Pushing the limits of OFDFT with neural networks

Andreas W. Hauser

doi:10.1038/s43588-024-00610-x

Pushing the limits of OFDFT with neural networks

Andreas W. Hauser^*

^*Corresponding author for this work

Institute of Experimental Physics (5110)

Research output: Contribution to journal › Comment/debate › peer-review

Abstract

A neural network-based method for advancing orbital-free density functional theory (OFDFT) is developed, which reaches DFT accuracy and maintains lower cost complexity.

Original language	English
Pages (from-to)	163-164
Number of pages	2
Journal	Nature Computational Science
Volume	4
Issue number	3
DOIs	https://doi.org/10.1038/s43588-024-00610-x
Publication status	Published - Mar 2024

ASJC Scopus subject areas

Computer Science (miscellaneous)
Computer Science Applications
Computer Networks and Communications

Access to Document

10.1038/s43588-024-00610-x

Cite this

@article{fcda89a15ad24edc94f0a92ca501ece1,

title = "Pushing the limits of OFDFT with neural networks",

abstract = "A neural network-based method for advancing orbital-free density functional theory (OFDFT) is developed, which reaches DFT accuracy and maintains lower cost complexity.",

author = "Hauser, {Andreas W.}",

note = "Publisher Copyright: {\textcopyright} Springer Nature America, Inc. 2024.",

year = "2024",

month = mar,

doi = "10.1038/s43588-024-00610-x",

language = "English",

volume = "4",

pages = "163--164",

journal = "Nature Computational Science",

issn = "2662-8457",

publisher = "Nature Research",

number = "3",

}

TY - JOUR

T1 - Pushing the limits of OFDFT with neural networks

AU - Hauser, Andreas W.

N1 - Publisher Copyright: © Springer Nature America, Inc. 2024.

PY - 2024/3

Y1 - 2024/3

N2 - A neural network-based method for advancing orbital-free density functional theory (OFDFT) is developed, which reaches DFT accuracy and maintains lower cost complexity.

AB - A neural network-based method for advancing orbital-free density functional theory (OFDFT) is developed, which reaches DFT accuracy and maintains lower cost complexity.

UR - http://www.scopus.com/inward/record.url?scp=85187183946&partnerID=8YFLogxK

U2 - 10.1038/s43588-024-00610-x

DO - 10.1038/s43588-024-00610-x

M3 - Comment/debate

AN - SCOPUS:85187183946

SN - 2662-8457

VL - 4

SP - 163

EP - 164

JO - Nature Computational Science

JF - Nature Computational Science

IS - 3

ER -

Pushing the limits of OFDFT with neural networks

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this