Journalartikel

Autorenliste: Ruth, M; Gerbig, D; Schreiner, PR

Jahr der Veröffentlichung: 2023

Seiten: 4912-4920

Zeitschrift: Journal of Chemical Theory and Computation

Bandnummer: 19

Heftnummer: 15

ISSN: 1549-9618

eISSN: 1549-9626

DOI Link: https://doi.org/10.1021/acs.jctc.3c00274

Verlag: American Chemical Society

Abstract: 
Accurate electronic energies and properties are crucialfor successfulreaction design and mechanistic investigations. Computing energiesand properties of molecular structures has proven extremely useful,and, with increasing computational power, the limits of high-levelapproaches (such as coupled cluster theory) are expanding to everlarger systems. However, because scaling is highly unfavorable, thesemethods are still not universally applicable to larger systems. Toaddress the need for fast and accurate electronic energies of largersystems, we created a database of around 8000 small organic monomers(2000 dimers) optimized at the B3LYP-D3(BJ)/cc-pVTZ level of theory.This database also includes single-point energies computed at variouslevels of theory, including PBE1PBE, & omega;& UBeta;97X, M06-2X,revTPSS, B3LYP, and BP86, for density functional theory as well asDLPNO-CCSD(T) and CCSD(T) for coupled cluster theory, all in conjunctionwith a cc-pVTZ basis. We used this database to train machine learningmodels based on graph neural networks using two different graph representations.Our models are able to make energy predictions from B3LYP-D3(BJ)/cc-pVTZinputs to CCSD(T)/cc-pVTZ outputs with a mean absolute error of 0.78and to DLPNO-CCSD(T)/cc-pVTZ with an mean absolute error of 0.50 and0.18 kcal mol(-1) for monomers and dimers, respectively.The model for dimers was further validated on the S22 database, andthe monomer model was tested on challenging systems, including thosewith highly conjugated or functionally complex molecules.

Harvard-Zitierstil: Ruth, M., Gerbig, D. and Schreiner, P. (2023) Machine Learning for Bridging the Gap between Density Functional Theory and Coupled Cluster Energies, Journal of Chemical Theory and Computation, 19(15), pp. 4912-4920. https://doi.org/10.1021/acs.jctc.3c00274

APA-Zitierstil: Ruth, M., Gerbig, D., & Schreiner, P. (2023). Machine Learning for Bridging the Gap between Density Functional Theory and Coupled Cluster Energies. Journal of Chemical Theory and Computation. 19(15), 4912-4920. https://doi.org/10.1021/acs.jctc.3c00274