On the use of advanced scanning transmission electron microscopy and machine learning for studying multi-component materials.

Journal: Faraday discussions
Published Date: Feb 24, 2026

Abstract

The nanoscale distribution of elements in two multi-component materials is assessed by unsupervised machine learning methods. These are compared to elemental maps to highlight the potential shortcomings of simplistic compositional analyses. Quantification of the resulting microstructure components provides insight into the evolution of the microstructure and the possible reasons for misinterpretation of the traditional element maps.

Authors

  • Alexander S Eggeman
    Department of Materials, University of Manchester, M13 9PL, UK. [email protected].
  • Christian Maddox
    Department of Materials, University of Manchester, M13 9PL, UK. [email protected].
  • Mark A Buckingham
    Department of Materials, University of Manchester, M13 9PL, UK. [email protected].
  • Zhiquan Kho
    Department of Materials, University of Manchester, M13 9PL, UK. [email protected].
  • Ran Eitan Abutbul
    Department of Chemical Engineering, University of Manchester, M13 9PL, UK.
  • Siguang Meng
    Department of Materials, University of Manchester, M13 9PL, UK. [email protected].
  • Xu Aiwanshu
    Department of Materials, University of Manchester, M13 9PL, UK. [email protected].
  • David J Lewis
    Department of Pharmacy, Pharmacology and Postgraduate Medicine, University of Hertfordshire, Hertfordshire, UK.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals