geometric information to predict flow fields on discrete points. DoMINO is validated for the automotive aerodynamics use case using the DrivAerML dataset.
  arXiv  Detail & Related papers  (2025-01-23T03:28:10Z)
• FlowTS: Time Series Generation via Rectified Flow [67.41208519939626]
  FlowTS is an ODE-based model that leverages rectified flow with straight-line transport in probability space. For unconditional setting, FlowTS achieves state-of-the-art performance, with context FID scores of 0.019 and 0.011 on Stock and ETTh datasets. For conditional setting, we have achieved superior performance in solar forecasting.
  arXiv  Detail & Related papers  (2024-11-12T03:03:23Z)
• PointSAGE: Mesh-independent superresolution approach to fluid flow predictions [0.0]
  High-resolution CFD simulations offer valuable insights into fluid behavior and flow patterns. As resolution increases, computational data requirements and time increase proportionately. We propose PointSAGE, a mesh-independent network to learn the complex fluid flow and directly predict fine simulations.
  arXiv  Detail & Related papers  (2024-04-06T12:49:09Z)
• Bridging the Sim-to-Real Gap with Bayesian Inference [53.61496586090384]
  We present SIM-FSVGD for learning robot dynamics from data. We use low-fidelity physical priors to regularize the training of neural network models. We demonstrate the effectiveness of SIM-FSVGD in bridging the sim-to-real gap on a high-performance RC racecar system.
  arXiv  Detail & Related papers  (2024-03-25T11:29:32Z)
• Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation [40.03897994619606]
  We introduce a layer-wise auto-weighting algorithm for continual and gradual TTA. We propose an exponential min-max scaler to make certain layers nearly frozen while mitigating outliers. Experiments on CIFAR-10C, CIFAR-100C, and ImageNet-C show our method outperforms conventional continual and gradual TTA approaches.
  arXiv  Detail & Related papers  (2023-11-10T03:54:40Z)
• In Situ Framework for Coupling Simulation and Machine Learning with Application to CFD [51.04126395480625]
  Recent years have seen many successful applications of machine learning (ML) to facilitate fluid dynamic computations. As simulations grow, generating new training datasets for traditional offline learning creates I/O and storage bottlenecks. This work offers a solution by simplifying this coupling and enabling in situ training and inference on heterogeneous clusters.
  arXiv  Detail & Related papers  (2023-06-22T14:07:54Z)
• ClimSim-Online: A Large Multi-scale Dataset and Framework for Hybrid ML-physics Climate Emulation [45.201929285600606]
  We present ClimSim-Online, which includes an end-to-end workflow for developing hybrid ML-physics simulators. The dataset is global and spans ten years at a high sampling frequency. We provide a cross-platform, containerized pipeline to integrate ML models into operational climate simulators.
  arXiv  Detail & Related papers  (2023-06-14T21:26:31Z)
• Improving CFD simulations by local machine-learned correction [0.0]
  High-fidelity computational fluid dynamics (CFD) simulations for design space explorations can be exceedingly expensive. This computational cost/accuracy trade-off is a major challenge for modern CFD simulations. We propose a method that uses a trained machine learning model that has learned to predict the discretization error.
  arXiv  Detail & Related papers  (2023-04-28T22:20:42Z)
• Advancing Reacting Flow Simulations with Data-Driven Models [50.9598607067535]
  Key to effective use of machine learning tools in multi-physics problems is to couple them to physical and computer models. The present chapter reviews some of the open opportunities for the application of data-driven reduced-order modeling of combustion systems.
  arXiv  Detail & Related papers  (2022-09-05T16:48:34Z)
• Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator [57.57321628587564]
  We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows. HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
  arXiv  Detail & Related papers  (2022-06-15T17:29:57Z)
• Stacked Generative Machine Learning Models for Fast Approximations of Steady-State Navier-Stokes Equations [1.4150517264592128]
  We develop a weakly-supervised approach to solve the steady-state Navier-Stokes equations under various boundary conditions. We achieve state-of-the-art results without any labeled simulation data. We train stacked models of increasing complexity generating the numerical solutions for N-S equations.
  arXiv  Detail & Related papers  (2021-12-13T05:08:55Z)
• Uncertainty-aware Remaining Useful Life predictor [57.74855412811814]
  Remaining Useful Life (RUL) estimation is the problem of inferring how long a certain industrial asset can be expected to operate. In this work, we consider Deep Gaussian Processes (DGPs) as possible solutions to the aforementioned limitations. The performance of the algorithms is evaluated on the N-CMAPSS dataset from NASA for aircraft engines.
  arXiv  Detail & Related papers  (2021-04-08T08:50:44Z)
• Machine learning for rapid discovery of laminar flow channel wall modifications that enhance heat transfer [56.34005280792013]
  We present a combination of accurate numerical simulations of arbitrary, flat, and non-flat channels and machine learning models predicting drag coefficient and Stanton number. We show that convolutional neural networks (CNN) can accurately predict the target properties at a fraction of the time of numerical simulations.
  arXiv  Detail & Related papers  (2021-01-19T16:14:02Z)
• Application of an automated machine learning-genetic algorithm (AutoML-GA) coupled with computational fluid dynamics simulations for rapid engine design optimization [0.0]
  The present work describes and validates an automated active learning approach, AutoML-GA, for surrogate-based optimization of internal combustion engines. A genetic algorithm is employed to locate the design optimum on the machine learning surrogate surface. It is demonstrated that AutoML-GA leads to a better optimum with a lower number of CFD simulations.
  arXiv  Detail & Related papers  (2021-01-07T17:50:52Z)
• CFDNet: a deep learning-based accelerator for fluid simulations [1.5649420473539182]
  CFD is used to predict engineering quantities of interest, such as the lift on a plane wing or the drag on a motor vehicle. Many systems of interest are prohibitively expensive for design optimization, due to the expense of evaluating CFD simulations. This paper introduces CFDNet -- a physical simulation and deep learning coupled framework.
  arXiv  Detail & Related papers  (2020-05-09T18:06:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.