Using Machine Learning to Find New Density Functionals

TL;DR

This paper reviews the progress and challenges in applying machine learning to develop new density functionals in electronic structure theory, highlighting current advancements and future directions.

Contribution

It provides a comprehensive overview of the state-of-the-art in machine learning density functional theory and discusses future challenges and technological solutions.

Findings

Machine learning has significantly advanced the development of density functionals.

Current challenges include data quality and transferability of models.

Future research directions involve integrating state-of-the-art tools to overcome existing limitations.

Abstract

Machine learning has now become an integral part of research and innovation. The field of machine learning density functional theory has continuously expanded over the years while making several noticeable advances. We briefly discuss the status of this field and point out some current and future challenges. We also talk about how state-of-the-art science and technology tools can help overcome these challenges. This draft is a part of the "Roadmap on Machine Learning in Electronic Structure" to be published in Electronic Structure (EST).