Program in Applied and Computational Mathematics, Princeton University, Princeton, New Jersey 08544, United States.
Laboratory of Computational Physics, Institute of Applied Physics and Computational Mathematics, Huayuan Road 6, Beijing 100088, People's Republic of China.
J Chem Theory Comput. 2021 Jan 12;17(1):170-181. doi: 10.1021/acs.jctc.0c00872. Epub 2020 Dec 9.
We propose a general machine learning-based framework for building an accurate and widely applicable energy functional within the framework of generalized Kohn-Sham density functional theory. To this end, we develop a way of training self-consistent models that are capable of taking large datasets from different systems and different kinds of labels. We demonstrate that the functional that results from this training procedure gives chemically accurate predictions on energy, force, dipole, and electron density for a large class of molecules. It can be continuously improved when more and more data are available.
我们提出了一种基于机器学习的通用框架，用于在广义 Kohn-Sham 密度泛函理论的框架内构建精确且广泛适用的能量泛函。为此，我们开发了一种训练自洽模型的方法，这种模型能够处理来自不同系统和不同类型标签的大型数据集。我们证明，从这种训练过程中得到的泛函可以对一大类分子的能量、力、偶极矩和电子密度给出化学上准确的预测。当有更多的数据可用时，它可以不断得到改进。
