EUVIMEDEUVIMED entdecken
Crossref

Convolutional neural network approach to ion Coulomb crystal image analysis

James Allsopp iD, Jake Diprose iD, Brianna R Heazlewood iD, Chase Zagorec-Marks iD, H J Lewandowski iD, Lorenzo S Petralia iD, Timothy P Softley iD

The Journal of Chemical Physics · 28.07.2025 · 163 (4)

DOI: 10.1063/5.0272967 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 22.07.2025. Verfasst von James Allsopp und 6 weiteren Autor:innen. Beteiligte Einrichtung: Research Software Group, University of Birmingham, Edgbaston B15 2TT, United Kingdom. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: Leverhulme Trust, HORIZON EUROPE European Research Council, Engineering and Physical Sciences Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper reports on the use of a convolutional neural network methodology to analyze fluorescence images of calcium-ion Coulomb crystals in the gas phase. A transfer-learning approach is adopted using the publicly available RESNET50 model. It is demonstrated that by retraining the neural network on around 500 000 simulated images, we are able to determine ion-numbers not only for a validation set of 100 000 simulated images but also for experimental calcium-ion images from two different laboratories using a wide range of ion-trap parameters. Absolute ion numbers in the crystal were determined for the experimental data with a percentage error of ∼10%. This analysis can be performed in a few seconds for an individual crystal image, and therefore, the method enables the objective, and efficient, analysis of such images in real time. The approach adopted also shows promising performance for identifying Ca+ ion numbers in images of mixed-species crystals, thereby enhancing the experimental methodologies for studying the kinetics and dynamics of cold ion–molecule reactions.

Autor:innen und Institutionen

  • Research Software Group, University of Birmingham, Edgbaston B15 2TT, United Kingdom.
  • Department of Physics, University of Liverpool, Liverpool L69 7ZE, United Kingdom.
  • JILA, National Institute of Standards and Technology and the University of Colorado, Boulder, Colorado 80309, USA.
  • Department of Physics, University of Colorado, Boulder, Colorado 80309, USA.
  • Institute for Breath Research, University of Innsbruck, Innsbruck, Austria.
  • School of Chemistry, University of Birmingham, Edgbaston B15 2TT, United Kingdom.

ORCID-Profile: James Allsopp, Jake Diprose, Brianna R Heazlewood, Chase Zagorec-Marks, H J Lewandowski, Lorenzo S Petralia, Timothy P Softley

Förderung

  • Leverhulme Trust
  • HORIZON EUROPE European Research Council
  • Engineering and Physical Sciences Research Council

Zitieren

APA

Allsopp, J., Diprose, J., Heazlewood, B. R., Zagorec-Marks, C., Lewandowski, H. J., Petralia, L. S., & Softley, T. P. (2025). Convolutional neural network approach to ion Coulomb crystal image analysis. The Journal of Chemical Physics, 163(4). https://doi.org/10.1063/5.0272967

Vancouver

Allsopp J, Diprose J, Heazlewood BR, Zagorec-Marks C, Lewandowski HJ, Petralia LS, et al. Convolutional neural network approach to ion Coulomb crystal image analysis. The Journal of Chemical Physics. 2025;163(4). doi:10.1063/5.0272967

BibTeX
@article{Allsopp2025,
  author = {Allsopp, James and Diprose, Jake and Heazlewood, Brianna R and Zagorec-Marks, Chase and Lewandowski, H J and Petralia, Lorenzo S and Softley, Timothy P},
  title = {Convolutional neural network approach to ion Coulomb crystal image analysis},
  journal = {The Journal of Chemical Physics},
  year = {2025},
  volume = {163},
  number = {4},
  doi = {10.1063/5.0272967}
}
Kostenlos starten →