SchrödingerNet: A Universal Neural Network Solver for The Schrödinger Equation

• DOI: 10.48550/arxiv.2408.04497
• Publication Date: 2025-01-07
• Authors: Yaolong Zhang; Bin Jiang; Hua Guo
• Keywords: Chemical Physics (physics.chem-ph); FOS: Physical sciences; Computational Physics (physics.comp-ph)

4 figure<br/>Recent advances in machine learning have facilitated numerically accurate solution of the electronic SchrödingerNet equation (SE) by integrating various neural network (NN)-based wavefunction ansatzes with variational Monte Carlo methods. Nevertheless, such NN-based methods are all based on the Born-Oppenheimer approximation (BOA) and require a separate and computationally expensive training for each nuclear configuration. In this work, we propose a novel NN architecture, SchrödingerNet, to solve the full electronic-nuclear SE by defining a loss function designed to equalize local energies across the system. This approach is based on a rotationally invariant total wavefunction ansatz that includes both nuclear and electronic coordinates. This strategy allows for an efficient and accurate generation of a continuous potential energy surface at any geometry within the well-sampled nuclear configuration space, and also incorporates non-BO corrections, through a single training process. Comparison with benchmarks of atomic and molecular systems demonstrates its accuracy and efficiency<br/>