An orbital-based representation for accurate quantum machine learning

Autor(en)

Konstantin Karandashev, O. Anatole Von Lilienfeld

Abstrakt

We introduce an electronic structure based representation for quantum machine learning (QML) of electronic properties throughout chemical compound space. The representation is constructed using computationally inexpensive ab initio calculations and explicitly accounts for changes in the electronic structure. We demonstrate the accuracy and flexibility of resulting QML models when applied to property labels, such as total potential energy, HOMO and LUMO energies, ionization potential, and electron affinity, using as datasets for training and testing entries from the QM7b, QM7b-T, QM9, and LIBE libraries. For the latter, we also demonstrate the ability of this approach to account for molecular species of different charge and spin multiplicity, resulting in QML models that infer total potential energies based on geometry, charge, and spin as input.

Organisation(en)

Computergestützte Materialphysik

Externe Organisation(en)

Universität Basel

Journal

Journal of Chemical Physics

Band

156

Anzahl der Seiten

11

ISSN

0021-9606

DOI

https://doi.org/10.1063/5.0083301

Publikationsdatum

03-2022

Peer-reviewed

Ja

ÖFOS 2012

103006 Chemische Physik

Schlagwörter

ASJC Scopus Sachgebiete

Allgemeine Physik und Astronomie, Physical and Theoretical Chemistry

Link zum Portal

https://ucrisportal.univie.ac.at/de/publications/584fcf30-11dd-498a-a017-93dc69777fb0