DeePKS + ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials
DeePKS + ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials
复制标题
DeePKS ABACUS 作为昂贵的量子力学模型和机器学习潜力之间的桥梁
DOI：
10.1021/acs.jpca.2c05000
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Linfeng Zhang
中科院分区：
文献类型：
--
作者：
Wenfei Li;Qi Ou;Yixiao Chen;Yu Cao;Renxi Liu;Chunyi Zhang;Daye Zheng;Chun Cai;Xifan Wu;Han Wang;Mohan Chen;Linfeng Zhang
最近，机器学习（ML）潜力的发展使得能够以量子力学（QM）模型的精度进行大规模和长时间的分子模拟。然而，对于不同水平的QM方法，例如在元GGA水平和/或具有精确交换的密度泛函理论（DFT）、量子蒙特卡罗等，由于其高成本，生成足够量的数据用于训练ML势仍然在计算上具有挑战性。在这项工作中，我们证明了这个问题可以在很大程度上缓解深科恩-沙姆（DeePKS），基于ML的DFT模型。DeePKS采用了一个计算效率高的基于神经网络的功能模型来构建一个校正项添加到一个便宜的DFT模型。在训练时，与高级QM方法相比，DeePKS提供了密切匹配的能量和力，但所需的训练数据数量比训练可靠的ML潜力所需的数量级少。因此，DeePKS可以作为昂贵的QM模型和ML潜力之间的桥梁：人们可以生成相当数量的高精度QM数据来训练DeePKS模型，然后使用DeePKS模型标记大量的配置来训练ML潜力。周期系统的这个方案是在DFT包ABACUS中实现的，该包是开源的，可以在各种应用中使用。
Recently, the development of machine learning (ML) potentials has made it possible to perform large-scale and long-time molecular simulations with the accuracy of quantum mechanical (QM) models. However, for different levels of QM methods, such as density functional theory (DFT) at the meta-GGA level and/or with exact exchange, quantum Monte Carlo, etc., generating a sufficient amount of data for training an ML potential has remained computationally challenging due to their high cost. In this work, we demonstrate that this issue can be largely alleviated with Deep Kohn–Sham (DeePKS), an ML-based DFT model. DeePKS employs a computationally efficient neural network-based functional model to construct a correction term added upon a cheap DFT model. Upon training, DeePKS offers closely matched energies and forces compared with high-level QM method, but the number of training data required is orders of magnitude less than that required for training a reliable ML potential. As such, DeePKS can serve as a bridge between expensive QM models and ML potentials: one can generate a decent amount of high-accuracy QM data to train a DeePKS model and then use the DeePKS model to label a much larger amount of configurations to train an ML potential. This scheme for periodic systems is implemented in a DFT package ABACUS, which is open source and ready for use in various applications.