mlsanityData to 14 Oct 2026

From Zero to Turbulence: Generative Modeling for 3D Flow Simulation

arXiv 2306.01776 ↗First posted 29 May 2023physics.flu-dyn cs.LGcited by 49

Not on the map. Why?

Cited by 27 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Simulations of turbulent flows in 3D are one of the most expensive simulations in computational fluid dynamics (CFD). Many works have been written on surrogate models to replace numerical solvers for fluid flows with faster, learned, autoregressive models. However, the intricacies of turbulence in three dimensions necessitate training these models with very small time steps, while generating realistic flow states requires either long roll-outs with many steps and significant error accumulation or starting from a known, realistic flow state - something we aimed to avoid in the first place. Instead, we propose to approach turbulent flow simulation as a generative task directly learning the manifold of all possible turbulent flow states without relying on any initial flow state. For our experiments, we introduce a challenging 3D turbulence dataset of high-resolution flows and detailed vortex structures caused by various objects and derive two novel sample evaluation metrics for turbulent flows. On this dataset, we show that our generative model captures the distribution of turbulent flows caused by unseen objects and generates high-quality, realistic samples amenable for downstream applications without access to any initial state.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 46 of its 77 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

46 of 77 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  9. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  10. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  11. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  12. 2023Consistency Modelscited by 1,822
34 more
  1. 2018Group Normalizationcited by 1,524
  2. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  3. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  4. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,234
  5. 2021Variational Diffusion Modelscited by 1,153
  6. 2021E(n) Equivariant Graph Neural Networkscited by 965
  7. 2020On Layer Normalization in the Transformer Architecturecited by 922
  8. 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
  9. 2021Machine learning accelerated computational fluid dynamicscited by 471
  10. 2022PDEBENCH: An Extensive Benchmark for Scientific Machine Learningcited by 413
  11. 2022Message Passing Neural PDE Solverscited by 386
  12. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 354
  13. 2020Universal Differential Equations for Scientific Machine Learningcited by 353
  14. 2021GemNet: Universal Directional Graph Neural Networks for Moleculescited by 343
  15. 2020Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Datacited by 248
  16. 2019Towards Physics-informed Deep Learning for Turbulent Flow Predictioncited by 204
  17. 2022Towards Multi-spatiotemporal-scale Generalized PDE Modelingcited by 197
  18. 2018Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discoverycited by 194
  19. 2022A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstructioncited by 152
  20. 2018Deep Fluids: A Generative Network for Parameterized Fluid Simulationscited by 121
  21. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 101
  22. 2021Learned Coarse Models for Efficient Turbulence Simulationcited by 91
  23. 2022AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutionscited by 82
  24. 2023Eagle: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformerscited by 57
  25. 2020CFDNet: a deep learning-based accelerator for fluid simulationscited by 40
  26. 2022Learning to Solve PDE-constrained Inverse Problems with Graph Networkscited by 37
  27. 2022Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networkscited by 34
  28. 2022Physics-Embedded Neural Networks: Graph Neural PDE Solvers with Mixed Boundary Conditionscited by 33
  29. 2023A Denoising Diffusion Model for Fluid Field Predictioncited by 32
  30. 2021Generative Modeling of Turbulencecited by 26
  31. 2021An Extensible Benchmark Suite for Learning to Simulate Physical Systemscited by 24
  32. 2023Generalization capabilities of conditional GAN for turbulent flow under changes of geometrycited by 4
  33. 2014Acceleration of a Full-scale Industrial CFD Application with OP2cited by 1
  34. 2017Enabling rootless Linux Containers in multi-user environments: the udocker toolcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 13; 2025: 18; 2026: 16.

49 papers.

Sort:

By area:

