Eagle: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformers

• URL: http://arxiv.org/abs/2302.10803v1
• Date: Thu, 16 Feb 2023 12:59:08 GMT
• Title: Eagle: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformers
• Authors: Steeven Janny, Aur\'elien B\'eneteau, Nicolas Thome, Madiha Nadri, Julie Digne, Christian Wolf
• Abstract summary: Estimating fluid dynamics is a notoriously hard problem to solve. We introduce a new model, method and benchmark for the problem. We show that our transformer outperforms state-of-the-art performance on, both, existing synthetic and real datasets.
• Score: 23.589419066824306
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Estimating fluid dynamics is classically done through the simulation and integration of numerical models solving the Navier-Stokes equations, which is computationally complex and time-consuming even on high-end hardware. This is a notoriously hard problem to solve, which has recently been addressed with machine learning, in particular graph neural networks (GNN) and variants trained and evaluated on datasets of static objects in static scenes with fixed geometry. We attempt to go beyond existing work in complexity and introduce a new model, method and benchmark. We propose EAGLE, a large-scale dataset of 1.1 million 2D meshes resulting from simulations of unsteady fluid dynamics caused by a moving flow source interacting with nonlinear scene structure, comprised of 600 different scenes of three different types. To perform future forecasting of pressure and velocity on the challenging EAGLE dataset, we introduce a new mesh transformer. It leverages node clustering, graph pooling and global attention to learn long-range dependencies between spatially distant data points without needing a large number of iterations, as existing GNN methods do. We show that our transformer outperforms state-of-the-art performance on, both, existing synthetic and real datasets and on EAGLE. Finally, we highlight that our approach learns to attend to airflow, integrating complex information in a single iteration.

Related papers

• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion [118.74385965694694]
  We present Motion DUSt3R (MonST3R), a novel geometry-first approach that directly estimates per-timestep geometry from dynamic scenes. By simply estimating a pointmap for each timestep, we can effectively adapt DUST3R's representation, previously only used for static scenes, to dynamic scenes. We show that by posing the problem as a fine-tuning task, identifying several suitable datasets, and strategically training the model on this limited data, we can surprisingly enable the model to handle dynamics.
  arXiv  Detail & Related papers  (2024-10-04T18:00:07Z)
• FlowBench: A Large Scale Benchmark for Flow Simulation over Complex Geometries [19.15738125919099]
  FlowBench is a dataset for neural simulators with over 10K samples. FlowBench will enable evaluating the interplay between complex geometry, coupled flow phenomena, and data sufficiency on the performance of neural PDE solvers.
  arXiv  Detail & Related papers  (2024-09-26T16:38:48Z)
• TorchDA: A Python package for performing data assimilation with deep learning forward and transformation functions [7.11946037942663]
  This study presents a novel Python package combining data assimilation with deep neural networks to serve as models for state transition and observation functions. Comprehensive experiments conducted on the Lorenz 63 and a two-dimensional shallow water system demonstrate significantly enhanced performance over standalone model predictions without assimilation. Overall, this innovative software package enables flexible integration of deep learning representations within data assimilation, conferring a versatile tool to tackle complex high dimensional dynamical systems across scientific domains.
  arXiv  Detail & Related papers  (2024-08-30T20:30:34Z)
• Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer [19.042551780033765]
  We present Hierarchical Contact Mesh Transformer (HCMT), which uses hierarchical mesh structures and can learn long-range dependencies. HCMT enables long-range interactions, and the hierarchical mesh structure quickly propagates collision effects to faraway positions. Our results show that HCMT provides significant performance improvements over existing methods.
  arXiv  Detail & Related papers  (2023-12-19T05:30:08Z)
• Generalizable data-driven turbulence closure modeling on unstructured grids with differentiable physics [1.8749305679160366]
  We introduce a framework for embedding deep learning models within a generic finite element solver to solve the Navier-Stokes equations. We validate our method for flow over a backwards-facing step and test its performance on novel geometries. We show that our GNN-based closure model may be learned in a data-limited scenario by interpreting closure modeling as a solver-constrained optimization.
  arXiv  Detail & Related papers  (2023-07-25T14:27:49Z)
• Machine Learning model for gas-liquid interface reconstruction in CFD numerical simulations [59.84561168501493]
  The volume of fluid (VoF) method is widely used in multi-phase flow simulations to track and locate the interface between two immiscible fluids. A major bottleneck of the VoF method is the interface reconstruction step due to its high computational cost and low accuracy on unstructured grids. We propose a machine learning enhanced VoF method based on Graph Neural Networks (GNN) to accelerate the interface reconstruction on general unstructured meshes.
  arXiv  Detail & Related papers  (2022-07-12T17:07:46Z)
• Benchmarking of Deep Learning models on 2D Laminar Flow behind Cylinder [0.0]
  Direct Numerical Simulation(DNS) is one of the tasks in Computational Fluid Dynamics. We train these three models in an autoencoder manner, for this the dataset is treated like sequential frames given to the model as input. We observe that recently introduced architecture called Transformer significantly outperforms its counterparts on the selected dataset.
  arXiv  Detail & Related papers  (2022-05-26T16:49:09Z)
• Equivariant vector field network for many-body system modeling [65.22203086172019]
  Equivariant Vector Field Network (EVFN) is built on a novel equivariant basis and the associated scalarization and vectorization layers. We evaluate our method on predicting trajectories of simulated Newton mechanics systems with both full and partially observed data.
  arXiv  Detail & Related papers  (2021-10-26T14:26:25Z)
• Using Data Assimilation to Train a Hybrid Forecast System that Combines Machine-Learning and Knowledge-Based Components [52.77024349608834]
  We consider the problem of data-assisted forecasting of chaotic dynamical systems when the available data is noisy partial measurements. We show that by using partial measurements of the state of the dynamical system, we can train a machine learning model to improve predictions made by an imperfect knowledge-based model.
  arXiv  Detail & Related papers  (2021-02-15T19:56:48Z)
• Learning to Simulate Complex Physics with Graph Networks [68.43901833812448]
  We present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains. Our framework---which we term "Graph Network-based Simulators" (GNS)--represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing. Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions, thousands of timesteps, and at least an order of magnitude more particles at test time.
  arXiv  Detail & Related papers  (2020-02-21T16:44:28Z)
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
  We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
  arXiv  Detail & Related papers  (2020-02-21T05:00:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.