Deep learning electronic structures from ab initio calculations holds great potential to revolutionize computational materials studies. While existing methods proved success in deep-learning density functional theory (DFT) Hamiltonian matrices, they are limited to DFT programs using localized atomic-like bases and heavily depend on the form of the bases. Here, we propose the DeepH-r method for deep-learning DFT Hamiltonians in real space, facilitating the prediction of DFT Hamiltonian in a basis-independent manner. An equivariant neural network architecture for modeling the real-space DFT potential is developed, targeting a more fundamental quantity in DFT. The real-space potential exhibits simplified principles of equivariance and enhanced nearsightedness, further boosting the performance of deep learning. When applied to evaluate the Hamiltonian matrix, this method significantly improved in accuracy, as exemplified in multiple case studies. Given the abundance of data in the real-space potential, this work may pave a novel pathway for establishing a ``large materials model" with increased accuracy.
@article{arxiv.2407.14379,
title = {Deep learning density functional theory Hamiltonian in real space},
author = {Zilong Yuan and Zechen Tang and Honggeng Tao and Xiaoxun Gong and Zezhou Chen and Yuxiang Wang and He Li and Yang Li and Zhiming Xu and Minghui Sun and Boheng Zhao and Chong Wang and Wenhui Duan and Yong Xu},
journal= {arXiv preprint arXiv:2407.14379},
year = {2024}
}