AB-UPT: Scaling Neural CFD Surrogates for High-Fidelity Automotive Aerodynamics Simulations via Anchored-Branched Universal Physics Transformers

• URL: http://arxiv.org/abs/2502.09692v3
• Date: Fri, 27 Jun 2025 12:59:19 GMT
• Title: AB-UPT: Scaling Neural CFD Surrogates for High-Fidelity Automotive Aerodynamics Simulations via Anchored-Branched Universal Physics Transformers
• Authors: Benedikt Alkin, Maurits Bleeker, Richard Kurle, Tobias Kronlachner, Reinhard Sonnleitner, Matthias Dorfer, Johannes Brandstetter,
• Abstract summary: We introduce Anchored-Branched Universal Physics Transformers (AB-UPT) as a novel modeling scheme for building neural surrogates for computational fluid dynamics (CFD) simulations.<n>AB-UPT is designed to: (i) decouple geometry encoding and prediction tasks via multi-branch operators; (ii) enable scalability to high-resolution outputs via neural simulation in a low-dimensional latent space; (iii) enforce physics consistency by a novel divergence-free formulation.<n>We show that AB-UPT yields state-of-the-art predictive accuracy of surface and volume fields on automotive CFD simulations ranging from
• Score: 14.26753008785739
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Recent advances in neural surrogate modeling offer the potential for transformative innovations in applications such as automotive aerodynamics. Yet, industrial-scale problems often involve volumetric meshes with cell counts reaching 100 million, presenting major scalability challenges. Complex geometries further complicate modeling through intricate surface-volume interactions, while quantities such as vorticity are highly nonlinear and must satisfy strict divergence-free constraints. To address these requirements, we introduce Anchored-Branched Universal Physics Transformers (AB-UPT) as a novel modeling scheme for building neural surrogates for computational fluid dynamics (CFD) simulations. AB-UPT is designed to: (i) decouple geometry encoding and prediction tasks via multi-branch operators; (ii) enable scalability to high-resolution outputs via neural simulation in a low-dimensional latent space, coupled with anchored neural field decoders to predict high-fidelity outputs; (iii) enforce physics consistency by a novel divergence-free formulation. We show that AB-UPT yields state-of-the-art predictive accuracy of surface and volume fields on automotive CFD simulations ranging from 33 thousand up to 150 million mesh cells. Furthermore, our anchored neural field architecture enables the enforcement of hard physical constraints on the physics predictions without degradation in performance, exemplified by modeling divergence-free vorticity fields. Notably, the proposed models can be trained on a single GPU in less than a day and predict industry-standard surface and volume fields within seconds. Additionally, we show that the flexible design of our method enables neural simulation from a computer-aided design geometry alone, omitting the need for costly CFD meshing procedures.

