EUVIMEDEUVIMED entdecken
Crossref

Inverse design epsilon-near-zero-based broadband nonreciprocal thermal emitter using hybrid deep learning framework

Jun-Yang Sui, Hai-Feng Zhang

Applied Physics Letters · 30.03.2026 · 128 (13)

DOI: 10.1063/5.0323320 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Physics Letters, online erschienen am 30.03.2026. Verfasst von Jun-Yang Sui und 1 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: Open Research Program in China's State Key Laboratory of Millimeter Waves', Postgraduate Research and Practice Innvation Program of Jiangsu Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Nonreciprocal thermal radiation, which breaks Kirchhoff's law by decoupling absorptivity and emissivity, is essential for advanced radiative heat transfer control. However, achieving broadband and tunable nonreciprocal thermal radiation with high design efficiency remains a challenge. This study proposes a novel hybrid deep learning framework, integrating the Artificial Rabbit Optimization and tandem neural network, to inversely design multilayer films (MLFs) based on magnetized gradient epsilon-near-zero (ENZ) InAs layers. By using the Artificial Rabbit Optimization algorithm, we collect a high-quality dataset with a noise ratio of only 3.2%, significantly reducing computational overhead compared to random sampling. The multitasking tandem neural network converges to a low cost function of 0.086, improving the accuracy and avoiding the scattering problem faced by traditional neural networks. Results show that significant nonreciprocal thermal radiation (nonreciprocity > 0.637 and peak 0.723) is achieved in the 14–19 μm range by exploiting the magneto-optical effects of InAs and ENZ-induced Brewster modes. Furthermore, the MLFs exhibit reversed absorptivity and emissivity spectra under reversed magnetic fields. These findings provide a data-efficient and scalable solution for dynamic thermal management and infrared camouflage, demonstrating the powerful synergy between deep learning and nonreciprocal photonics.

Förderung

  • Open Research Program in China's State Key Laboratory of Millimeter Waves'
  • Postgraduate Research and Practice Innvation Program of Jiangsu Province

Zitieren

APA

Sui, J., & Zhang, H. (2026). Inverse design epsilon-near-zero-based broadband nonreciprocal thermal emitter using hybrid deep learning framework. Applied Physics Letters, 128(13). https://doi.org/10.1063/5.0323320

Vancouver

Sui J, Zhang H. Inverse design epsilon-near-zero-based broadband nonreciprocal thermal emitter using hybrid deep learning framework. Applied Physics Letters. 2026;128(13). doi:10.1063/5.0323320

BibTeX
@article{Sui2026,
  author = {Sui, Jun-Yang and Zhang, Hai-Feng},
  title = {Inverse design epsilon-near-zero-based broadband nonreciprocal thermal emitter using hybrid deep learning framework},
  journal = {Applied Physics Letters},
  year = {2026},
  volume = {128},
  number = {13},
  doi = {10.1063/5.0323320}
}
Kostenlos starten →