[1] T A Bonin, A Choukulkar, W A Brewer, et al. Evaluation of turbulence measurement techniques from a single Doppler lidar. Atmospheric Measurement Techniques, 10, 1-26(2017).

[2] M Y T Leung, Wen Zhou, Chiming Shun, et al. Large-scale circulation control of the occurrence of low-level turbulence at Hong Kong international airport. Advances in Atmospheric Sciences, 35, 435-444(2018).

[3] N Wildmann, E Pschke, A Roiger, et al. Towards improved turbulence estimation with Doppler wind lidar velocity-azimuth display (VAD) scans. Atmospheric Measurement Techniques, 13, 4141-4158(2020).

[4] [4] Dyk R V, Pariseau D H, Dodson R E, et al. Systems integration of unmanned aircraft into the national airspace: Part of the federal aviation administration next generation air transptation system[C]IEEE Symposium on Systems Infmation Engineering Design, SIEDS, 2012:125, 34.

[5] [5] ganization I. Meteological Service f International Air Navigation: Annex 3 to the Convention on International Civil Aviation[M]. Chicago: International Civil Aviation ganization, 1998.

[6] P W Chan. Validating the turbulence parameterization schemes of a numerical model using eddy dissipation rate and turbulent kinetic energy measurements in terrain-disrupted airflow. Meteorology & Atmospheric Physics, 108, 95-112(2010).

[7] Lihui Jiang, Zhiguang Gao, Xinglong Xiong, et al. Study on type recognition of low attitude wind shearbased on lidar image processing. Infrared and Laser Engineering, 41, 3410-3415(2012).

[8] Lihui Jiang, Hong Chen, Zibo Zhuang, et al. Recognition on low-level wind shear of wavelet invariant moments. Infrared and Laser Engineering, 43, 3783-3787(2014).

[9] Xiaoqing Chen, Junguo Ma, Qiang Fu, et al. Target recognition using singular value feature for laser imaging radar. Infrared and Laser Engineering, 40, 1801-1805(2011).

[10] Qiwei Xu, Peipei Wang, Zhenjia Zeng, et al. Extracting atmospheric turbulence phase using deep convolutional neural network. Acta Physica Sinica, 69, 286-296(2020).

[11] Zhangli Lan, Heng Kuang, Zhan Li, et al. Study on CNN-based turbulence image degradation intensity classification. Computer Systems & Applications, 28, 199-204(2019).

[12] Xiaoli Yin, Yilin Guo, Xiaozhou Cui, et al. Method of mode recognition for Multi-OAM multiplexing based on convolutional neural network. Journal of Beijing University of Posts and Telecommunications, 42, 47-52(2019).

[13] S Vasudevan. Mutual information based learning rate decay for stochastic gradient descent training of deep neural networks. Entropy, 22, 560(2020).

[14] [14] Keskar N S, Saon G. A nonmonotone learning rate strategy f SGD training of deep neural wks[C] IEEE International Conference on Acoustics. IEEE, 2015.

[15] Jingyi Qu, Wei Zhu, Renbiao Wu. Image classification for dual-channel neural networks based on attenuation factor. Systems Engineering and Electronics, 39, 1391-1399(2017).

[16] F Davies, C G Collier, G N Pearson, et al. Doppler lidar measurements of turbulent structure function over an urban area. Journal of Atmospheric & Oceanic Technology, 21, 753-761(2003).

[17] [17] Zhang Zhaoshun, Cui Guixiang, Xu Chunxiao. They Modeling of Turbulence[M]. Beijing: Tsinghua University Press, 2005. (in Chinese)

[18] G E Hinton, R R Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313, 504-507(2006).

[19] [19] Wu Jiaquan. Research on neural wk based ECG classification algithm energyefficient architecture[D]. Hangzhou: Zhejiang University, 2020. (in Chinese)

[20] Xu Huang, Zhigang Ling, Xiuxin Li. Discriminative deep feature learning method by fusing linear discriminant analysis for image recognition. Journal of Image and Graphics, 23, 510-518(2018).

[21] Chang Luo, Jie Wang, Shiqiang Wang, et al. General deep transfer features based high resolution remote scene classification. Systems Engineering and Electronics, 40, 682-691(2018).