mlsanityData to 7 Oct 2026

Generative Learning for Forecasting the Dynamics of Complex Systems

arXiv 2402.17157 ↗First posted 27 Feb 2024cs.LG physics.comp-ph physics.flu-dyncited by 6

Not on the map. Why?

Abstract (arXiv)

We introduce generative models for accelerating simulations of complex systems through learning and evolving their effective dynamics. In the proposed Generative Learning of Effective Dynamics (G-LED), instances of high dimensional data are down sampled to a lower dimensional manifold that is evolved through an auto-regressive attention mechanism. In turn, Bayesian diffusion models, that map this low-dimensional manifold onto its corresponding high-dimensional space, capture the statistics of the system dynamics. We demonstrate the capabilities and drawbacks of G-LED in simulations of several benchmark systems, including the Kuramoto-Sivashinsky (KS) equation, two-dimensional high Reynolds number flow over a backward-facing step, and simulations of three-dimensional turbulent channel flow. The results demonstrate that generative learning offers new frontiers for the accurate forecasting of the statistical properties of complex systems at a reduced computational cost.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 45 of its 80 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

45 of 80 references.

References · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2013Auto-Encoding Variational Bayescited by 3,980
  8. 2023Mistral 7Bcited by 3,065
  9. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  10. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
  11. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  12. 2021Variational Diffusion Modelscited by 1,145
33 more
  1. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  2. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  3. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  4. 2022Fourier Neural Operator with Learned Deformations for PDEs on General Geometriescited by 416
  5. 2023GenCast: Diffusion-based ensemble forecasting for medium-range weathercited by 169
  6. 2018Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networkscited by 155
  7. 2022A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstructioncited by 150
  8. 2019Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networkscited by 127
  9. 2020Transformers for Modeling Physical Systemscited by 105
  10. 2023DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecastingcited by 105
  11. 2021PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEscited by 97
  12. 2020Multiscale Simulations of Complex Systems by Learning their Effective Dynamicscited by 86
  13. 2022Predicting Physics in Mesh-reduced Space with Temporal Attentioncited by 82
  14. 2023CoCoGen: Physically-Consistent and Conditioned Score-based Generative Models for Forward and Inverse Problemscited by 54
  15. 2020Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structurescited by 52
  16. 2022Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systemscited by 50
  17. 2022Learning to correct spectral methods for simulating turbulent flowscited by 49
  18. 2019Deep learning to discover and predict dynamics on an inertial manifoldcited by 42
  19. 2022Neural Implicit Flow: a mesh-agnostic dimensionality reduction paradigm of spatio-temporal datacited by 37
  20. 2023Bayesian Conditional Diffusion Models for Versatile Spatiotemporal Turbulence Generationcited by 28
  21. 2023Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedbackcited by 27
  22. 2023SEEDS: Emulation of Weather Forecast Ensembles with Diffusion Modelscited by 26
  23. 2019Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systemscited by 25
  24. 2022Semi-supervised Invertible Neural Operators for Bayesian Inverse Problemscited by 25
  25. 2020Multi-fidelity Generative Deep Learning Turbulent Flowscited by 21
  26. 2023Differentiable hybrid neural modeling for fluid-structure interactioncited by 18
  27. 2021Physics-aware, probabilistic model order reduction with guaranteed stabilitycited by 12
  28. 2023Mori-Zwanzig latent space Koopman closure for nonlinear autoencodercited by 12
  29. 2023Interpretable learning of effective dynamics for multiscale systemscited by 11
  30. 2023Inexpensive High Fidelity Melt Pool Models in Additive Manufacturing Using Generative Deep Diffusioncited by 11
  31. 2020Learning Similarity Metrics for Numerical Simulationscited by 9
  32. 2022Modelling spatiotemporal turbulent dynamics with the convolutional autoencoder echo state networkcited by 4
  33. 2023Interpretable reduced-order modeling with time-scale separationcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 5.

6 papers.

  1. 2024Data-Driven Stochastic Closure Modeling via Conditional Diffusion Model and Neural Operatorcited by 12
  2. 2025Generative emulation of chaotic dynamics with coherent priorcited by 7
  3. 2025Rectified Flows for Fast Multiscale Fluid Flow Modelingcited by 4
  4. 2025Generative forecasting with joint probability modelscited by 2
  5. 2025Efficient probabilistic surrogate modeling techniques for partially-observed large-scale dynamical systemscited by 1
  6. 2025Enabling Probabilistic Learning on Manifolds through Double Diffusion Mapscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Generative Learning of the Solution of Parametric Partial Differential Equations Using Guided Diffusion Models and Virtual Observations
  2. 2025Physics-aware generative models for turbulent fluid flows through energy-consistent stochastic interpolants
  3. 2026StocBench: A Benchmark for Generative Modeling of Stochastic Dynamics
  4. 2026Generative Modeling of Stochastic Dynamics for Long-Time Evolution
  5. 2025Fast and Flexible Probabilistic Forecasting of Dynamical Systems using Flow Matching and Physical Perturbation
  6. 2024Response Theory via Generative Score Modeling
  7. 2024Generative AI for fast and accurate statistical computation of fluids
  8. 2024GUD: Generation with Unified Diffusion