EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Chirality Detection in Scanning Tunneling Microscopy Data Using Artificial Intelligence

Tim J Seifert iD, Mandy Stritzke, Peer Kasten, Björn Möller, Tim Fingscheidt iD, Markus Etzkorn, Timo de Wolff iD, Uta Schlickum iD

Small Methods · 2024-12 · 8 (12)

DOI: 10.1002/smtd.202400549 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Small Methods, online erschienen am 09.09.2024. Verfasst von Tim J Seifert und 7 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Applied Physics, TU Braunschweig, 38106, Braunschweig, Germany. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Niedersächsisches Ministerium für Wissenschaft und Kultur, Fonds der Chemischen Industrie.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Enantiospecific effects play an uprising role in chemistry and technical applications. Chiral molecular networks formed by self‐assembly processes at surfaces can be imaged by scanning probe microscopy (SPM). Low contrast and high noise in the topography map often interfere with the automatic image analysis using classical methods. The long SPM image acquisition times restrain Artificial Intelligence‐based methods requiring large training sets, leaving only tedious manual work, inducing human‐dependent errors and biased labeling. By generating realistic looking synthetic images, the acquisition of real datasets is avoided. Two state‐of‐the‐art object detection architectures are trained to localize and classify chiral unit‐cells in a regular molecular chiral network formed by self‐assembly of linear molecular bricks. The comparison of different architectures and datasets demonstrates that the training on purely synthetic data outperforms models trained using augmented datasets. A Faster R‐CNN model trained solely on synthetic data achieved an excellent mean average precision of 99% on real data. Hence this approach and the transfer to real data show high success, also highlighting the high robustness against experimental noise and different zoom levels across the full experimentally reasonable parameter range. The generalizability of this idea is demonstrated by achieving equally high performance on a different structure, too.

Schlagwörter

Stichwörter der Autor:innen

chiral networksmachine learningmolecular self‐assemblyobject detectionscanning probe microscopysynthetic training data

Autor:innen und Institutionen

  • Institute of Applied Physics, TU Braunschweig, 38106, Braunschweig, Germany.
  • Institute of Analysis and Algebra, TU Braunschweig, 38106, Braunschweig, Germany.
  • Institute for Communications Technology, TU Braunschweig, 38106, Braunschweig, Germany.
  • Laboratory for Emerging Nanometrology, TU Braunschweig, 38106, Braunschweig, Germany.

ORCID-Profile: Tim J Seifert, Tim Fingscheidt, Timo de Wolff, Uta Schlickum

Förderung

  • Niedersächsisches Ministerium für Wissenschaft und Kultur
  • Fonds der Chemischen Industrie

Zitieren

APA

Seifert, T. J., Stritzke, M., Kasten, P., Möller, B., Fingscheidt, T., Etzkorn, M., de Wolff, T., & Schlickum, U. (2024). Chirality Detection in Scanning Tunneling Microscopy Data Using Artificial Intelligence. Small Methods, 8(12). https://doi.org/10.1002/smtd.202400549

Vancouver

Seifert TJ, Stritzke M, Kasten P, Möller B, Fingscheidt T, Etzkorn M, et al. Chirality Detection in Scanning Tunneling Microscopy Data Using Artificial Intelligence. Small Methods. 2024;8(12). doi:10.1002/smtd.202400549

BibTeX
@article{Seifert2024,
  author = {Seifert, Tim J and Stritzke, Mandy and Kasten, Peer and Möller, Björn and Fingscheidt, Tim and Etzkorn, Markus and de Wolff, Timo and Schlickum, Uta},
  title = {Chirality Detection in Scanning Tunneling Microscopy Data Using Artificial Intelligence},
  journal = {Small Methods},
  year = {2024},
  volume = {8},
  number = {12},
  doi = {10.1002/smtd.202400549}
}
Kostenlos starten →