Rapid and Accurate Prediction of the Axial Magnetic Anisotropy in Cobalt(II) Complexes Using a Machine-Learning Approach

Henrique C Silva Junior; Heloisa N S Menezes; Glaucio B Ferreira; Guilherme P Guedes

doi:10.1021/acs.inorgchem.3c02569

Rapid and Accurate Prediction of the Axial Magnetic Anisotropy in Cobalt(II) Complexes Using a Machine-Learning Approach

Inorg Chem. 2023 Sep 18;62(37):14838-14842. doi: 10.1021/acs.inorgchem.3c02569. Epub 2023 Sep 7.

Authors

Henrique C Silva Junior¹, Heloisa N S Menezes¹, Glaucio B Ferreira¹, Guilherme P Guedes¹

Affiliation

¹ Instituto de Química, Universidade Federal Fluminense, Niterói, Rio de Janeiro 24020-141, Brazil.

PMID: 37676736
DOI: 10.1021/acs.inorgchem.3c02569

Abstract

Estimating the magnetic anisotropy for single-ion magnets is complex due to its multireference nature. This study demonstrates that deep neural networks (DNNs) can provide accurate axial magnetic anisotropy (D) values, closely matching the complete-active-space self-consistent-field (CASSCF) quality using density functional theory (DFT) data. We curated an 86-parameter database (UFF1) with electronic data from over 33000 cobalt(II) compounds. The DNN achieved an R² of 0.906 and a mean absolute error of 18.1 cm^-1 in comparison to reference CASSCF D values. Remarkably, it is 11 times more accurate than DFT methods and 7700 times faster. This approach hints at DNNs predicting the anisotropy in larger molecules, even when trained on smaller ligands.