Physics-guided source selection for few-shot transfer learning to characterise bismuth-doped fiber amplifier
Authors:
- Yuhang HuangYHYuhang Huang
- Ben MillsBMBen Mills
- Jess FerrissJFJess Ferriss
- Zahra KakaeiZKZahra Kakaei
- Qiubai YangQYQiubai Yang
- Nilopal ChoudhuryNCNilopal Choudhury
- James A. Grant-JacobJGJames A. Grant-Jacob
- Michalis N. ZervasMZMichalis N. Zervas
- Jayanta SahuJSJayanta Sahu
Open Access
- 5 November 2026
- journal article
- Published by Optica Publishing Group in Optics Express
- Vol. 34 (23) , 43816
Abstract
Bismuth-doped fiber amplifiers (BDFAs) can extend optical amplification beyond the C + L bands into the low-loss window of silica fibers, but each additional fiber normally requires extensive gain and noise-figure characterisation. Here, we demonstrate physics-guided source selection for few-shot transfer learning in Bi/Ge co-doped BDFAs. Four fibers spanning 5.4–22.9 mol% GeO 2 were characterised over 480 operating points each. Across 12 directed transfer-learning pairs, a two-descriptor feature distance based on GeCl 4 flow during fiber preform fabrication and 1385-nm absorption predicted transfer benefit. Selecting the physically matched source reduced the target-data requirement by up to 7x, and prospective validation on an unseen fifth fiber correctly identified the optimal transfer-learning source. More broadly, these results show that source quality, as captured by simple physical descriptors, can be more important than source-data volume in photonic transfer learning.Keywords
Funding Information
- Engineering and Physical Sciences Research Council (EP/W028786/1)
- Engineering and Physical Sciences Research Council (EP/T026197/1)
- Engineering and Physical Sciences Research Council (EP/Z002567/1)
This publication has 15 references indexed in Scilit:
- Spectroscopic characterization of bismuth active centres in germanosilicate optical fibers: Impact of Ge concentration on E–S band amplifier gainJournal of Luminescence, 2026
- Neural network modeling of bismuth-doped fiber amplifierJournal of the European Optical Society-Rapid Publications, 2023
- Recent advances in Bi-doped silica-based optical fibers: A short reviewJournal of Non-Crystalline Solids: X, 2022
- Fiber-Agnostic Machine Learning-Based Raman Amplifier ModelsJournal of Lightwave Technology, 2022
- Machine learning and applications in ultrafast photonicsNature Photonics, 2020
- The Influence of the MCVD Process Parameters on the Optical Properties of Bismuth-Doped Phosphosilicate FibersJournal of Lightwave Technology, 2020
- A 23-dB bismuth-doped optical fiber amplifier for a 1700-nm bandScientific Reports, 2016
- Bismuth-doped optical fibers: a challenging active medium for near-IR lasers and optical amplifiersLight: Science & Applications, 2012
- CW bismuth fibre laserQuantum Electronics, 2005
- Low-noise erbium-doped fibre amplifier operating at 1.54μmElectronics Letters, 1987