Physics-Informed Neural Networks for Modeling Galactic Gravitational Potentials
Abstract
We introduce a physics-informed neural framework for modeling static and time-dependent galactic gravitational potentials. The method combines data-driven learning with embedded physical constraints to capture complex, small-scale features while preserving global physical consistency. We quantify predictive uncertainty through a Bayesian framework, and model time evolution using a neural ODE approach. Applied to mock systems of varying complexity, the model achieves reconstruction errors at the sub-percent level ( mean acceleration error) and improves dynamical consistency compared to analytic baselines. This method complements existing analytic methods, enabling physics-informed baseline potentials to be combined with neural residual fields to achieve both interpretable and accurate potential models.
Cite
@article{arxiv.2602.01806,
title = {Physics-Informed Neural Networks for Modeling Galactic Gravitational Potentials},
author = {Charlotte Myers and Nathaniel Starkman and Lina Necib},
journal= {arXiv preprint arXiv:2602.01806},
year = {2026}
}
Comments
7 pages, 4 figures