Related papers

• OmniFluids: Unified Physics Pre-trained Modeling of Fluid Dynamics [25.066485418709114]
  We introduce OmniFluids, a unified physics pre-trained operator learning framework.<n>It integrates physics-only pre-training, coarse-grid operator distillation, and few-shot fine-tuning.<n>It significantly outperforms state-of-the-art AI-driven methods in flow field reconstruction and turbulence statistics accuracy.
  arXiv  Detail & Related papers  (2025-06-12T16:23:02Z)
• Flow Matching for Geometric Trajectory Simulation [4.271235935891555]
  N-body systems are a fundamental problem with applications in a wide range of fields, such as molecular dynamics, biochemistry, and pedestrian dynamics.<n>Machine learning has become an invaluable tool for scaling physics-based simulators and developing models directly from experimental data.<n>To generate realistic trajectories, existing methods must learn complex transformations starting from uninformed noise and do not allow for the exploitation of domain-informed priors.<n>We propose STFlow to address this limitation. By leveraging flow matching and data-dependent couplings, STFlow facilitates physics-informed simulation of geometric trajectories without sacrificing model expressivity or scalability.
  arXiv  Detail & Related papers  (2025-05-24T11:18:59Z)
• 3D Neural Operator-Based Flow Surrogates around 3D geometries: Signed Distance Functions and Derivative Constraints [3.100300350494905]
  computational cost of high-fidelity 3D flow simulations remains a significant challenge. We evaluate Deep Operator Networks (DeepONet) and Geometric-DeepONet, a variant that incorporates geometry information via signed distance functions (SDFs) Our results show that Geometric-DeepONet improves boundary-layer accuracy by up to 32% compared to standard DeepONet.
  arXiv  Detail & Related papers  (2025-03-21T16:40:48Z)
• Multifidelity Simulation-based Inference for Computationally Expensive Simulators [5.863359332854155]
  We introduce MF-NPE, a multifidelity approach to neural posterior estimation that leverages inexpensive low-fidelity simulations to infer parameters of high-fidelity simulators within a limited simulation budget.<n> MF-NPE shows comparable performance to current approaches while requiring up to two orders of magnitude fewer high-fidelity simulations.
  arXiv  Detail & Related papers  (2025-02-12T13:59:22Z)
• Transfer learning in Scalable Graph Neural Network for Improved Physical Simulation [37.1565271299621]
  We introduce a pre-training and transfer learning paradigm for graph network simulators.<n>We show that our proposed transfer learning methods allow the model to perform even better when fine-tuned with small amounts of training data.
  arXiv  Detail & Related papers  (2025-02-07T08:18:23Z)
• Geometry Matters: Benchmarking Scientific ML Approaches for Flow Prediction around Complex Geometries [23.111935712144277]
  Rapid yet accurate simulations of fluid dynamics around complex geometries is critical in a variety of engineering and scientific applications.<n>While scientific machine learning (SciML) has shown promise, most studies are constrained to simple geometries.<n>This study addresses this gap by benchmarking diverse SciML models for fluid flow prediction over intricate geometries.
  arXiv  Detail & Related papers  (2024-12-31T00:23:15Z)
• GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects [55.02281855589641]
  GausSim is a novel neural network-based simulator designed to capture the dynamic behaviors of real-world elastic objects represented through Gaussian kernels. We leverage continuum mechanics and treat each kernel as a Center of Mass System (CMS) that represents continuous piece of matter. In addition, GausSim incorporates explicit physics constraints, such as mass and momentum conservation, ensuring interpretable results and robust, physically plausible simulations.
  arXiv  Detail & Related papers  (2024-12-23T18:58:17Z)
• Physics-enhanced Neural Operator for Simulating Turbulent Transport [9.923888452768919]
  This paper presents a physics-enhanced neural operator (PENO) that incorporates physical knowledge of partial differential equations (PDEs) to accurately model flow dynamics. The proposed method is evaluated through its performance on two distinct sets of 3D turbulent flow data.
  arXiv  Detail & Related papers  (2024-05-31T20:05:17Z)
• 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)
• Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators [12.165876595927452]
  Universal Physics Transformers (UPTs) are efficient and unified learning paradigm for a wide range of problems.<n>UPTs operate without grid- or particle-based latent meshes, enabling flexibility across structures and particles.<n>We demonstrate diverse applicability and efficacy of UPTs in mesh-based fluid simulations, and steady-state Reynolds averaged Navier-Stokes simulations.
  arXiv  Detail & Related papers  (2024-02-19T18:52:13Z)
• Neural Operators for Accelerating Scientific Simulations and Design [85.89660065887956]
  An AI framework, known as Neural Operators, presents a principled framework for learning mappings between functions defined on continuous domains. Neural Operators can augment or even replace existing simulators in many applications, such as computational fluid dynamics, weather forecasting, and material modeling.
  arXiv  Detail & Related papers  (2023-09-27T00:12:07Z)
• Learning Controllable Adaptive Simulation for Multi-resolution Physics [86.8993558124143]
  We introduce Learning controllable Adaptive simulation for Multi-resolution Physics (LAMP) as the first full deep learning-based surrogate model. LAMP consists of a Graph Neural Network (GNN) for learning the forward evolution, and a GNN-based actor-critic for learning the policy of spatial refinement and coarsening. We demonstrate that our LAMP outperforms state-of-the-art deep learning surrogate models, and can adaptively trade-off computation to improve long-term prediction error.
  arXiv  Detail & Related papers  (2023-05-01T23:20:27Z)
• NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition [67.46012350241969]
  This paper proposes a general acceleration methodology called NeuralStagger. It decomposing the original learning tasks into several coarser-resolution subtasks. We demonstrate the successful application of NeuralStagger on 2D and 3D fluid dynamics simulations.
  arXiv  Detail & Related papers  (2023-02-20T19:36:52Z)
• 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)
• Multi-fidelity Hierarchical Neural Processes [79.0284780825048]
  Multi-fidelity surrogate modeling reduces the computational cost by fusing different simulation outputs. We propose Multi-fidelity Hierarchical Neural Processes (MF-HNP), a unified neural latent variable model for multi-fidelity surrogate modeling. We evaluate MF-HNP on epidemiology and climate modeling tasks, achieving competitive performance in terms of accuracy and uncertainty estimation.
  arXiv  Detail & Related papers  (2022-06-10T04:54:13Z)
• Investigation of Physics-Informed Deep Learning for the Prediction of Parametric, Three-Dimensional Flow Based on Boundary Data [0.0]
  We present a parameterized surrogate model for the prediction of three-dimensional flow fields in aerothermal vehicle simulations. The proposed physics-informed neural network (PINN) design is aimed at learning families of flow solutions according to a geometric variation.
  arXiv  Detail & Related papers  (2022-03-17T09:54:22Z)
• 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)

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.