Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Machine learning and density functional theory

Nature Reviews Physics volume 4, pages 357–358 (2022)Cite this article

Subjects

Over the past decade machine learning has made significant advances in approximating density functionals, but whether this signals the end of human-designed functionals remains to be seen. Ryan Pederson, Bhupalee Kalita and Kieron Burke discuss the rise of machine learning for functional design.

In 2016, DeepMind’s AlphaGo made history as the first computer program to defeat a professional human player in the board game Go. Aside from excelling at board games with human-designed rules, machine learning (ML) has seen impressive applications in scientific research1 where the rules are instead governed by nature, such as protein folding and, more recently, density functional theory (DFT). But can the ML approach to DFT approximations significantly outperform human-designed ones and solve long-standing challenges?

This is a preview of subscription content, access via your institution

Relevant articles

Open Access articles citing this article.

Access options

Rent or buy this article

Get just this article for as long as you need it

$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

References

  1. Douglas, M. R. Machine learning as a tool in theoretical science. Nat. Rev. Phys. 4, 145–146 (2022).

    Article  Google Scholar 

  2. Austin, B. et al. Nersc-10 Workload Analysis (Data from 2018) (NERSC, 2020); https://portal.nersc.gov/project/m888/nersc10/workload/N10_Workload_Analysis.latest.pdf.

  3. Cohen, A. J., Mori-Sánchez, P. & Yang, W. Challenges for density functional theory. Chem. Rev. 112, 289–320 (2012).

    Article  Google Scholar 

  4. Snyder, J. C. et al. Finding density functionals with machine learning. Phys. Rev. Lett. 108, 253002 (2012).

    Article  ADS  Google Scholar 

  5. Brockherde, F. et al. Bypassing the Kohn-Sham equations with machine learning. Nat. Commun. 8, 872 (2017).

    Article  ADS  Google Scholar 

  6. Nagai, R., Akashi, R. & Sugino, O. Completing density functional theory by machine learning hidden messages from molecules. npj Comput. Mater. 6, 43 (2020).

    Article  ADS  Google Scholar 

  7. Li, L. et al. Kohn-Sham equations as regularizer: Building prior knowledge into machine-learned physics. Phys. Rev. Lett. 126, 036401 (2021).

    Article  ADS  Google Scholar 

  8. Kirkpatrick, J. et al. Pushing the frontiers of density functionals by solving the fractional electron problem. Science 374, 1385–1389 (2021).

    Article  ADS  Google Scholar 

  9. Cruz, F. G., Lam, K.-C. & Burke, K. Exchange−correlation energy density from virial theorem. J. Phys. Chem. A 102, 4911 (1998).

    Article  Google Scholar 

  10. Perdew, J. P. Artificial intelligence “sees” split electrons. Science 374, 1322–1323 (2021).

    Article  ADS  Google Scholar 

Download references

Acknowledgements

Work supported by DOE DE-SC0008696 (R.P.) and NSF CHE-2154371 (B.K., K.B.).

Author information

Authors and Affiliations

  1. Department of Physics and Astronomy, University of California, Irvine, CA, USA

    Ryan Pederson & Kieron Burke

  2. Department of Chemistry, University of California, Irvine, CA, USA

    Bhupalee Kalita & Kieron Burke

Authors
  1. Ryan Pederson
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bhupalee Kalita
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kieron Burke
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kieron Burke.

Ethics declarations

Competing interests

The authors declare no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Pederson, R., Kalita, B. & Burke, K. Machine learning and density functional theory. Nat Rev Phys 4, 357–358 (2022). https://doi.org/10.1038/s42254-022-00470-2

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42254-022-00470-2

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing