Machine Learning Density Functionals from the Random-Phase Approximation

Autor(en)

Stefan Riemelmoser, Carla Verdi, Merzuk Kaltak, Georg Kresse

Abstrakt

Kohn-Sham density functional theory (DFT) is the standard method for first-principles calculations in computational chemistry and materials science. More accurate theories such as the random-phase approximation (RPA) are limited in application due to their large computational cost. Here, we use machine learning to map the RPA to a pure Kohn-Sham density functional. The machine learned RPA model (ML-RPA) is a nonlocal extension of the standard gradient approximation. The density descriptors used as ingredients for the enhancement factor are nonlocal counterparts of the local density and its gradient. Rather than fitting only RPA exchange-correlation energies, we also include derivative information in the form of RPA optimized effective potentials. We train a single ML-RPA functional for diamond, its surfaces, and liquid water. The accuracy of ML-RPA for the formation energies of 28 diamond surfaces reaches that of state-of-the-art van der Waals functionals. For liquid water, however, ML-RPA cannot yet improve upon the standard gradient approximation. Overall, our work demonstrates how machine learning can extend the applicability of the RPA to larger system sizes, time scales, and chemical spaces.

Organisation(en)

Computergestützte Materialphysik

Externe Organisation(en)

The University of Sydney, University of Queensland, VASP Software GmbH

Journal

Journal of Chemical Theory and Computation

Band

19

Seiten

7287-7299

Anzahl der Seiten

13

ISSN

1549-9618

DOI

https://doi.org/10.48550/arXiv.2308.00665

Publikationsdatum

10-2023

Peer-reviewed

Ja

ÖFOS 2012

103018 Materialphysik, 104027 Computational Chemistry, 102019 Machine Learning

ASJC Scopus Sachgebiete

Computer Science Applications, Physical and Theoretical Chemistry

Link zum Portal

https://ucrisportal.univie.ac.at/de/publications/d246bb06-be14-470c-8b34-49510baba2e3