Abstract
A novel mode decomposition method for multimode fiber (MMF) is proposed by using a hybrid network, which combined deep-learning convolutional neural network (DL-CNN) with iterative gradient ascent algorithm (IGAA). DL-CNN is used as the global search for the rough modal amplitudes and relative phases. IGAA is designed as the local optimization to obtain the accurate values of modal decomposition. Although a mini-datasets are employed, the hybrid network shows very good accuracy of modal decomposition and fast convergence. For all of 3-, 5-, 6-, 8-, 10-mode cases, correlation coefficient of the reconstructed and the true near-field intensity patterns can be optimized to higher than 0.98.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References:
An, Yi., Huang, L., Li, J., Leng, J., Yang, L., Zhou, Pu.: Learning to decompose the modes in few-mode fibers with deep convolutional neural network. Opt. Express 27(7), 10127–10137 (2019)
Gao, H., Haifeng, Hu., Zhao, Y., Li, J.: A real-time fiber mode demodulation method enhanced by convolution neural network. Opt. Fiber Technol. Fiber Technol. 50, 139–144 (2019)
He, K., Zhang, X., Ren, S.: Deep residual learning for image recognition. In: IEEE conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Huang, L., Guo, S., Leng, J., LüZhou, HPu., Cheng, X.: Real-time mode decomposition for few-mode fiber based on numerical method. Opt. Express 23(4), 4620–4629 (2015)
Jiang, M., An, Yi., Rongtao, Su., Huang, L., Li, J., Ma, P., Zhou, Pu., Ma, Y.: Deep mode decomposition: real-time mode decomposition of multimode fibers based on unsupervised learning. IEEE J. Sel. Top. Quantum Electron. 28(4), 0900207 (2022)
Kaiser, T., Flamm, D., Schröter, S., Duparre, M.: Complete modal decomposition for optical fibers using CGH-based correlation filters. Opt. Express 17(11), 9347–9356 (2009)
Kim, B., Na, J., Kim, J., Kim, H., Jenong, Y.: Modal decomposition of fiber modes based on direct far-field measurements at two different distances with a multi-variable optimization algorithm. Opt. Express 29(13), 21502–21520 (2021)
Kim, B., Na, J., Jenong, Y.: Convolutional neural network combined with stochastic parallel gradient descent to decompose fiber modes based on far-field measurements. J. Lightwave Technol. 41(18), 5973–5982 (2023)
Liu, A., Lin, T., Han, H., Zhang, X., Chen, Ze., Gan, F., Lv, H., Liu, X.: Analyzing modal power in multi-mode waveguide via machine learning. Opt. Express 26(17), 22100–22109 (2018)
Lyu, M., Lin, Z., Li, G., Situ, G.: Fast modal decomposition for optical fibers using digital holography. Sci. Rep. 7(1), 6556 (2017)
Manuylovich, E.S., Dvoyrin, V.V., Turitsyn, S.K.: Fast mode decomposition in few-mode fibers. Nat. Commun. 11(1), 5507 (2020)
Manuylovich, E., Donodin, A., Turitsyn, S.: Intensity-only-measurement mode decomposition in few-mode fibers. Opt. Express 29(22), 36769–36783 (2021)
Mengjun, Xu., Hou, M., Luo, X., Jiangtao, Xu., Chen, W., An, Yi., Zeng, X., Li, J., Huang, L.: Multi-order hybrid vector mode decomposition in few-mode fibers with DL-based SPGD algorithm. Opt. Laser Technol. 167, 109795 (2023)
Nicholson, J.W., Yablon, A.D., Ramachandran, S., Ghalmi, S.: Spatially and spectrally resolved imaging of modal content in large-mode-area fibers. Opt. Express 16(10), 7233–7243 (2008)
Richardson, D., Fini, J., Nelson, L.: Space-division multiplexing in optical fibres. Nat. Photon. 7, 354–362 (2013)
Rothe, S., Zhang, Q., Koukourakis, N., Czarske, J.: Intensity-only mode decomposition on multimode fibers using a densely connected convolutional network. J. Lightwave Technol. 39(6), 1672–1679 (2021)
Shapira, O., Abouraddy, A.F., Joannopoulos, J.D., Fink, Y.: Complete modal decomposition for optical waveguides. Phys. Rev. Lett. 94(14), 143902 (2005)
Snyder, A.W., Love, J.D.: Optical waveguide Theory. Springer (1983)
Tian, Z., Pei, Li., Wang, J., HuXuZheng, K.W.J., Li, J., Ning, T.: High-performance mode decomposition using physics- and data-driven deep learning. Opt. Express 30(22), 39932–39945 (2022)
Yan, W., Xiaojun, Xu., Wang, J.: Mode decomposition for few mode fibers using the fractional Fourier system. Opt. Express 27(10), 13871–13883 (2019)
Yan, B., Zhang, J., Wang, M., Jiang, Y., Mi, S.: Degenerated mode decomposition with convolutional neural network for few-mode fibers. Opt. Laser Technol. 154, 108287 (2022)
Funding
Project is supported by the Beijing Natural Science Foundation (No. 4192022).
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Ethical approval
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Dong, X., Yu, Z. & Su, X. High-accuracy mode decomposition for multi-mode fibers using hybrid network with mini-datasets. Opt Quant Electron 56, 1006 (2024). https://doi.org/10.1007/s11082-024-06945-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11082-024-06945-z