Learning Effective Dynamics across Spatio-Temporal Scales of Complex Flows
Not on the map. Why?
Abstract (arXiv)
Modeling and simulation of complex fluid flows with dynamics that span multiple spatio-temporal scales is a fundamental challenge in many scientific and engineering domains. Full-scale resolving simulations for systems such as highly turbulent flows are not feasible in the foreseeable future, and reduced-order models must capture dynamics that involve interactions across scales. In the present work, we propose a novel framework, Graph-based Learning of Effective Dynamics (Graph-LED), that leverages graph neural networks (GNNs), as well as an attention-based autoregressive model, to extract the effective dynamics from a small amount of simulation data. GNNs represent flow fields on unstructured meshes as graphs and effectively handle complex geometries and non-uniform grids. The proposed method combines a GNN based, dimensionality reduction for variable-size unstructured meshes with an autoregressive temporal attention model that can learn temporal dependencies automatically. We evaluated the proposed approach on a suite of fluid dynamics problems, including flow past a cylinder and flow over a backward-facing step over a range of Reynolds numbers. The results demonstrate robust and effective forecasting of spatio-temporal physics; in the case of the flow past a cylinder, both small-scale effects that occur close to the cylinder as well as its wake are accurately captured.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 28 of its 55 references that are in the map. First posted on arXiv 11 Feb 2025.
Builds on
28 of 55 references.
References · 28
- 2017Attention Is All You Needcited by 60,361
- 2016Layer Normalizationcited by 5,669
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
- 2020Learning Mesh-Based Simulation with Graph Networkscited by 868
- 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 494
- 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 310
- 2018Graph networks as learnable physics engines for inference and controlcited by 244
- 2016Professor Forcing: A New Algorithm for Training Recurrent Networkscited by 216
- 2018Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networkscited by 155
- 2019Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networkscited by 129
16 more
- 2020Transformers for Modeling Physical Systemscited by 106
- 2021PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEscited by 98
- 2021Learned Coarse Models for Efficient Turbulence Simulationcited by 91
- 2020Multiscale Simulations of Complex Systems by Learning their Effective Dynamicscited by 86
- 2021POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decompositioncited by 79
- 2019Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamicscited by 45
- 2019Graph Element Networks: adaptive, structured computation and memorycited by 41
- 2022Physical Design using Differentiable Learned Simulatorscited by 37
- 2020Deep Neural Networks for Nonlinear Model Order Reduction of Unsteady Flowscited by 36
- 2020Multi-fidelity Generative Deep Learning Turbulent Flowscited by 21
- 2021Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systemscited by 17
- 2020Eigen-GNN: A Graph Structure Preserving Plug-in for GNNscited by 14
- 2023Interpretable A-posteriori Error Indication for Graph Neural Network Surrogate Modelscited by 6
- 2023Nonlinear embeddings for conserving Hamiltonians and other quantities with Neural Galerkin schemescited by 3
- 2024GNUMAP: A Parameter-Free Approach to Unsupervised Dimensionality Reduction via Graph Neural Networkscited by 2
- 2024Scalable and Consistent Graph Neural Networks for Distributed Mesh-based Data-driven Modelingcited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.