Hybrid prediction framework and structural optimization for gap-compensated nested hollow-core anti-resonant fibers
Optics Express · 02.11.2026 · 34 (22) · 42906
DOI: 10.1364/oe.613524 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 30.10.2026. Verfasst von Chenwei Sun und 10 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced …. Die Arbeit nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Project of State Grid Corporation of China, Open Fund of the State Key Laboratory of High-Efficiency Special Cable Technology.
Abstract (Originalsprache)
Hollow-core anti-resonant fibers (HC-ARFs) offer low-loss broadband guidance, but the geometric complexity introduced by gap-compensated cladding tubes poses a challenge to accurate confinement loss (CL) prediction. We develop a cascaded hybrid framework that couples an artificial neural network (ANN) with extreme gradient boosting (XGBoost) for rapid broadband CL prediction. The ANN captures the global nonlinear dependence of CL on fiber geometry and wavelength, whereas XGBoost refines the initial predictions by learning log-space residuals from augmented features combining the original inputs and ANN hidden-layer activations. Compared with the standalone ANN, the resulting hybrid model reduces the mean absolute percentage error by 5.5%. When employed as an efficient surrogate for structural optimization, the model identifies a low-loss design within the investigated geometric parameter ranges, with CL below 0.2 dB/km over 1.1–1.45 μm. Independent finite-element calculations for the selected low-loss structure closely reproduce the predicted spectrum, with an average deviation of 0.0064 dB/km, indicating the broader potential of hybrid machine-learning surrogate models to accelerate design-space exploration and optimization for structurally complex HC-ARFs.
Autor:innen und Institutionen
- Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai University, Shanghai 200444, China.
- State Key Laboratory of High-Efficiency Special Cable Technology, Shanghai 200000, China.
- State Grid Jiangxi Electric Power Co., Ltd., Nanchang 330077, China.
ORCID-Profile: Chengbo Mou, Yunqi Liu, Wei Chen
Förderung
- National Natural Science Foundation of China
- Science and Technology Project of State Grid Corporation of China
- Open Fund of the State Key Laboratory of High-Efficiency Special Cable Technology
- Shandong Province Technology Innovation Guidance Plan
- Open Fund Project of the Key Laboratory of Ocean Observation Technology, Ministry of Natural Resources (MNR)
- Shanghai Qiyuan State-Owned Assets Pioneer Project
- National Key R&D Program of China
- Open Fund of the Laboratory of Science and Technology on Marine Navigation and Control, China State Shipbuilding Corporation
Zitieren
APA
Sun, C., Xiao, Z., Jiang, B., Wang, F., Zhu, Z., Zhang, Y., Liu, J., Tu, J., Mou, C., Liu, Y., & Chen, W. (2026). Hybrid prediction framework and structural optimization for gap-compensated nested hollow-core anti-resonant fibers. Optics Express, 34(22), 42906. https://doi.org/10.1364/oe.613524
Vancouver
Sun C, Xiao Z, Jiang B, Wang F, Zhu Z, Zhang Y, et al. Hybrid prediction framework and structural optimization for gap-compensated nested hollow-core anti-resonant fibers. Optics Express. 2026;34(22):42906. doi:10.1364/oe.613524
BibTeX
@article{Sun2026,
author = {Sun, Chenwei and Xiao, Ziyang and Jiang, Bin and Wang, Fei and Zhu, Zhenghan and Zhang, Yufeng and Liu, Jingping and Tu, Jiankun and Mou, Chengbo and Liu, Yunqi and Chen, Wei},
title = {Hybrid prediction framework and structural optimization for gap-compensated nested hollow-core anti-resonant fibers},
journal = {Optics Express},
year = {2026},
volume = {34},
number = {22},
pages = {42906},
doi = {10.1364/oe.613524}
}
EUVIMED