English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach

Ramakrishnan, R., Dral, P. O., Rupp, M., & von Lilienfeld, O. A. (2015). Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach. Journal of Chemical Theory and Computation, 11(5), 2087-2096. doi:10.1021/acs.jctc.5b00099.

Item is

Files

show Files
hide Files
:
ct5b00099_si_001.pdf (Supplementary material), 361KB
Name:
ct5b00099_si_001.pdf
Description:
Supporting Information
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Ramakrishnan, Raghunathan1, Author
Dral, Pavlo O.2, 3, Author              
Rupp, Matthias1, Author
von Lilienfeld, O. Anatole1, 4, Author
Affiliations:
1Institute of Physical Chemistry and National Center for Computational Design and Discovery of Novel Materials, Department of Chemistry, University of Basel, Klingelbergstraße 80, CH-4056 Basel, Switzerland, ou_persistent22              
2Research Department Thiel, Max-Planck-Institut für Kohlenforschung, Max Planck Society, ou_1445590              
3Computer-Chemie-Centrum and Interdisciplinary Center for Molecular Materials, Department Chemie und Pharmazie, Friedrich-Alexander-Universität Erlangen-Nürnberg, Nägelsbachstraße 25, 91052 Erlangen, Germany, ou_persistent22              
4Argonne Leadership Computing Facility, Argonne National Laboratory, 9700 S. Cass Avenue, Lemont, Illinois 60439, United States, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Chemically accurate and comprehensive studies of the virtual space of all possible molecules are severely limited by the computational cost of quantum chemistry. We introduce a composite strategy that adds machine learning corrections to computationally inexpensive approximate legacy quantum methods. After training, highly accurate predictions of enthalpies, free energies, entropies, and electron correlation energies are possible, for significantly larger molecular sets than used for training. For thermochemical properties of up to 16k isomers of C7H10O2 we present numerical evidence that chemical accuracy can be reached. We also predict electron correlation energy in post Hartree–Fock methods, at the computational cost of Hartree–Fock, and we establish a qualitative relationship between molecular entropy and electron correlation. The transferability of our approach is demonstrated, using semiempirical quantum chemistry and machine learning models trained on 1 and 10% of 134k organic molecules, to reproduce enthalpies of all remaining molecules at density functional theory level of accuracy.

Details

show
hide
Language(s): eng - English
 Dates: 2015-02-032015-04-102015-05-12
 Publication Status: Published in print
 Pages: 10
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1021/acs.jctc.5b00099
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Journal of Chemical Theory and Computation
  Other : J. Chem. Theory Comput.
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Washington, D.C. : American Chemical Society
Pages: - Volume / Issue: 11 (5) Sequence Number: - Start / End Page: 2087 - 2096 Identifier: ISSN: 1549-9618
CoNE: https://pure.mpg.de/cone/journals/resource/111088195283832