[1] [1] GUEYE I, DIOP I, DIOUM I, et al. Cooperative systems in optical wireless communication: a survey[J]. Journal of Theoretical and Applied Information Technology, 2020, 98(11): 1901-1916.

[2] [2] KASHANI M A, UYSAL M, KAVEHRAD M. A novel statistical channel model for turbulence-induced fading in free-space optical systems[J]. Journal of Lightwave Technology, 2015, 33(11): 2303-2312.

[3] [3] SANDALIDIS H G, TSIFTSIS T A, KARAGIANNIDIS G K, et al. BER performance of FSO links over strong atmospheric turbulence channels with pointing errors[J]. IEEE Communications Letters, 2008, 12(1): 44-46.

[4] [4] PEPPAS K P, LAZARAKIS F, ALEXANDRIDIS A, et al. Simple, accurate formula for the average bit error probability of multiple-input multiple-output free-space optical links over negative exponential turbulence channels[J]. Optics Letters, 2012, 37(15): 3243-3245.

[5] [5] ODEYEMI K O, OWOLAWI P A, SRIVASTAVA V M. Performance analysis of free space optical system with spatial modulation and diversity combiners over the Gamma Gamma atmospheric turbulence[J]. Optics Communications, 2017, 382: 205-211.

[6] [6] ZENG Y, NG T S. A semi-blind channel estimation method for multiuser multiantenna OFDM systems [J]. IEEE Transactions on Signal Processing, 2004, 52(5): 1419-1429.

[8] [8] DARWESH L, ARNON S. Deep learning for free space optics in a data center environment[C]//Laser Communication and Propagation Through the Atmosphere and Oceans VII. September 18, 2018, San Diego, United States. Washington: SPIE, 2018: 24-32.

[9] [9] AMIRABADI M A, KAHAEI M H, NEZAMALHOSSEINI S A, et al. Deep learning for channel estimation in FSO communication system[J]. Optics Communications, 2020, 459: 1-7.

[10] [10] CHEN W, ZHANG M, WANG D, et al. Deep learning-based channel modeling for free space optical communications [J]. Journal of Lightwave Technology, 2022, 41(1): 183-198.

[11] [11] NDIAYE P, SOW A, DIOP M, et al. Free space optical channel estimation based on deep learning algorithms[C]//2023 International Workshop on Fiber Optics on Access Networks(FOAN), October 30-31, 2023, Gent, Belgium. Piscataway: IEEE, 2023: 27-31.

[12] [12] ELFIKKY A, REZKI Z. Symbol detection and channel estimation for space optical communications using neural network and autoencoder [J]. IEEE Transactions on Machine Learning in Communications and Networking, 2024, 2: 110-128.

[13] [13] CHEN D, WANG R, WANG C, et al. Joint estimation model for FSO channel parameters and performance evaluation based on CNNs[J]. Applied Optics, 2024, 63(9): 2156-2166.

[14] [14] MISHRA P, SONALI, DIXIT A, et al. Machine learning techniques for channel estimation in free space optical communication systems[C]//2019 IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), December 16-19, 2019, Goa, India. Piscataway: IEEE, 2019: 1-6.

[15] [15] AVETA F, REFAI H H, LOPRESTI P G. Cognitive multi-point free space optical communication: real-time users discovery using unsupervised machine learning[J]. IEEE Access, 2020, 8: 207575-207588.

[16] [16] AVETA F, ALGEDIR A, REFAI H. Quality of transmission estimation for multi-user free space optical communication using supervised machine learning[C]//2021 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW), June 21-23, 2021, Cleveland, USA. Piscataway: IEEE, 2021: 1-5.

[17] [17] LIONIS A, PEPPAS K, NISTAZAKIS H E, et al. Using machine learning algorithms for accurate received optical power prediction of an FSO link over a maritime environment[J]. Photonics, 2021, 8(6): 1-17.

[18] [18] KAUR S, KAUR J, SHARMA A. Predicting the performance of radio over free space optics system using machine learning techniques[J]. Optik, 2023, 281: 1-17.