Abstract
Beams carrying orbital angular momentum (OAM) have attracted considerable interest in high-capacity optical communication owing to their infinite-dimensional state space. Conventional methods for detecting OAM modes face significant limitations, including bulky systems, slow response times, and restricted detection ranges. Although deep learning algorithm have shown promise in mitigating some of these challenges, the characterization of mode distributions within mixed-mode OAM beams has received limited attention. We propose an all-optical, end-to-end approach for decomposing mixed-mode OAM beams and estimating their mode weights using diffractive deep neural network (D2NN). The network directly maps the incident optical field to outputs that both identify the constituent OAM modes and estimate their relative contributions. Numerical simulations demonstrate that the method can accurately recover the weights of up to 21 hybrid modes. Moreover, it maintains strong robustness under atmospheric perturbations, with the relative error remaining below 7%. This approach enables precise and efficient reconstruction of the OAM beams across varying numbers of modes, offering broad potential in multidimensional information encoding, quantum information processing, and optical computing.
Keywords
diffractive optical neural networks; orbital angular momentum; mixed-mode decomposition; mode-weight estimation
Acknowledgements
This research was supported by National Key Research and Development Program of China (No. 2021YFA1401003), and the National Natural Science Foundation of China (Nos. 62305345, U24A6010, 62222513).
Author contributions
L.-X.G. supervised the whole project. W.-L.J. performed the theoretical calculations and validation. W.-L.J. and W.-J.D. completed the initial structure and network construction. W.-L.J. and W.-J.D. contributed to the results analysis and data processing. W.-L.J. contributed to the data interpretation. W.-J.D. wrote the initial manuscript. W.-L.J., W.-J.D., H.-Y.L., and G.-Y.H. revised and edited the manuscript. All authors contributed to the discussions and preparation of the manuscript.
Competing interests
Xiangang Luo serves as an Editor for the Journal, and no other author has reported any competing interests.
References
[1] Al Ibrahim RH, Zheng SQ, Ng TK et al. Optical image rotation based on orbital angular momentum decomposition and combination. J Opt 24, 115605 (2022). DOI: 10.1088/2040-8986/ac8a02
[2] Li MM, Yan SH, Zhang YN et al. Orbital angular momentum in optical manipulations. J Opt 24, 114001 (2022). DOI: 10.1088/2040-8986/ac9192
[3] Andersen MF, Ryu C, Cladé P et al. Quantized rotation of atoms from photons with orbital angular momentum. Phys Rev Lett 97, 170406 (2006). DOI: 10.1103/PhysRevLett.97.170406
[4] Orlov S, Stanaitis K, Kizevičius P et al. Single-pixel terahertz imaging with enhanced edge detection using angular momentum of structured light. APL Photonics 10, 050805 (2025). DOI: 10.1063/5.0255550
[5] Li N, Zheng SL, He T et al. Metasurface-based dual-mode bright-field and spiral phase contrast THz imaging with enhanced focal depth. J Lightwave Technol 43, 4322–4330 (2025). DOI: 10.1109/JLT.2024.3521973
[6] Wang JK, Zhang WH, Qi QQ et al. Gradual edge enhancement in spiral phase contrast imaging with fractional vortex filters. Sci Rep 5, 15826 (2015). DOI: 10.1038/srep15826
Copyright
Open Access. © The Author(s). This article is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/.
Cite this Article
Wang LJ, Wang JD, Ha YL et al. Decomposition and mode-weight estimation of mixed-mode OAM beams via diffractive neural networks. Intell Opto-Electron 2, 250011 (2026).
