mlsanityData to 7 Oct 2026

Mixing Artificial and Natural Intelligence: From Statistical Mechanics to AI and Back to Turbulence

arXiv 2403.17993 ↗First posted 26 Mar 2024cs.LG cond-mat.stat-mech cs.AIcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

The paper reflects on the future role of AI in scientific research, with a special focus on turbulence studies, and examines the evolution of AI, particularly through Diffusion Models rooted in non-equilibrium statistical mechanics. It underscores the significant impact of AI on advancing reduced, Lagrangian models of turbulence through innovative use of deep neural networks. Additionally, the paper reviews various other AI applications in turbulence research and outlines potential challenges and opportunities in the concurrent advancement of AI and statistical hydrodynamics. This discussion sets the stage for a future where AI and turbulence research are intricately intertwined, leading to more profound insights and advancements in both fields.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 52 of its 163 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

52 of 163 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Synthetic Lagrangian Turbulence by Generative Diffusion Models17 Jul

Other references · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2018Neural Ordinary Differential Equationscited by 3,733
  8. 2015Automatic differentiation in machine learning: a surveycited by 846
  9. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 491
  10. 2017Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equationscited by 362
  11. 2023A mathematical perspective on Transformerscited by 160
  12. 2017Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equationscited by 158
38 more
  1. 2023The emergence of clusters in self-attention dynamicscited by 133
  2. 2024Dynamical Regimes of Diffusion Modelscited by 133
  3. 2019Theoretical guarantees for sampling and inference in generative models with latent diffusionscited by 97
  4. 2023β-Variational autoencoders and transformers for reduced-order modelling of fluid flowscited by 76
  5. 2023Non-Denoising Forward-Time Diffusionscited by 75
  6. 2021Simulation Intelligence: Towards a New Generation of Scientific Methodscited by 68
  7. 2019A review on Deep Reinforcement Learning for Fluid Mechanicscited by 65
  8. 2022Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamicscited by 30
  9. 2016Optimal structure and parameter learning of Ising modelscited by 26
  10. 2021Learning Efficient Navigation in Vortical Flow Fieldscited by 26
  11. 2020A reinforcement learning approach to rare trajectory samplingcited by 21
  12. 2021Physics-Informed Graphical Neural Network for Parameter & State Estimations in Power Systemscited by 21
  13. 2023Identifying regions of importance in wall-bounded turbulence through explainable deep learningcited by 15
  14. 2023Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Modelscited by 15
  15. 2018From Deep to Physics-Informed Learning of Turbulence: Diagnosticscited by 14
  16. 2019Machine learning strategies for path-planning microswimmers in turbulent flowscited by 13
  17. 2024A non-intrusive machine learning framework for debiasing long-time coarse resolution climate simulations and quantifying rare events statisticscited by 9
  18. 2021Reinforcement learning for pursuit and evasion of microswimmers at low Reynolds numbercited by 7
  19. 2021Embedding Power Flow into Machine Learning for Parameter and State Estimationcited by 6
  20. 2017Online Learning of Power Transmission Dynamicscited by 5
  21. 2021Neural Particle Image Velocimetrycited by 4
  22. 2023A Physics-Informed Machine Learning for Electricity Markets: A NYISO Case Studycited by 4
  23. 2023Adaptive learning of effective dynamics: Adaptive real-time, online modeling for complex systemscited by 4
  24. 2024Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanicscited by 4
  25. 2017Ensemble Control of Cycling Energy Loads: Markov Decision Approachcited by 3
  26. 2018Gauges, Loops, and Polynomials for Partition Functions of Graphical Modelscited by 3
  27. 2019Learning a Generator Model from Terminal Bus Datacited by 3
  28. 2018Mean Field Control for Efficient Mixing of Energy Loadscited by 2
  29. 2021Prediction and Prevention of Pandemics via Graphical Model Inference and Convex Programmingcited by 2
  30. 2022Statistical Mechanics of Thermostatically Controlled Multi-Zone Buildingscited by 2
  31. 2023Universality and Control of Fat Tailscited by 2
  32. 2023An energy-based model approach to rare event probability estimationcited by 2
  33. 2023Extreme Event Prediction with Multi-agent Reinforcement Learning-based Parametrization of Atmospheric and Oceanic Turbulencecited by 2
  34. 2014Cascading of Fluctuations in Interdependent Energy Infrastructures: Gas-Grid Couplingcited by 1
  35. 2017Thermal Transients in District Heating Systemscited by 1
  36. 2021Which Neural Network to Choose for Post-Fault Localization, Dynamic State Estimation and Optimal Measurement Placement in Power Systems?cited by 1
  37. 2021Physics informed machine learning with Smoothed Particle Hydrodynamics: Hierarchy of reduced Lagrangian models of turbulencecited by 1
  38. 2021Towards Model Reduction for Power System Transients with Physics-Informed PDEcited by 1

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Generative AI for fast and accurate statistical computation of fluids
  2. 2025Autoregressive regularized score-based diffusion models for multi-scenarios fluid flow prediction
  3. 2023Turbulence Scaling from Deep Learning Diffusion Generative Models
  4. 2025Physics-aware generative models for turbulent fluid flows through energy-consistent stochastic interpolants
  5. 2023Thermodynamic AI and the fluctuation frontier
  6. 2023Diffusion Models for Generative Artificial Intelligence: An Introduction for Applied Mathematicians
  7. 2023Diffusion model based data generation for partial differential equations
  8. 2024Integrating Neural Operators with Diffusion Models Improves Spectral Representation in Turbulence Modeling