Diffusion Model Enabled Data-Physics Hybrid Waveform Modeling for Experimental Optical Transmission System
Journal of Lightwave Technology · 2026-08 · 44 (15) · 6541-6558
DOI: 10.1109/jlt.2026.3698936 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Lightwave Technology, 2026-08. Verfasst von Minghui Shi und 7 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China, Shanghai Jiao Tong University 2030 Initiative.
Abstract (Originalsprache)
Waveform-level modeling of optical transmission systems serves as a pivotal tool for characterizing system properties, enabling cost-effective system design and optimization. However, conventional physics-based methods, such as the split-step Fourier method (SSFM), suffer from high computational complexity and exhibit performance discrepancies when compared with experimental systems due to parameter mismatches. Meanwhile, although purely data-driven neural network (NN) approaches are widely employed in simulations, they often lack rigorous validation within real-world experimental setups. To address these challenges, this paper proposes a diffusion model-enabled data-physics hybrid framework to achieve accurate and generalizable modeling of optical transmission systems. By leveraging the inherent iterative denoising process of diffusion models, the proposed method effectively characterizes system noise distributions. Compared to traditional generative adversarial networks (GANs), it demonstrates superior training stability and enhanced generalization capabilities. The effectiveness of the proposed model is experimentally validated over a 40-channel, 60 GBaud, 1600 km full C-band transmission system. Experimental results indicate that the diffusion model exhibits consistently higher stability and accuracy across multiple training trials than the GAN-based baseline. In generalization tests across varying launch powers and transmission distances, the diffusion model achieves average Q-factor errors of merely 0.06 dB and 0.09 dB. These results correspond to error reductions of 50% and 78%, respectively, compared to the GAN baseline. Furthermore, the model demonstrates exceptional cross-modulation format generalization, enabling it to be trained on a single modulation format and directly applied to others. Leveraging this framework, we successfully achieve efficient transmission performance prediction, modulation format selection, and parameter optimization for nonlinear compensation (NLC) algorithms within our experimental platform. Ultimately, this proposed framework holds promise for lowering the barrier to experimental validation and expediting the intelligent evolution of next-generation optical networks.
Förderung
- National Key R&D Program of China
- National Natural Science Foundation of China
- Shanghai Jiao Tong University 2030 Initiative
Zitieren
APA
Shi, M., Niu, Z., Xiao, J., Li, L., Jiang, N., Chen, M., Hu, W., & Yi, L. (2026). Diffusion Model Enabled Data-Physics Hybrid Waveform Modeling for Experimental Optical Transmission System. Journal of Lightwave Technology, 44(15), 6541-6558. https://doi.org/10.1109/jlt.2026.3698936
Vancouver
Shi M, Niu Z, Xiao J, Li L, Jiang N, Chen M, et al. Diffusion Model Enabled Data-Physics Hybrid Waveform Modeling for Experimental Optical Transmission System. Journal of Lightwave Technology. 2026;44(15):6541-6558. doi:10.1109/jlt.2026.3698936
BibTeX
@article{Shi2026,
author = {Shi, Minghui and Niu, Zekun and Xiao, Junzhe and Li, Lyu and Jiang, Nianheng and Chen, Mingzhe and Hu, Weisheng and Yi, Lilin},
title = {Diffusion Model Enabled Data-Physics Hybrid Waveform Modeling for Experimental Optical Transmission System},
journal = {Journal of Lightwave Technology},
year = {2026},
volume = {44},
number = {15},
pages = {6541--6558},
doi = {10.1109/jlt.2026.3698936}
}
EUVIMED