Reconstructing Galactic Gravitational Potentials from Stellar Kinematics with Physics-Informed Neural NetworksPINNs for Galactic PotentialsGalactic PINNssubmitted

The Astrophysical JournalApJ·2026submitted·C. Myers†, N. Starkman, et al.C. Myers†, N. Starkman, L. NecibC. Myers†, N. Starkman, L. Necib·The Astrophysical JournalApJ·2026submitted
The Astrophysical JournalApJ·2026submitted
A physics-informed neural network learns only the corrections to an analytic galactic potential, reaching sub-percent acceleration errors while staying interpretable.
A physics-informed neural network learns only the corrections to an analytic galactic potential, reaching sub-percent acceleration errors while staying interpretable. Its orbits are more faithful than the analytic model’s alone, and Bayesian and time-dependent versions add uncertainties and follow a potential as it changes. Led by undergraduate Charlotte Myers; code in galactoPINNs, first shown at NeurIPS 2025.
