Machine Learning Approaches toward Orbital-free Density Functional Theory: Simultaneous Training on the Kinetic Energy Density Functional and Its Functional Derivative

Ralf Meyer, Manuel Weichselbaum, Andreas W. Hauser

Research output: Contribution to journalArticle

Abstract

Orbital-free approaches might offer a way to boost the applicability of density functional theory by orders of magnitude in system size. An important ingredient for this endeavor is the kinetic energy density functional. Snyder et al. [ Phys. Rev. Lett. 2012, 108, 253002] presented a machine learning approximation for this functional achieving chemical accuracy on a one-dimensional model system. However, a poor performance with respect to the functional derivative, a crucial element in iterative energy minimization procedures, enforced the application of a computationally expensive projection method. In this work we circumvent this issue by including the functional derivative into the training of various machine learning models. Besides kernel ridge regression, the original method of choice, we also test the performance of convolutional neural network techniques borrowed from the field of image recognition.
Original languageEnglish
Pages (from-to)5685-5694
Number of pages10
JournalJournal of Chemical Theory and Computation
Volume16
Issue number9
DOIs
Publication statusPublished - 8 Sep 2020

ASJC Scopus subject areas

  • Computer Science Applications
  • Physical and Theoretical Chemistry

Fields of Expertise

  • Advanced Materials Science

Fingerprint Dive into the research topics of 'Machine Learning Approaches toward Orbital-free Density Functional Theory: Simultaneous Training on the Kinetic Energy Density Functional and Its Functional Derivative'. Together they form a unique fingerprint.

Cite this