Realizing large materials models has emerged as a critical endeavor for materials research in the new era of artificial intelligence, but how to achieve this fantastic and challenging objective remains elusive. Here, we propose a feasible pathway to address this paramount pursuit by developing universal materials models of deep-learning density functional theory Hamiltonian (DeepH), enabling computational modeling of the complicated structure-property relationship of materials in general. By constructing a large materials database and substantially improving the DeepH method, we obtain a universal materials model of DeepH capable of handling diverse elemental compositions and material structures, achieving remarkable accuracy in predicting material properties. We further showcase a promising application of fine-tuning universal materials models for enhancing specific materials models. This work not only demonstrates the concept of DeepH's universal materials model but also lays the groundwork for developing large materials models, opening up significant opportunities for advancing artificial intelligence-driven materials discovery.
@article{arxiv.2406.10536,
title = {Universal materials model of deep-learning density functional theory Hamiltonian},
author = {Yuxiang Wang and Yang Li and Zechen Tang and He Li and Zilong Yuan and Honggeng Tao and Nianlong Zou and Ting Bao and Xinghao Liang and Zezhou Chen and Shanghua Xu and Ce Bian and Zhiming Xu and Chong Wang and Chen Si and Wenhui Duan and Yong Xu},
journal= {arXiv preprint arXiv:2406.10536},
year = {2024}
}