Discovering conservation laws from trajectories via machine learning
arXiv:2102.04008
Abstract
Invariants and conservation laws convey critical information about the underlying dynamics of a system, yet it is generally infeasible to find them from large-scale data without any prior knowledge or human insight. We propose ConservNet to achieve this goal, a neural network that spontaneously discovers a conserved quantity from grouped data where the members of each group share invariants, similar to a general experimental setting where trajectories from different trials are observed. As a neural network trained with a novel and intuitive loss function called noise-variance loss, ConservNet learns the hidden invariants in each group of multi-dimensional observables in a data-driven, end-to-end manner. Our model successfully discovers underlying invariants from the simulated systems having invariants as well as a real-world double pendulum trajectory. Since the model is robust to various noises and data conditions compared to baseline, our approach is directly applicable to experimental data for discovering hidden conservation laws and further, general relationships between variables.
arXiv comment12 pages, 9 figures
References in corpus (16)
- Machine learning phases of matter
- Searching for Exotic Particles in High-Energy Physics with Deep Learning
- Data-driven discovery of coordinates and governing equations
- Many-body quantum state tomography with neural networks
- Learning phase transitions by confusion
- Quantum Loop Topography for Machine Learning
- Machine Learning Topological Invariants with Neural Networks
- Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
- Data-driven quantitative modeling of bacterial active nematics
- Kernel methods for interpretable machine learning of order parameters
- AI Poincaré: Machine Learning Conservation Laws from Trajectories
- Toward an AI Physicist for Unsupervised Learning
- Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
- Deep Learning Topological Invariants of Band Insulators
- Neural network interpretation using descrambler groups
- Learning a Local Symmetry with Neural-Networks