English

First principles physics-informed neural network for quantum wavefunctions and eigenvalue surfaces

Machine Learning 2022-11-22 v3 Materials Science Computational Physics

Abstract

Physics-informed neural networks have been widely applied to learn general parametric solutions of differential equations. Here, we propose a neural network to discover parametric eigenvalue and eigenfunction surfaces of quantum systems. We apply our method to solve the hydrogen molecular ion. This is an ab-initio deep learning method that solves the Schrodinger equation with the Coulomb potential yielding realistic wavefunctions that include a cusp at the ion positions. The neural solutions are continuous and differentiable functions of the interatomic distance and their derivatives are analytically calculated by applying automatic differentiation. Such a parametric and analytical form of the solutions is useful for further calculations such as the determination of force fields.

Keywords

Cite

@article{arxiv.2211.04607,
  title  = {First principles physics-informed neural network for quantum wavefunctions and eigenvalue surfaces},
  author = {Marios Mattheakis and Gabriel R. Schleder and Daniel T. Larson and Efthimios Kaxiras},
  journal= {arXiv preprint arXiv:2211.04607},
  year   = {2022}
}
R2 v1 2026-06-28T05:27:53.629Z