Rediscovering orbital mechanics with machine learning

• URL: http://arxiv.org/abs/2202.02306v1
• Date: Fri, 4 Feb 2022 18:44:21 GMT
• Title: Rediscovering orbital mechanics with machine learning
• Authors: Pablo Lemos, Niall Jeffrey, Miles Cranmer, Shirley Ho, Peter Battaglia
• Abstract summary: We train a "graph neural network" to simulate the dynamics of our solar system's Sun, planets, and large moons from 30 years of trajectory data. We then use symbolic regression to discover an analytical expression for the force law implicitly learned by the neural network.
• Score: 1.2999518604217852
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present an approach for using machine learning to automatically discover the governing equations and hidden properties of real physical systems from observations. We train a "graph neural network" to simulate the dynamics of our solar system's Sun, planets, and large moons from 30 years of trajectory data. We then use symbolic regression to discover an analytical expression for the force law implicitly learned by the neural network, which our results showed is equivalent to Newton's law of gravitation. The key assumptions that were required were translational and rotational equivariance, and Newton's second and third laws of motion. Our approach correctly discovered the form of the symbolic force law. Furthermore, our approach did not require any assumptions about the masses of planets and moons or physical constants. They, too, were accurately inferred through our methods. Though, of course, the classical law of gravitation has been known since Isaac Newton, our result serves as a validation that our method can discover unknown laws and hidden properties from observed data. More broadly this work represents a key step toward realizing the potential of machine learning for accelerating scientific discovery.

Related papers

• On Newton's Method to Unlearn Neural Networks [44.85793893441989]
  We seek approximate unlearning algorithms for neural networks (NNs) that return identical models to the retrained oracle. We propose CureNewton's method, a principle approach that leverages cubic regularization to handle the Hessian degeneracy effectively. Experiments across different models and datasets show that our method can achieve competitive unlearning performance to the state-of-the-art algorithm in practical unlearning settings.
  arXiv  Detail & Related papers  (2024-06-20T17:12:20Z)
• Quantum Sensing from Gravity as Universal Dephasing Channel for Qubits [41.96816488439435]
  WeExploit the generic phenomena of the gravitational redshift and Aharonov-Bohm phase. We show that entangled quantum states dephase with a universal rate. We propose qubit-based platforms as quantum sensors for precision gravitometers and mechanical strain gauges.
  arXiv  Detail & Related papers  (2024-06-05T13:36:06Z)
• Newton's laws of motion can generate gravity-mediated entanglement [0.0]
  Two masses in an initial superposition of spatially localized states are allowed to interact only through gravity. We show that one can generate the same amount of entanglement in this setup by using classical time evolution given by Newton's laws of motion.
  arXiv  Detail & Related papers  (2024-01-15T16:57:15Z)
• Loss Dynamics of Temporal Difference Reinforcement Learning [36.772501199987076]
  We study the case learning curves for temporal difference learning of a value function with linear function approximators. We study how learning dynamics and plateaus depend on feature structure, learning rate, discount factor, and reward function.
  arXiv  Detail & Related papers  (2023-07-10T18:17:50Z)
• Exact conservation laws for neural network integrators of dynamical systems [0.0]
  We present an approach which uses Noether's Theorem to inherently incorporate conservation laws into the architecture of the neural network. We demonstrate this leads to better predictions for three model systems.
  arXiv  Detail & Related papers  (2022-09-23T15:45:05Z)
• Reconstruction of observed mechanical motions with Artificial Intelligence tools [0.0]
  The laws are represented by neural networks with a limited number of parameters. We reconstruct both integrable and chaotic motions, as we demonstrate in the example of the gravity pendulum and the double pendulum.
  arXiv  Detail & Related papers  (2022-02-23T11:52:08Z)
• Machine Learning for Discovering Effective Interaction Kernels between Celestial Bodies from Ephemerides [10.77689830299308]
  We use a data-driven learning approach to derive a stable and accurate model for the motion of celestial bodies in our Solar System. By modeling the major astronomical bodies in the Solar System as pairwise interacting agents, our learned model generate extremely accurate dynamics. Our model can provide a unified explanation to the observation data, especially in terms of reproducing the perihelion precession of Mars, Mercury, and the Moon.
  arXiv  Detail & Related papers  (2021-08-26T16:30:59Z)
• The problem of engines in statistical physics [62.997667081978825]
  Engines are open systems that can generate work cyclically, at the expense of an external disequilibrium. Recent advances in the theory of open quantum systems point to a more realistic description of autonomous engines. We show how the external loading force and the thermal noise may be incorporated into the relevant equations of motion.
  arXiv  Detail & Related papers  (2021-08-17T03:59:09Z)
• Machine-Learning Non-Conservative Dynamics for New-Physics Detection [69.45430691069974]
  Given a trajectory governed by unknown forces, our Neural New-Physics Detector (NNPhD) aims to detect new physics. We demonstrate that NNPhD successfully discovers new physics by decomposing the force field into conservative and non-conservative components. We also show how NNPhD coupled with an integrator outperforms previous methods for predicting the future of a damped double pendulum.
  arXiv  Detail & Related papers  (2021-05-31T18:00:10Z)
• AI Poincar\'e: Machine Learning Conservation Laws from Trajectories [0.0]
  We present AI Poincar'e, a machine learning algorithm for auto-discovering conserved quantities. We test it on five Hamiltonian systems, including the gravitational 3-body problem.
  arXiv  Detail & Related papers  (2020-11-09T19:23:28Z)
• Parsimonious neural networks learn interpretable physical laws [77.34726150561087]
  We propose parsimonious neural networks (PNNs) that combine neural networks with evolutionary optimization to find models that balance accuracy with parsimony. The power and versatility of the approach is demonstrated by developing models for classical mechanics and to predict the melting temperature of materials from fundamental properties.
  arXiv  Detail & Related papers  (2020-05-08T16:15:47Z)

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.