CaltechAUTHORS
  A Caltech Library Service

A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules

Cheng, Lixue and Welborn, Matthew and Christensen, Anders S. and Miller, Thomas F., III (2019) A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules. Journal of Chemical Physics, 150 (13). Art. No. 131103. ISSN 0021-9606. http://resolver.caltech.edu/CaltechAUTHORS:20190415-085751643

[img] PDF - Submitted Version
See Usage Policy.

541Kb
[img] PDF - Supplemental Material
See Usage Policy.

153Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20190415-085751643

Abstract

We address the degree to which machine learning (ML) can be used to accurately and transferably predict post-Hartree-Fock correlation energies. Refined strategies for feature design and selection are presented, and the molecular-orbital-based machine learning (MOB-ML) method is applied to several test systems. Strikingly, for the second-order Møller-Plessett perturbation theory, coupled cluster with singles and doubles (CCSD), and CCSD with perturbative triples levels of theory, it is shown that the thermally accessible (350 K) potential energy surface for a single water molecule can be described to within 1 mhartree using a model that is trained from only a single reference calculation at a randomized geometry. To explore the breadth of chemical diversity that can be described, MOB-ML is also applied to a new dataset of thermalized (350 K) geometries of 7211 organic models with up to seven heavy atoms. In comparison with the previously reported Δ-ML method, MOB-ML is shown to reach chemical accuracy with threefold fewer training geometries. Finally, a transferability test in which models trained for seven-heavy-atom systems are used to predict energies for thirteen-heavy-atom systems reveals that MOB-ML reaches chemical accuracy with 36-fold fewer training calculations than Δ-ML (140 vs 5000 training calculations).


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1063/1.5088393DOIArticle
https://arxiv.org/abs/1901.03309arXivDiscussion Paper
ORCID:
AuthorORCID
Cheng, Lixue0000-0002-7329-0585
Christensen, Anders S.0000-0002-7253-6897
Miller, Thomas F., III0000-0002-1882-5380
Additional Information:© 2019 Published under license by AIP Publishing. Submitted: 10 January 2019; Accepted: 19 March 2019; Published Online: 4 April 2019. We thank Daniel Smith (Molecular Sciences Software Institute) and Alberto Gobbi (Genentech) for a helpful discussion about available training datasets. T.F.M. acknowledges support from AFOSR Award No. FA9550-17-1-0102. A.S.C. acknowledges support from the National Centre of Competence in Research (NCCR) Materials Revolution: Computational Design and Discovery of Novel Materials (MARVEL) of the Swiss National Science Foundation (SNSF). We also acknowledge support from the Resnick Sustainability Institute postdoctoral fellowship (M.W.) and the Camille Dreyfus Teacher-Scholar Award (T.F.M.). Computational resources were provided by the National Energy Research Scientific Computing Center (NERSC), a DOE Office of Science User Facility supported by the DOE Office of Science under Contract No. DE-AC02-05CH11231.
Group:Resnick Sustainability Institute
Funders:
Funding AgencyGrant Number
Air Force Office of Scientific Research (AFOSR)FA9550-17-1-0102
Swiss National Science Foundation (SNSF)UNSPECIFIED
Resnick Sustainability InstituteUNSPECIFIED
Camille and Henry Dreyfus FoundationUNSPECIFIED
Department of Energy (DOE)DE-AC02-05CH11231
Record Number:CaltechAUTHORS:20190415-085751643
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20190415-085751643
Official Citation:A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules. Lixue Cheng, Matthew Welborn, Anders S. Christensen, and Thomas F. Miller III. The Journal of Chemical Physics 2019 150:13; doi: 10.1063/1.5088393
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94699
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:16 Apr 2019 21:51
Last Modified:16 Apr 2019 21:51

Repository Staff Only: item control page