Your privacy, your choice

We use essential cookies to make sure the site can function. We also use optional cookies for advertising, personalisation of content, usage analysis, and social media, as well as to allow video information to be shared for both marketing, analytics and editorial purposes.

By accepting optional cookies, you consent to the processing of your personal data - including transfers to third parties. Some third parties are outside of the European Economic Area, with varying standards of data protection.

See our privacy policy for more information on the use of your personal data.

for further information and to change your choices.
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.

  • NEWS AND VIEWS

Machine learning slashes the testing needed to work out battery lifetimes

A machine-learning method that reasons and adapts has been developed to solve one of the most time-consuming bottlenecks in battery development.
By
  1. Chao Hu

    1. Chao Hu is at the School of Mechanical, Aerospace, and Manufacturing Engineering, University of Connecticut, Storrs, Connecticut 06269, USA.

Lithium-ion batteries are increasingly used as power sources for diverse applications ranging from electric vehicles to medical devices. However, for any new battery design, it still takes a frustratingly long time to answer one fundamental question: how long will the batteries last? Conventional approaches to answering this question require batteries to be repeatedly cycled (charged and discharged) until they reach an end-of-life threshold, a process that can take months or even years. Writing in Nature, Zhang et al.1 present a machine-learning method that short-circuits this waiting game, predicting battery lifetime with an accuracy that is sufficient for real-world use in one week or less — even for designs that the model has never encountered.

Access options

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

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

Nature 650, 41-42 (2026)

doi: https://doi.org/10.1038/d41586-026-00168-w

References

  1. Zhang, J. et al. Nature 650, 110–115 (2026).

    Article  Google Scholar 

  2. Ramadass, P., Haran, B., Gomadam, P. M., White, R. & Popov, B. N. J. Electrochem. Soc. 151, A196 (2004).

    Article  Google Scholar 

  3. Ramadesigan, V. et al. J. Electrochem. Soc. 158, A1048 (2011).

    Article  Google Scholar 

  4. Birkl, C. R., Roberts, M. R., McTurk, E., Bruce, P. G. & Howey, D. A. J. Power Sources 341, 373–386 (2017).

    Article  Google Scholar 

  5. Shen, S., Sadoughi, M., Li, M., Wang, Z. & Hu, C. Appl. Energy 260, 114296 (2020).

    Article  Google Scholar 

  6. Figgener, J. et al. Nature Energy 9, 1438–1447 (2024).

    Article  Google Scholar 

  7. Severson, K. A. et al. Nature Energy 4, 383–391 (2019).

    Article  Google Scholar 

Download references

Competing Interests

The author declares no competing interests.

Subjects

Latest on:

Nature Careers

Jobs

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