Physics-Informed Neural Networks as Solvers for the Time-Dependent Schrödinger Equation

Download PDF

Karan Shah, Patrick Stiller, Nico Hoffmann, Attila Cangi

Published: 01 Dec 2022, Last Modified: 01 Oct 2024Machine Learning for Physical Science Workshop, NeurIPS 2022EveryoneCC BY 4.0
Abstract: We demonstrate the utility of physics-informed neural networks (PINNs) as solvers for the non-relativistic, time-dependent Schrödinger equation. We study the performance and generalisability of PINN solvers on the time evolution of a quantum harmonic oscillator across varying system parameters, domains, and energy states.