de.mpg.escidoc.pubman.appbase.FacesBean
Deutsch
 
Hilfe Wegweiser Impressum Kontakt Einloggen
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Zeitschriftenartikel

Machine Learning of Accurate Energy-Conserving Molecular Force Fields

MPG-Autoren
http://pubman.mpdl.mpg.de/cone/persons/resource/persons22175

Tkatchenko,  Alexandre
Theory, Fritz Haber Institute, Max Planck Society;
Physics and Materials Science Research Unit, University of Luxembourg;

http://pubman.mpdl.mpg.de/cone/persons/resource/persons192349

Sauceda,  Huziel E.
Theory, Fritz Haber Institute, Max Planck Society;

Externe Ressourcen
Es sind keine Externen Ressourcen verfügbar
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Chmiela, S., Tkatchenko, A., Sauceda, H. E., Poltavsky, I., Schütt, K. T., & Müller, K.-R. (in press). Machine Learning of Accurate Energy-Conserving Molecular Force Fields. Science Advances.


Zitierlink: http://hdl.handle.net/11858/00-001M-0000-002C-B181-0
Zusammenfassung
Using conservation of energy { a fundamental property of closed classical and quantum mechanical systems { we develop an efficient gradient-domain machine learning (GDML) approach to construct accurate molecular force fields using a restricted number of samples from ab initio molecular dynamics (AIMD) trajectories. The GDML implementation is able to reproduce global potentialenergy surfaces of intermediate-size molecules with an accuracy of 0.3 kcal/mol for energies and 1 kcal/mol/Å for atomic forces using only 1000 conformational geometries for training. We demonstrate this accuracy for AIMD trajectories of molecules, including benzene, toluene, naphthalene, ethanol, uracil, and aspirin. The challenge of constructing conservative force fields is accomplished in our work by learning in a Hilbert space of vector-valued functions that obey the law of energy conservation. The GDML approach enables quantitative molecular dynamics simulations for molecules at a fraction of cost of explicit AIMD calculations, thereby allowing the construction of efficient force fields with the accuracy and transferability of high-level ab initio methods.