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

Accurate machine learning in materials science facilitated by using diverse data sources

A strategy for machine learning has been developed that exploits the fact that data are often collected in different ways with varying levels of accuracy. The approach was used to build a model that predicts a key property of materials.
  1. Rohit Batra

    1. Rohit Batra is at the Center for Nanoscale Materials, Argonne National Laboratory, Lemont, Illinois 60439, USA.

    View author publications

    You can also search for this author in PubMed  Google Scholar

Scientists are always hunting for materials that have superior properties. They therefore continually synthesize, characterize and measure the properties of new materials using a range of experimental techniques. Computational modelling is also used to estimate the properties of materials. However, there is usually a trade-off between the cost of the experiments (or simulations) and the accuracy of the measurements (or estimates), which has limited the number of materials that can be tested rigorously. Writing in Nature Computational Science, Chen et al.1 report a machine-learning approach that combines data from multiple sources of measurements and simulations, all of which have different levels of approximation, to learn and predict materials’ properties. Their method allows the construction of a more general and accurate model of such properties than was previously possible, thereby facilitating the screening of promising material candidates.

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 589, 524-525 (2021)

doi: https://doi.org/10.1038/d41586-020-03259-4

References

  1. Chen, C., Zuo, Y., Ye, W., Li, X. & Ong, S. P. Nature Comput. Sci. 1, 46–53 (2021).

    Article  Google Scholar 

  2. Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O. & Walsh, A. Nature 559, 547–555 (2018).

    Article  PubMed  Google Scholar 

  3. Ramprasad, R., Batra, R., Pilania, G., Mannodi-Kanakkithodi, A. & Kim, C. npj Comput. Mater. 3, 54 (2017).

    Article  Google Scholar 

  4. Stanev, V. et al. npj Comput. Mater. 4, 29 (2018).

    Article  Google Scholar 

  5. Sendek, A. D. et al. Chem. Mater. 31, 342–352 (2019).

    Article  Google Scholar 

  6. Mannodi-Kanakkithodi, A. et al. Mater. Today 21, 785–796 (2018).

    Article  Google Scholar 

  7. Huo, H. et al. npj Comput. Mater. 5, 62 (2019).

    Article  Google Scholar 

  8. Chen, C., Ye, W., Zuo, Y., Zheng, C. & Ong, S. P. Chem. Mater. 31, 3564–3572 (2019).

    Article  Google Scholar 

  9. Rohit, B., Pilania, G., Uberuaga, B. P. & Ramprasad, R. ACS Appl. Mater. Interf. 11, 24906–24918 (2019).

    Article  Google Scholar 

  10. Dahl, G. E., Jaitly, N. & Salakhutdinov, R. Preprint at https://arxiv.org/abs/1406.1231 (2014).

Download references

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

Search

Advanced search

Quick links