mlsanityData to 14 Oct 2026

FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation

arXiv 2505.20349 ↗First posted 25 May 2025physics.flu-dyn cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Data-driven modeling of fluid dynamics has advanced rapidly with neural PDE solvers, yet a fair and strong benchmark remains fragmented due to the absence of unified PDE datasets and standardized evaluation protocols. Although architectural innovations are abundant, fair assessment is further impeded by the lack of clear disentanglement between spatial, temporal and loss modules. In this paper, we introduce FD-Bench, the first fair, modular, comprehensive and reproducible benchmark for data-driven fluid simulation. FD-Bench systematically evaluates 85 baseline models across 10 representative flow scenarios under a unified experimental setup. It provides four key contributions: (1) a modular design enabling fair comparisons across spatial, temporal, and loss function modules; (2) the first systematic framework for direct comparison with traditional numerical solvers; (3) fine-grained generalization analysis across resolutions, initial conditions, and temporal windows; and (4) a user-friendly, extensible codebase to support future research. Through rigorous empirical studies, FD-Bench establishes the most comprehensive leaderboard to date, resolving long-standing issues in reproducibility and comparability, and laying a foundation for robust evaluation of future data-driven fluid models. The code is open-sourced at https://github.com/WillDreamer/FD-Bench.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 88 of its 150 references that are in the map. First posted on arXiv 25 May 2025.

Builds on

88 of 150 references.

References · 88

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2022Flow Matching for Generative Modelingcited by 5,702
  4. 2018Neural Ordinary Differential Equationscited by 3,779
  5. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  6. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  7. 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
  8. 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
  9. 2022FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operatorscited by 776
  10. 2021Learning the solution operator of parametric partial differential equations with physics-informed DeepOnetscited by 540
  11. 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 527
  12. 2022Fourier Neural Operator with Learned Deformations for PDEs on General Geometriescited by 427
38 more
  1. 2022PDEBENCH: An Extensive Benchmark for Scientific Machine Learningcited by 413
  2. 2022Message Passing Neural PDE Solverscited by 386
  3. 2020Multipole Graph Neural Operator for Parametric Partial Differential Equationscited by 349
  4. 2021Choose a Transformer: Fourier or Galerkincited by 343
  5. 2023GNOT: A General Neural Operator Transformer for Operator Learningcited by 336
  6. 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 326
  7. 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEscited by 303
  8. 2021U-FNO -- An enhanced Fourier neural operator-based deep-learning model for multiphase flowcited by 297
  9. 2021Factorized Fourier Neural Operatorscited by 249
  10. 2021Multiwavelet-based Operator Learning for Differential Equationscited by 234
  11. 2022U-NO: U-shaped Neural Operatorscited by 230
  12. 2019Towards Physics-informed Deep Learning for Turbulent Flow Predictioncited by 204
  13. 2024Poseidon: Efficient Foundation Models for PDEscited by 200
  14. 2022MIONet: Learning multiple-input operators via tensor productcited by 181
  15. 2020Physics-informed learning of governing equations from scarce datacited by 167
  16. 2024DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Trainingcited by 151
  17. 2024The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learningcited by 145
  18. 2023Scalable Transformer for PDE Surrogate Modelingcited by 128
  19. 2020Incorporating Symmetry into Deep Dynamics Models for Improved Generalizationcited by 126
  20. 2024DiffusionPDE: Generative PDE-Solving Under Partial Observationcited by 108
  21. 2020Transformers for Modeling Physical Systemscited by 106
  22. 2023In-Context Operator Learning with Data Prompts for Differential Equation Problemscited by 101
  23. 2022MultiScale MeshGraphNetscited by 98
  24. 2022Approximately Equivariant Networks for Imperfectly Symmetric Dynamicscited by 97
  25. 2022Clifford Neural Layers for PDE Modelingcited by 92
  26. 2024Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equationscited by 91
  27. 2024Physics-Informed Diffusion Modelscited by 90
  28. 2023Solving High-Dimensional PDEs with Latent Spectral Modelscited by 89
  29. 2023PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEscited by 87
  30. 2022Neural-Fly Enables Rapid Learning for Agile Flight in Strong Windscited by 85
  31. 2022Predicting Physics in Mesh-reduced Space with Temporal Attentioncited by 84
  32. 2022NOMAD: Nonlinear Manifold Decoders for Operator Learningcited by 83
  33. 2022Continuous PDE Dynamics Forecasting with Implicit Neural Representationscited by 73
  34. 2023Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulationcited by 71
  35. 2025InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciencescited by 68
  36. 2023PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networkscited by 64
  37. 2020Learning Continuous System Dynamics from Irregularly-Sampled Partial Observationscited by 61
  38. 2021Encoding physics to learn reaction-diffusion processescited by 61

50 most cited of 88 All 88 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Generalized Neural Operator for Parametric and Boundary-Value Problemscited by 1
  2. 2026Derived Fields Preserve Fine-Scale Detail in Budgeted Neural Simulatorscited by 0
  3. 2026Open datasets and machine learning for two-phase heat transfer: a review following a spatial-temporal taxonomycited by 0
  4. 2026Hybrid Lagrangian-Eulerian Model for Lagrangian Fluid Simulationcited by 0
  5. 2026AutoPDEBench: Benchmarking LLM Auto-Research for Neural PDE Solver Designcited by 0