Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs
arXiv:2305.12334 · doi:10.1016/j.neunet.2024.106341
Abstract
The great learning ability of deep learning models facilitates us to comprehend the real physical world, making learning to simulate complicated particle systems a promising endeavour. However, the complex laws of the physical world pose significant challenges to the learning based simulations, such as the varying spatial dependencies between interacting particles and varying temporal dependencies between particle system states in different time stamps, which dominate particles' interacting behaviour and the physical systems' evolution patterns. Existing learning based simulation methods fail to fully account for the complexities, making them unable to yield satisfactory simulations. To better comprehend the complex physical laws, this paper proposes a novel learning based simulation model- Graph Networks with Spatial-Temporal neural Ordinary Equations (GNSTODE)- that characterizes the varying spatial and temporal dependencies in particle systems using a united end-to-end framework. Through training with real-world particle-particle interaction observations, GNSTODE is able to simulate any possible particle systems with high precisions. We empirically evaluate GNSTODE's simulation performance on two real-world particle systems, Gravity and Coulomb, with varying levels of spatial and temporal dependencies. The results show that the proposed GNSTODE yields significantly better simulations than state-of-the-art learning based simulation methods, which proves that GNSTODE can serve as an effective solution to particle simulations in real-world application.
arXiv comment12 pages,5 figures, 6 tables, 49 references
References in corpus (17)
- Adam: A Method for Stochastic Optimization
- A Comprehensive Survey on Graph Neural Networks
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- A Survey on Knowledge Graphs: Representation, Acquisition and Applications
- Machine Learning for Fluid Mechanics
- Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
- Hamiltonian Neural Networks
- Learning Graph Embedding with Adversarial Training Methods
- Transformers for Modeling Physical Systems
- Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
- Diffusion Improves Graph Learning
- Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids
- Orbital Graph Convolutional Neural Network for Material Property Prediction
- A Dual-Dimer Method for Training Physics-Constrained Neural Networks with Minimax Architecture
- Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
- Learning Neural Event Functions for Ordinary Differential Equations