EUVIMEDEUVIMED entdecken
Crossref

Active Learning For Tractable and Reproducible Pulsed Laser Deposition

Jackson S. Bentley, Christopher Rouleau, Ilia N. Ivanov, T. Zac Ward, Jiaqiang Yan, Anghea Dolisca, Rob G. Moore, Gyula Eres, Richard F. Haglund, Sumner B. Harris, Matthew Brahlek

Advanced Functional Materials · 2026-11 · 36 (90)

DOI: 10.1002/adfm.78266 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Functional Materials, online erschienen am 29.09.2026. Verfasst von Jackson S. Bentley und 10 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: U.S. Department of Energy.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper shows how data‐driven machine learning approaches can improve growth control, reproducibility, and physical insight in the pulsed laser deposition (PLD) growth of correlated oxides. Despite well‐known relationships between growth conditions and material properties, consistently producing high‐quality films of complex materials like remains difficult due to the highly non‐equilibrium nature of PLD and the defects and competing phases that accumulate during growth. Here, we use an active learning framework based on Gaussian process Bayesian optimization that incorporates measured bulk and surface lattice properties along with impurity phase information to efficiently map the multidimensional growth space of by PLD. By tuning the relative weighting of these properties, the model identifies an optimized region where phase‐pure films of exhibit two‐dimensional surfaces, near‐ideal lattice parameters, and minimal sub‐bandgap optical absorption. The trained model reveals clear competition among different defect formation mechanisms that are connected to unseen parameters like supersaturation and surface mobility, thus giving insight into the highly non‐equilibrium process of PLD growth. Together, this demonstrates that property‐guided machine learning can accelerate materials optimization while providing a new way to address fundamental growth mechanisms in PLD that enable understanding and utilization of quantum phenomena found in complex oxides.

Förderung

  • U.S. Department of Energy

Zitieren

APA

Bentley, J. S., Rouleau, C., Ivanov, I. N., Ward, T. Z., Yan, J., Dolisca, A., Moore, R. G., Eres, G., Haglund, R. F., Harris, S. B., & Brahlek, M. (2026). Active Learning For Tractable and Reproducible Pulsed Laser Deposition. Advanced Functional Materials, 36(90). https://doi.org/10.1002/adfm.78266

Vancouver

Bentley JS, Rouleau C, Ivanov IN, Ward TZ, Yan J, Dolisca A, et al. Active Learning For Tractable and Reproducible Pulsed Laser Deposition. Advanced Functional Materials. 2026;36(90). doi:10.1002/adfm.78266

BibTeX
@article{Bentley2026,
  author = {Bentley, Jackson S. and Rouleau, Christopher and Ivanov, Ilia N. and Ward, T. Zac and Yan, Jiaqiang and Dolisca, Anghea and Moore, Rob G. and Eres, Gyula and Haglund, Richard F. and Harris, Sumner B. and Brahlek, Matthew},
  title = {Active Learning For Tractable and Reproducible Pulsed Laser Deposition},
  journal = {Advanced Functional Materials},
  year = {2026},
  volume = {36},
  number = {90},
  doi = {10.1002/adfm.78266}
}
Kostenlos starten →