Lune

ICLR2024Top-tier venue

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

Marten Lienen, David Lüdke, Jan Hansen-Palmus, Stephan Günnemann

Abstract

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

22 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Add and Thin: Diffusion for Temporal Point Processes cites Improved Denoising Diffusion Probabilistic Models
  • Add and Thin: Diffusion for Temporal Point Processes cites Denoising Diffusion Probabilistic Models
  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Implicit Models
  • Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes cites Denoising Diffusion Probabilistic Models
  • Improved Denoising Diffusion Probabilistic Models cites Denoising Diffusion Probabilistic Models
  • Improved Denoising Diffusion Probabilistic Models cites Denoising Diffusion Implicit Models
  • DiffusionPDE: Generative PDE-Solving under Partial Observation cites Denoising Diffusion Probabilistic Models
  • DiffusionPDE: Generative PDE-Solving under Partial Observation cites Denoising Diffusion Implicit Models
  • Physics-Informed Diffusion Models cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Physics-Informed Diffusion Models cites Denoising Diffusion Probabilistic Models
  • Physics-Informed Diffusion Models cites Denoising Diffusion Implicit Models
  • Denoising Diffusion Implicit Models cites Denoising Diffusion Probabilistic Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers22

  1. Physics-Informed Diffusion ModelsJan-Hendrik Bastek, WaiChing Sun, Dennis M. KochmannICLR 2025 · 165 citations
  2. DiffusionPDE: Generative PDE-Solving under Partial ObservationJiahe Huang, Guandao Yang, Zichen Wang, Jeong Joon ParkNeurIPS 2024 · 148 citations
  3. Probabilistic Forecasting with Stochastic Interpolants and Föllmer ProcessesYifan Chen, Mark Goldstein, Mengjian Hua, Michael S. Albergo et al.ICML 2024 · 53 citations
  4. Add and Thin: Diffusion for Temporal Point ProcessesDavid Lüdke, Marin Bilos, Oleksandr Shchur, Marten Lienen et al.NeurIPS 2023 · 34 citations
  5. Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODEHao Wu, Huiyuan Wang, Kun Wang, Weiyan Wang et al.ICML 2024 · 25 citations

Builds on23

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  2. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  3. Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
  4. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessTri Dao, Daniel Y. Fu, Stefano Ermon, Atri Rudra et al.NeurIPS 2022 · 5,493 citations
  5. Improved Denoising Diffusion Probabilistic ModelsAlexander Quinn Nichol, Prafulla DhariwalICML 2021 · 5,234 citations

Related papers

  1. P3D: Highly Scalable 3D Neural Surrogates for Physics Simulations with Global ContextBenjamin Holzschuh, Georg Kohl, Florian Redinger, Nils ThuereyICLR 2026 · 4 citations
  2. Learning Incompressible Fluid Dynamics from Scratch - Towards Fast, Differentiable Fluid Models that GeneralizeNils Wandel, Michael Weinmann, Reinhard KleinICLR 2021 · 82 citations
  3. Self-Guided Diffusion Model for Accelerating Computational Fluid DynamicsRuoyan Li, Zijie Huang, Haixin Wang, Guancheng Wan et al.KDD 2026
  4. SurfsUp: Learning Fluid Simulation for Novel SurfacesArjun Mani, Ishaan Preetam Chandratreya, Elliot Creager, Carl Vondrick et al.ICCV 2023 · 6 citations
  5. SurroFlow: A Flow-Based Surrogate Model for Parameter Space Exploration and Uncertainty QuantificationJingyi Shen, Yuhan Duan, Han-Wei ShenIEEE VIS 2024 · 6 citations
Dusk over the sea between two cliffs drawn in fine vertical lines