EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Machine Learning-Enabled Image Classification for Automated Electron Microscopy

Alexandra L Day iD, Carolin B Wahl iD, Vishu Gupta, Roberto Dos Reis iD, Wei-Keng Liao, Chad A Mirkin, Vinayak P Dravid iD, Alok Choudhary, Ankit Agrawal iD

Microscopy and Microanalysis · 04.07.2024 · 30 (3) · 456-465

DOI: 10.1093/mam/ozae042 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Microscopy and Microanalysis, online erschienen am 17.05.2024. Verfasst von Alexandra L Day und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, McCormick School of Engineering, Northwestern University, Technological Institute, 2145 Sheridan R…. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Sherman Fairchild Foundation, Toyota Research Institute, Northwestern Center for Nanocombinatorics.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditionally, materials discovery has been driven more by evidence and intuition than by systematic design. However, the advent of “big data” and an exponential increase in computational power have reshaped the landscape. Today, we use simulations, artificial intelligence (AI), and machine learning (ML) to predict materials characteristics, which dramatically accelerates the discovery of novel materials. For instance, combinatorial megalibraries, where millions of distinct nanoparticles are created on a single chip, have spurred the need for automated characterization tools. This paper presents an ML model specifically developed to perform real-time binary classification of grayscale high-angle annular dark-field images of nanoparticles sourced from these megalibraries. Given the high costs associated with downstream processing errors, a primary requirement for our model was to minimize false positives while maintaining efficacy on unseen images. We elaborate on the computational challenges and our solutions, including managing memory constraints, optimizing training time, and utilizing Neural Architecture Search tools. The final model outperformed our expectations, achieving over 95% precision and a weighted F-score of more than 90% on our test data set. This paper discusses the development, challenges, and successful outcomes of this significant advancement in the application of AI and ML to materials discovery.

Schlagwörter

Stichwörter der Autor:innen

automated characterizationcombinatorial megalibrariesmachine learningnanomaterials

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, McCormick School of Engineering, Northwestern University, Technological Institute, 2145 Sheridan Road, Room L359, Evanston, IL 60208, USA.
  • Department of Materials Science and Engineering, McCormick School of Engineering, Northwestern University, Cook Hall, 2220 Campus Drive, Room 2036, Evanston, IL 60208, USA.
  • International Institute for Nanotechnology, Northwestern University, Technological Institute, 2145 Sheridan Road, Room K111, Evanston, IL 60208, USA.
  • The NUANCE Center, Northwestern University, Technological Institute, 2145 Sheridan Road, Room A173, Evanston, IL 60208, USA.
  • Department of Chemistry, Northwestern University, Technological Institute, 2145 Sheridan Road, Room K148, Evanston, IL 60208, USA.

ORCID-Profile: Alexandra L Day, Carolin B Wahl, Roberto Dos Reis, Vinayak P Dravid, Ankit Agrawal

Förderung

  • Sherman Fairchild Foundation
  • Toyota Research Institute
  • Northwestern Center for Nanocombinatorics
  • NIST DOC
  • Department of Energy
  • NSF
  • National Energy Research Scientific Computing Center
  • DOE Office of Science User Facility

Zitieren

APA

Day, A. L., Wahl, C. B., Gupta, V., Dos Reis, R., Liao, W. K., Mirkin, C. A., Dravid, V. P., Choudhary, A., & Agrawal, A. (2024). Machine Learning-Enabled Image Classification for Automated Electron Microscopy. Microscopy and Microanalysis, 30(3), 456-465. https://doi.org/10.1093/mam/ozae042

Vancouver

Day AL, Wahl CB, Gupta V, Dos Reis R, Liao WK, Mirkin CA, et al. Machine Learning-Enabled Image Classification for Automated Electron Microscopy. Microscopy and Microanalysis. 2024;30(3):456-465. doi:10.1093/mam/ozae042

BibTeX
@article{Day2024,
  author = {Day, Alexandra L and Wahl, Carolin B and Gupta, Vishu and Dos Reis, Roberto and Liao, Wei-Keng and Mirkin, Chad A and Dravid, Vinayak P and Choudhary, Alok and Agrawal, Ankit},
  title = {Machine Learning-Enabled Image Classification for Automated Electron Microscopy},
  journal = {Microscopy and Microanalysis},
  year = {2024},
  volume = {30},
  number = {3},
  pages = {456--465},
  doi = {10.1093/mam/ozae042}
}
Kostenlos starten →