Generalized Density-Functional Tight-Binding Repulsive Potentials from Unsupervised Machine Learning

Kranz, Julian J. and Kubillus, Maximilian and Ramakrishnan, Raghunathan and von Lilienfeld, O. Anatole and Elstner, Marcus. (2018) Generalized Density-Functional Tight-Binding Repulsive Potentials from Unsupervised Machine Learning. Journal of Chemical Theory and Computation, 14 (5). pp. 2341-2352 .

PDF - Accepted Version

Official URL: https://edoc.unibas.ch/68688/

Downloads: Statistics Overview


We combine the approximate density-functional tight-binding (DFTB) method with unsupervised machine learning. This allows us to improve transferability and accuracy, make use of large quantum chemical data sets for the parametrization, and efficiently automatize the parametrization process of DFTB. For this purpose, generalized pair-potentials are introduced, where the chemical environment is included during the learning process, leading to more specific effective two-body potentials. We train on energies and forces of equilibrium and nonequilibrium structures of 2100 molecules, and test on ∼130 000 organic molecules containing O, N, C, H, and F atoms. Atomization energies of the reference method can be reproduced within an error of ∼2.6 kcal/mol, indicating drastic improvement over standard DFTB.
Faculties and Departments:05 Faculty of Science > Departement Chemie
05 Faculty of Science > Departement Chemie > Chemie > Physikalische Chemie (Lilienfeld)
UniBasel Contributors:Ramakrishnan, Raghunathan and von Lilienfeld, Anatole
Item Type:Article, refereed
Article Subtype:Research Article
Publisher:American Chemical Society
Note:Publication type according to Uni Basel Research Database: Journal article
Identification Number:
edoc DOI:
Last Modified:01 Jul 2020 09:34
Deposited On:21 Aug 2019 14:22

Repository Staff Only: item control page