涡旋光具有特殊的螺旋相位因子，使用涡旋光进行通信编码能够极大地提高通信容量。实际通信环境的湍流、雾霾会导致涡旋光发生散射而形成散斑，这使得涡旋光通信的实际应用难度加大。因此，从散斑中准确高效地测量入射涡旋光的拓扑荷数对涡旋光通信具有重大意义。涡旋光经过散射介质之后形成的散斑场的特性与其拓扑荷数息息相关。基于深度神经网络高效的特征提取特点，采用分类神经网络实现了经过散射后的涡旋光拓扑荷数的测量，且测量准确率达到100%。

Vortex beams have special spiral phase factors, and the communication capacity can be greatly improved by using vortex beams for communication coding. The atmospheric turbulence and haze in the actual communication environment will lead to the scattering of vortex beams and form speckles, which increases the difficulty of information decoding in the vortex optical communication. Therefore, it is of great significance to accurately and efficiently measure the topological charges of vortex beams from the speckles for their application in vortex optical communication. The characteristics of the speckle field formed after vortex beams passing through scattering medium are closely related to the topological charges. Based on the efficient feature extraction of depth neural network, the measurement of topological charges of scattered vortex beams is realized by using classified neural network, and the measurement accuracy is up to 100%.