LGCOMP-PHFLU-DYNFeb 11, 2025

Learning Effective Dynamics across Spatio-Temporal Scales of Complex Flows

arXiv:2502.07990v12 citationsh-index: 5CPAL
Originality Highly original
AI Analysis

This addresses the problem of simulating turbulent flows for scientific and engineering domains, offering a novel method for reduced-order modeling.

The paper tackles the challenge of modeling complex fluid flows with multi-scale dynamics by proposing Graph-LED, a framework using graph neural networks and attention-based autoregressive models to extract effective dynamics from limited simulation data, achieving robust forecasting in fluid dynamics problems like flow past a cylinder.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes