Preprint
Aug 2026
Physics-Constrained Neural Flow Maps for Long-Horizon Prediction of Spin Dynamics
A physics-constrained neural flow map that learns finite-time dynamics directly on the unit sphere that outperforms an adapted Long Short-Term Memory in in-domain accuracy and geometric stability and enables physically admissible long-horizon prediction.
Haoen Feng, Sheng-Lan Yuan, Shi-Rong Lin
· 0 citations