Issue 16, 2024

Deep Mind 21 functional does not extrapolate to transition metal chemistry

Abstract

The development of density functional approximations stands at a crossroads: while machine-learned functionals show potential to surpass their human-designed counterparts, their extrapolation to unseen chemistry lags behind. Here we assess how well the recent Deep Mind 21 (DM21) machine-learned functional [Science, 2021, 374, 1385–1389], trained on main-group chemistry, extrapolates to transition metal chemistry (TMC). We show that DM21 demonstrates comparable or occasionally superior accuracy to B3LYP for TMC, but consistently struggles with achieving self-consistent field convergence for TMC molecules. We also compare main-group and TMC machine-learning DM21 features to shed light on DM21's challenges in TMC. We finally propose strategies to overcome limitations in the extrapolative capabilities of machine-learned functionals in TMC.

Graphical abstract: Deep Mind 21 functional does not extrapolate to transition metal chemistry

Supplementary files

Article information

Article type
Paper
Submitted
28 2 2024
Accepted
28 3 2024
First published
04 4 2024
This article is Open Access
Creative Commons BY license

Phys. Chem. Chem. Phys., 2024,26, 12289-12298

Deep Mind 21 functional does not extrapolate to transition metal chemistry

H. Zhao, T. Gould and S. Vuckovic, Phys. Chem. Chem. Phys., 2024, 26, 12289 DOI: 10.1039/D4CP00878B

This article is licensed under a Creative Commons Attribution 3.0 Unported Licence. You can use material from this article in other publications without requesting further permissions from the RSC, provided that the correct acknowledgement is given.

Read more about how to correctly acknowledge RSC content.

Social activity

Spotlight

Advertisements