Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Learning Electron Densities in the Condensed Phase

Lewis, A., Grisafi, A., Ceriotti, M., & Rossi, M. (2021). Learning Electron Densities in the Condensed Phase. Journal of Chemical Theory and Computation, 17(11), 7203-7214. doi:10.1021/acs.jctc.1c00576.

Item is

Basisdaten

einblenden: ausblenden:
Genre: Zeitschriftenartikel

Dateien

einblenden: Dateien
ausblenden: Dateien
:
ct1c00576_si_002.pdf (Ergänzendes Material), 387KB
Name:
ct1c00576_si_002.pdf
Beschreibung:
Supporting Information: Equations for the calculation of the overlap matrix and vector of projections in periodic systems, an error analysis of the electrostatic and Hartree energies, the optimizations of the SALTED hyper-paramaters for the homogeneous and heterogeneous data sets, the optimization of the direct GPR hyper-parameters and their learning curves, and an illustration of the application of SALTED to isolated molecules using NAOs
OA-Status:
Keine Angabe
Sichtbarkeit:
Öffentlich
MIME-Typ / Prüfsumme:
application/pdf / [MD5]
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-
Lizenz:
-
:
acs.jctc.1c00576.pdf (Verlagsversion), 2MB
Name:
acs.jctc.1c00576.pdf
Beschreibung:
Open access funded by Max Planck Society.
OA-Status:
Keine Angabe
Sichtbarkeit:
Öffentlich
MIME-Typ / Prüfsumme:
application/pdf / [MD5]
Technische Metadaten:
Copyright Datum:
2021
Copyright Info:
© The Authors. Published byAmerican Chemical Society

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
https://arxiv.org/abs/2106.05364 (Preprint)
Beschreibung:
-
OA-Status:
Keine Angabe
externe Referenz:
https://dx.doi.org/10.1021/acs.jctc.1c00576 (Verlagsversion)
Beschreibung:
-
OA-Status:
Keine Angabe

Urheber

einblenden:
ausblenden:
 Urheber:
Lewis, A.1, Autor           
Grisafi, A.2, Autor
Ceriotti, M.2, Autor
Rossi, M.1, Autor           
Affiliations:
1Simulations from Ab Initio Approaches, Theory Department, Max Planck Institute for the Structure and Dynamics of Matter, Max Planck Society, ou_3185035              
2Laboratory of Computational Science and Modeling, IMX, École Polytechnique Féd́erale de Lausanne, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: We introduce a local machine-learning method for predicting the electron densities of periodic systems. The framework is based on a numerical, atom-centered auxiliary basis, which enables an accurate expansion of the all-electron density in a form suitable for learning isolated and periodic systems alike. We show that, using this formulation, the electron densities of metals, semiconductors, and molecular crystals can all be accurately predicted using symmetry-adapted Gaussian process regression models, properly adjusted for the nonorthogonal nature of the basis. These predicted densities enable the efficient calculation of electronic properties, which present errors on the order of tens of meV/atom when compared to ab initio density-functional calculations. We demonstrate the key power of this approach by using a model trained on ice unit cells containing only 4 water molecules to predict the electron densities of cells containing up to 512 molecules and see no increase in the magnitude of the errors of derived electronic properties when increasing the system size. Indeed, we find that these extrapolated derived energies are more accurate than those predicted using a direct machine-learning model. Finally, on heterogeneous data sets SALTED can predict electron densities with errors below 4%.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2021-06-102021-10-202021-11-09
 Publikationsstatus: Erschienen
 Seiten: 12
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: Expertenbegutachtung
 Identifikatoren: arXiv: 2106.05364
DOI: 10.1021/acs.jctc.1c00576
 Art des Abschluß: -

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Journal of Chemical Theory and Computation
  Andere : J. Chem. Theory Comput.
Genre der Quelle: Zeitschrift
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Washington, D.C. : American Chemical Society
Seiten: - Band / Heft: 17 (11) Artikelnummer: - Start- / Endseite: 7203 - 7214 Identifikator: ISSN: 1549-9618
CoNE: https://pure.mpg.de/cone/journals/resource/111088195283832