The central role of density functional theory in the AI age

Author(s)
Bing Huang, Guido Falk von Rudorff, O. Anatole von Lilienfeld
Abstract

Density functional theory (DFT) plays a pivotal role in chemical and materials science because of its relatively high predictive power, applicability, versatility, and computational efficiency. We review recent progress in machine learning (ML) model developments, which have relied heavily on DFT for synthetic data generation and for the design of model architectures. The general relevance of these developments is placed in a broader context for chemical and materials sciences. DFT-based ML models have reached high efficiency, accuracy, scalability, and transferability and pave the way to the routine use of successful experimental planning software within self-driving laboratories.

Organisation(s)
Computational Materials Physics
External organisation(s)
Universität Kassel, Vector Institute for Artificial Intelligence, University of Toronto, Technische Universität Berlin
Journal
Science
Volume
381
Pages
170-175
No. of pages
6
ISSN
0036-8075
DOI
https://doi.org/10.1126/science.abn3445
Publication date
07-2023
Peer reviewed
Yes
Austrian Fields of Science 2012
103006 Chemical physics, 102019 Machine learning
ASJC Scopus subject areas
General
Portal url
https://ucrisportal.univie.ac.at/en/publications/the-central-role-of-density-functional-theory-in-the-ai-age(197ca089-8a78-4bd6-9478-0fc307153f5b).html