Machine Learning-Assisted Selection of Active Spaces for Strongly Correlated Transition Metal Systems

0546397 - ÚFCH JH 2022 RIV US eng J - Journal Article
Golub, Pavlo - Antalík, Andrej - Veis, Libor - Brabec, Jiří
Machine Learning-Assisted Selection of Active Spaces for Strongly Correlated Transition Metal Systems.
Journal of Chemical Theory and Computation. Roč. 17, č. 10 (2021), s. 6053-6072. ISSN 1549-9618. E-ISSN 1549-9626
R&D Projects: GA ČR(CZ) GJ19-13126Y
Grant - others:Ga MŠk(CZ) LM2015070
Institutional support: RVO:61388955
Keywords : MATRIX RENORMALIZATION-GROUP * DENSITY-FUNCTIONAL THEORY * MOLECULAR-STRUCTURE
OECD category: Physical chemistry
Impact factor: 6.578, year: 2021
Method of publishing: Limited access

Active space quantum chemical methods could provide very accurate description of strongly correlated electronic systems, which is of tremendous value for natural sciences. The proper choice of the active space is crucial but a nontrivial task. In this article, we present a neural network-based approach for automatic selection of active spaces, focused on transition metal systems. The training set has been formed from artificial systems composed of one transition metal and various ligands, on which we have performed the density matrix renormalization group and calculated the single-site entropy. On the selected set of systems, ranging from small benchmark molecules up to larger challenging systems involving two metallic centers, we demonstrate that our machine learning models could predict the active space orbitals with reasonable accuracy. We also tested the transferability on out-of-the-model systems, including bimetallic complexes and complexes with ligands, which were not involved in the training set. Also, we tested the correctness of the automatically selected active spaces on a Fe(II)–porphyrin model, where we studied the lowest states at the DMRG level and compared the energy difference between spin states or the energy difference between conformations of ferrocene with recent studies.
Permanent Link: http://hdl.handle.net/11104/0322923