EUVIMEDEUVIMED entdecken
Crossref

A generative model for the bidirectional design of quantum wells in semiconductor lasers using diffusion model

Bo Yuan, Xuanlan Wang, Liqing Wu, Jie Chai, Shuai Li, Yue Song, Jian Xin, Zhijun Zhang, Xingping Zhou, Nianqiang Li, Yuechun Shi

Physica Scripta · 17.07.2026 · 101 (28) · 286002

DOI: 10.1088/1402-4896/ae83eb ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physica Scripta, online erschienen am 15.07.2026. Verfasst von Bo Yuan und 10 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Gefördert von: Key R&D Program of Zhejiang, Ningbo Natural Science Foundation Youth Doctoral Innovation Research Project, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The traditional design of quantum wells (QWs) requires the coupled solution of structural, electronic and optical parameters, making brute-force simulation-based screening costly and limiting rapid iteration during device design. In this paper, a conditional diffusion approach is introduced to generate QW band-gain signatures directly from structural parameters. Based on a fine-tuned Stable Diffusion model, a design generative model of QWs with a physics-constrained hybrid loss function is achieved. A contrastive language-image pre-training module is further applied as an image-to-parameter retrieval component. Compared with a classical generative adversarial network and an unfine-tuned diffusion model, the fine-tuned diffusion model achieves higher image-level fidelity and lower PL-wavelength error on held-out QW designs. The physical simulator, dataset construction, split protocol and computational cost are reported to define the evaluation conditions. The results suggest that the framework is best interpreted as a fast surrogate for screening and visualization within the sampled design domain, rather than as a replacement for the underlying physics solver.

Förderung

  • Key R&D Program of Zhejiang
  • Ningbo Natural Science Foundation Youth Doctoral Innovation Research Project
  • National Natural Science Foundation of China

Zitieren

APA

Yuan, B., Wang, X., Wu, L., Chai, J., Li, S., Song, Y., Xin, J., Zhang, Z., Zhou, X., Li, N., & Shi, Y. (2026). A generative model for the bidirectional design of quantum wells in semiconductor lasers using diffusion model. Physica Scripta, 101(28), 286002. https://doi.org/10.1088/1402-4896/ae83eb

Vancouver

Yuan B, Wang X, Wu L, Chai J, Li S, Song Y, et al. A generative model for the bidirectional design of quantum wells in semiconductor lasers using diffusion model. Physica Scripta. 2026;101(28):286002. doi:10.1088/1402-4896/ae83eb

BibTeX
@article{Yuan2026,
  author = {Yuan, Bo and Wang, Xuanlan and Wu, Liqing and Chai, Jie and Li, Shuai and Song, Yue and Xin, Jian and Zhang, Zhijun and Zhou, Xingping and Li, Nianqiang and Shi, Yuechun},
  title = {A generative model for the bidirectional design of quantum wells in semiconductor lasers using diffusion model},
  journal = {Physica Scripta},
  year = {2026},
  volume = {101},
  number = {28},
  pages = {286002},
  doi = {10.1088/1402-4896/ae83eb}
}
Kostenlos starten →