  1. 2024DiffusionPDE: Generative PDE-Solving Under Partial Observationcited by 108
  2. 2024Physics-Informed Diffusion Modelscited by 90
  3. 2023Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulationcited by 71
  4. 2024Probabilistic Forecasting with Stochastic Interpolants and F"ollmer Processescited by 66
  5. 2024Flow Matching with Gaussian Process Priors for Probabilistic Time Series Forecastingcited by 43
  6. 2025Generative Latent Neural PDE Solver using Flow Matchingcited by 28
  7. 2024Differentiability in Unrolled Training of Neural Physics Simulators on Transient Dynamicscited by 27
  8. 2024Text2PDE: Latent Diffusion Models for Accessible Physics Simulationcited by 25
  9. 2025Learning Distributions of Complex Fluid Simulations with Diffusion Graph Networkscited by 25
  10. 2025Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaoscited by 21
  11. 2025TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videoscited by 11
  12. 2025Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanicscited by 10
37 more
  1. 2024Parametric model reduction of mean-field and stochastic systems via higher-order action matchingcited by 9
  2. 2024Predicting Change, Not States: An Alternate Framework for Neural PDE Surrogatescited by 8
  3. 2025Edit-Based Flow Matching for Temporal Point Processescited by 8
  4. 2023PGODE: Towards High-quality System Dynamics Modelingcited by 7
  5. 2024Generative prediction of flow fields around an obstacle using the diffusion modelcited by 6
  6. 2024Generating Physical Dynamics under Priorscited by 6
  7. 2025EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scalecited by 6
  8. 2026Particle-Guided Diffusion Models for Partial Differential Equationscited by 5
  9. 2026FlowRefiner: Flow Matching-Based Iterative Refinement for 3D Turbulent Flow Simulationcited by 5
  10. 2024Unfolding Time: Generative Modeling for Turbulent Flows in 4Dcited by 4
  11. 2024DiffFluid: Plain Diffusion Models are Effective Predictors of Flow Dynamicscited by 4
  12. 2025Generative Modeling with Bayesian Sample Inferencecited by 4
  13. 2024Accelerating the discovery of steady-states of planetary interior dynamics with machine learningcited by 3
  14. 2026Adaptive Diffusion Posterior Sampling for Data and Model Fusion of Complex Nonlinear Dynamical Systemscited by 3
  15. 2025Autoregressive regularized score-based diffusion models for multi-scenarios fluid flow predictioncited by 2
  16. 2025Reframing Generative Models for Physical Systems using Stochastic Interpolantscited by 2
  17. 2026Divergence-Free Diffusion Models for Incompressible Fluid Flowscited by 2
  18. 2025Learning to generate physical ocean states: Towards hybrid climate modelingcited by 1
  19. 2025Topology Guidance: Controlling the Outputs of Generative Models via Vector Field Topologycited by 1
  20. 2025Synthetic Geology: Structural Geology Meets Deep Learningcited by 1
  21. 2025Pixel-Resolved Long-Context Learning for Turbulence at Exascale: Resolving Small-scale Eddies Toward the Viscous Limitcited by 1
  22. 2025Generating time-consistent dynamics with discriminator-guided image diffusion modelscited by 0
  23. 2025OmniFluids: Physics Pre-trained Modeling of Fluid Dynamicscited by 0
  24. 2025Discrete Bayesian Sample Inference for Graph Generationcited by 0
  25. 2025Reconstructing Multi-Scale Physical Fields from Extremely Sparse Measurements with an Autoencoder-Diffusion Cascadecited by 0
  26. 2026Bias-Constrained Diffusion Schedules for PDE Emulations: Reconstruction Error Minimization and Efficient Unrolled Trainingcited by 0
  27. 2026One Scale at a Time: Scale-Autoregressive Modeling for Fluid Flow Distributionscited by 0
  28. 2026Inpainting physics: self-supervised learning for context-driven fluid simulationcited by 0
  29. 2026DiffATS: Diffusion in Aligned Tensor Spacecited by 0
  30. 2026A fully GPU-based workflow for building physics emulators of hypersonic flowscited by 0
  31. 2026Multiscale Hypersonic Boundary Layer Reconstruction via Spectral Binning and Subdomain-wise Conditional Diffusioncited by 0
  32. 2026A Shortcut to Statistically Steady-State Turbulence with Flow Matchingcited by 0
  33. 2026Composing Flow-Matching Energies with Known Physics: Generation, OOD Detection, and Inversion on PDE Fieldscited by 0
  34. 2026FLARE: Flow Matching with Local Axis-Angle Representations for Stochastic Micromagnetic Evolutioncited by 0
  35. 2026Scale-Split Neural Operator for Memory- and Data-Efficient 3D Turbulence Predictioncited by 0
  36. 2026Primal-Dual Flow Matching for Sample-Wise Constrained Generationcited by 0
  37. 2026Learn the Dynamics, Enforce the Physics: Generative Latent Operators for High-Dimensional Beam Evolutioncited by 0