Learning to Simulate Complex Physics with Graph Networks

• URL: http://arxiv.org/abs/2002.09405v2
• Date: Mon, 14 Sep 2020 16:52:10 GMT
• Title: Learning to Simulate Complex Physics with Graph Networks
• Authors: Alvaro Sanchez-Gonzalez, Jonathan Godwin, Tobias Pfaff, Rex Ying, Jure Leskovec, Peter W. Battaglia
• Abstract summary: 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.
• Score: 68.43901833812448
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Here we present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains, involving fluids, rigid solids, and deformable materials interacting with one another. 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. Our model was robust to hyperparameter choices across various evaluation metrics: the main determinants of long-term performance were the number of message-passing steps, and mitigating the accumulation of error by corrupting the training data with noise. Our GNS framework advances the state-of-the-art in learned physical simulation, and holds promise for solving a wide range of complex forward and inverse problems.

Related papers

• Bond Graphs for multi-physics informed Neural Networks for multi-variate time series [6.775534755081169]
  Existing methods are not adapted to tasks with complex multi-physical and multi-domain phenomena. We propose a Neural Bond graph (NBgE) producing multi-physics-informed representations that can be fed into any task-specific model.
  arXiv  Detail & Related papers  (2024-05-22T12:30:25Z)
• Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs [75.7104463046767]
  This paper proposes a novel learning based simulation model that characterizes the varying spatial and temporal dependencies in particle systems. We empirically evaluate GNSTODE's simulation performance on two real-world particle systems, Gravity and Coulomb.
  arXiv  Detail & Related papers  (2023-05-21T03:51:03Z)
• Graph Neural Network-based surrogate model for granular flows [2.153852088624324]
  Granular flow dynamics is crucial for assessing various geotechnical risks, including landslides and debris flows. Traditional continuum and discrete numerical methods are limited by their computational cost in simulating large-scale systems. We develop a graph neural network-based simulator (GNS) that takes the current state of granular flow and predicts the next state using explicit integration by learning the local interaction laws.
  arXiv  Detail & Related papers  (2023-05-09T07:28:12Z)
• Learning rigid dynamics with face interaction graph networks [11.029321427540829]
  We introduce the Face Interaction Graph Network (FIGNet) which computes interactions between mesh faces, rather than nodes. FIGNet is around 4x more accurate in simulating complex shape interactions, while also 8x more computationally efficient on sparse, rigid meshes. It can learn frictional dynamics directly from real-world data, and can be more accurate than analytical solvers given modest amounts of training data.
  arXiv  Detail & Related papers  (2022-12-07T11:22:42Z)
• Transformer with Implicit Edges for Particle-based Physics Simulation [135.77656965678196]
  Transformer with Implicit Edges (TIE) captures the rich semantics of particle interactions in an edge-free manner. We evaluate our model on diverse domains of varying complexity and materials.
  arXiv  Detail & Related papers  (2022-07-22T03:45:29Z)
• Learning 3D Granular Flow Simulations [6.308272531414633]
  We present a Graph Neural Networks approach towards accurate modeling of complex 3D granular flow simulation processes created by the discrete element method LIGGGHTS. We discuss how to implement Graph Neural Networks that deal with 3D objects, boundary conditions, particle - particle, and particle - boundary interactions.
  arXiv  Detail & Related papers  (2021-05-04T17:27:59Z)
• gradSim: Differentiable simulation for system identification and visuomotor control [66.37288629125996]
  We present gradSim, a framework that overcomes the dependence on 3D supervision by leveraging differentiable multiphysics simulation and differentiable rendering. Our unified graph enables learning in challenging visuomotor control tasks, without relying on state-based (3D) supervision.
  arXiv  Detail & Related papers  (2021-04-06T16:32:01Z)
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling [86.9726984929758]
  We focus on the integration of incomplete physics models into deep generative models. We propose a VAE architecture in which a part of the latent space is grounded by physics. We demonstrate generative performance improvements over a set of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-02-25T20:28:52Z)
• Learning Mesh-Based Simulation with Graph Networks [20.29893312074383]
  We introduce MeshGraphNets, a framework for learning mesh-based simulations using graph neural networks. Our results show it can accurately predict the dynamics of a wide range of physical systems, including aerodynamics, structural mechanics, and cloth.
  arXiv  Detail & Related papers  (2020-10-07T13:34:49Z)
• Large-scale Neural Solvers for Partial Differential Equations [48.7576911714538]
  Solving partial differential equations (PDE) is an indispensable part of many branches of science as many processes can be modelled in terms of PDEs. Recent numerical solvers require manual discretization of the underlying equation as well as sophisticated, tailored code for distributed computing. We examine the applicability of continuous, mesh-free neural solvers for partial differential equations, physics-informed neural networks (PINNs) We discuss the accuracy of GatedPINN with respect to analytical solutions -- as well as state-of-the-art numerical solvers, such as spectral solvers.
  arXiv  Detail & Related papers  (2020-09-08T13:26:51Z)

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.