DeePKS: a comprehensive data-driven approach towards chemically accurate density functional theory
This work addresses the challenge of improving accuracy in computational chemistry for researchers and practitioners, representing a novel method rather than an incremental advancement.
The authors tackled the problem of achieving chemically accurate predictions in density functional theory by developing a machine learning-based framework, resulting in a functional that provides accurate predictions for energy, force, dipole, and electron density across a large class of molecules.
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.