EUVIMEDEUVIMED entdecken
Crossref

Few-shot learning-based rapid spatiotemporal wavefront prediction with a lightweight Fourier graph neural network in adaptive optics

Ju Tang, Jiayong Chen, Zhijian Qin, Haocheng Feng, Jiazhen Dou, Zhenbo Ren, Jianglei Di, Yuwen Qin

Photonics Research · 01.07.2026 · 14 (7) · 2862

DOI: 10.1364/prj.586204 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Photonics Research, online erschienen am 16.06.2026. Verfasst von Ju Tang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 29 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Introducing Innovative and Entrepreneurial Teams of “The Pearl River Talent Recruitment Program”, Guangdong Basic and Applied Basic Research Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Adaptive optics (AO) systems hold significant application values, but are fundamentally limited by the inherent time delay challenge between wavefront sensing and correction. Prediction algorithms have emerged to infer future wavefront evolution, thereby enabling predictive AO. However, existing algorithms often face trade-offs among accuracy, data efficiency, generalization capacity, and response bandwidth. To address these limitations, here we propose, to our knowledge, a novel few-shot learning framework for spatiotemporal wavefront prediction, termed the Fourier graph neural network (FGNN). FGNN uniquely enables accurate forecasting of wavefront evolution using only few-shot wavefront frames. It also exhibits strong robustness under varying turbulence conditions, including changes in wind speed, Fried parameter, and wavefront sensor frequency. Among all comparative algorithms, FGNN possesses the lowest parameter count, the minimum computational complexity, and the shortest response time of 0.121 ms. It reduces the residual wavefront error by up to 70% and improves the peak intensity of the focused spot by ∼30 % in an experimental open-loop AO setup. By providing a data-efficient and computationally lightweight solution, FGNN serves as a powerful tool for advanced AO technology in specific scenarios, with significant potential for applications in astronomical observation and laser communications.

Förderung

  • National Natural Science Foundation of China
  • Guangdong Introducing Innovative and Entrepreneurial Teams of “The Pearl River Talent Recruitment Program”
  • Guangdong Basic and Applied Basic Research Foundation

Zitieren

APA

Tang, J., Chen, J., Qin, Z., Feng, H., Dou, J., Ren, Z., Di, J., & Qin, Y. (2026). Few-shot learning-based rapid spatiotemporal wavefront prediction with a lightweight Fourier graph neural network in adaptive optics. Photonics Research, 14(7), 2862. https://doi.org/10.1364/prj.586204

Vancouver

Tang J, Chen J, Qin Z, Feng H, Dou J, Ren Z, et al. Few-shot learning-based rapid spatiotemporal wavefront prediction with a lightweight Fourier graph neural network in adaptive optics. Photonics Research. 2026;14(7):2862. doi:10.1364/prj.586204

BibTeX
@article{Tang2026,
  author = {Tang, Ju and Chen, Jiayong and Qin, Zhijian and Feng, Haocheng and Dou, Jiazhen and Ren, Zhenbo and Di, Jianglei and Qin, Yuwen},
  title = {Few-shot learning-based rapid spatiotemporal wavefront prediction with a lightweight Fourier graph neural network in adaptive optics},
  journal = {Photonics Research},
  year = {2026},
  volume = {14},
  number = {7},
  pages = {2862},
  doi = {10.1364/prj.586204}
}
Kostenlos starten →