Vuckovic Research Group has recently published a new article with Heng Zhao as the first author (just 6 months into his PhD!) and in collaboration with Tim Gould, in the PCCP Emerging Investigators collection in the journal Physical Chemistry Chemical Physics (PCCP) Emerging Investigators collection, entitled "Deep Mind 21 functional does not extrapolate to transition metal chemistry".

For more information and to read the article: https://pubs.rsc.org/en/content/articlehtml/2024/cp/d4cp00878b?page=search

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.