Paper Image

Machine learning improves density functional theory

Published on:

1 November 2023

Primary Category:

Chemical Physics

Paper Authors:

Johannes Voss


Key Details

Machine learning can improve accuracy of density functional theory

Neural networks trained as exchange-correlation functionals

Post-DFT machine learning corrections

Atomic structure-based corrections

AI generated summary

Machine learning improves density functional theory

This paper reviews how machine learning techniques like neural networks can supplement density functional approximations to achieve higher accuracy. Machine learning models are trained on benchmark quantum chemistry and experimental data to correct errors like self-interaction and static correlation in semi-local density functionals.

Answers from this paper


No comments yet, be the first to start the conversation...

Sign up to comment on this paper

Sign Up