EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Discovering Process Dynamics for Scalable Perovskite Solar Cell Manufacturing with Explainable AI

Lukas Klein, Sebastian Ziegler iD, Felix Laufer iD, Charlotte Debus iD, Markus Götz iD, Klaus Maier-Hein iD, Ulrich W Paetzold iD, Fabian Isensee iD, Paul F Jäger

Advanced Materials · 2024-02 · 36 (7)

DOI: 10.1002/adma.202307160 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Materials, online erschienen am 07.12.2023. Verfasst von Lukas Klein und 8 weiteren Autor:innen. Beteiligte Einrichtung: Interactive Machine Learning Group, German Cancer Research Center, 69120, Heidelberg, Germany. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Helmholtz Association, German Federal Ministry of Education and Research, Karlsruhe School of Optics and Photonics.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large‐area processing of perovskite semiconductor thin‐films is complex and evokes unexplained variance in quality, posing a major hurdle for the commercialization of perovskite photovoltaics. Advances in scalable fabrication processes are currently limited to gradual and arbitrary trial‐and‐error procedures. While the in situ acquisition of photoluminescence (PL) videos has the potential to reveal important variations in the thin‐film formation process, the high dimensionality of the data quickly surpasses the limits of human analysis. In response, this study leverages deep learning (DL) and explainable artificial intelligence (XAI) to discover relationships between sensor information acquired during the perovskite thin‐film formation process and the resulting solar cell performance indicators, while rendering these relationships humanly understandable. The study further shows how gained insights can be distilled into actionable recommendations for perovskite thin‐film processing, advancing toward industrial‐scale solar cell manufacturing. This study demonstrates that XAI methods will play a critical role in accelerating energy materials science.

Schlagwörter

Stichwörter der Autor:innen

deep learningenergy materials scienceexplainable artificial intelligence (XAI)knowledge discoveryperovskite solar cells

Autor:innen und Institutionen

  • Interactive Machine Learning Group, German Cancer Research Center, 69120, Heidelberg, Germany.
  • Institute for Machine Learning, ETH Zürich, Zürich, 8092, Switzerland.
  • Helmholtz Imaging, German Cancer Research Center, 69120, Heidelberg, Germany.
  • Division of Medical Image Computing, German Cancer Research Center, 69120, Heidelberg, Germany.
  • Light Technology Institute, Karlsruhe Institute of Technology, 76131, Karlsruhe, Germany.
  • Steinbuch Centre for Computing, Karlsruhe Institute of Technology, 76344, Eggenstein-Leopoldshafen, Germany.

ORCID-Profile: Sebastian Ziegler, Felix Laufer, Charlotte Debus, Markus Götz, Klaus Maier-Hein, Ulrich W Paetzold, Fabian Isensee

Förderung

  • Helmholtz Association
  • German Federal Ministry of Education and Research
  • Karlsruhe School of Optics and Photonics

Zitieren

APA

Klein, L., Ziegler, S., Laufer, F., Debus, C., Götz, M., Maier-Hein, K., Paetzold, U. W., Isensee, F., & Jäger, P. F. (2024). Discovering Process Dynamics for Scalable Perovskite Solar Cell Manufacturing with Explainable AI. Advanced Materials, 36(7). https://doi.org/10.1002/adma.202307160

Vancouver

Klein L, Ziegler S, Laufer F, Debus C, Götz M, Maier-Hein K, et al. Discovering Process Dynamics for Scalable Perovskite Solar Cell Manufacturing with Explainable AI. Advanced Materials. 2024;36(7). doi:10.1002/adma.202307160

BibTeX
@article{Klein2024,
  author = {Klein, Lukas and Ziegler, Sebastian and Laufer, Felix and Debus, Charlotte and Götz, Markus and Maier-Hein, Klaus and Paetzold, Ulrich W and Isensee, Fabian and Jäger, Paul F},
  title = {Discovering Process Dynamics for Scalable Perovskite Solar Cell Manufacturing with Explainable AI},
  journal = {Advanced Materials},
  year = {2024},
  volume = {36},
  number = {7},
  doi = {10.1002/adma.202307160}
}
Kostenlos starten →