Chirality Detection in Scanning Tunneling Microscopy Data Using Artificial Intelligence
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.
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
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}
}
EUVIMED