Photo of Charlotte Myers

Charlotte Myers

Undergraduate · 2024 – 2026 · with Prof. Lina Necib (MIT)

2026 Goldwater Scholar

See their path on the collaborator map →

Papers & software together

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

Orbits of a test particle in a Milky Way–LMC system, integrated in the true potential, a near-true analytic model, and three neural-network models. The most complete neural-network models track the true orbit almost exactly, while the near-true analytic model drifts away from it.

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, so it stays interpretable while reaching sub-percent acceleration errors and more faithful orbits than analytic models alone.

A physics-informed neural network learns only the corrections to an analytic galactic potential, so it stays interpretable while reaching sub-percent acceleration errors and more faithful orbits than analytic models alone. Bayesian and time-dependent extensions add uncertainties and follow the potential as it evolves. Led by undergraduate Charlotte Myers; code in galactoPINNs, first shown at NeurIPS 2025.

student† 1st | 2nd | 2026
2026Context ›

galactoPINNs

Orbits of a test particle in a Milky Way–LMC system, integrated in the true potential, a near-true analytic model, and three neural-network models. The most complete neural-network models track the true orbit almost exactly, while the near-true analytic model drifts away from it.

Physics-informed neural networks for galactic potentials

Physics-informed neural networks for galactic potentials

Achievements