Abstract: The empirical models of dispersive media are suitable for describing media such as plasma, water, and biological tissues. In order to reconstruct the electromagnetic parameters of the dispersive media, this paper proposes a method for inversion of electromagnetic parameters of dispersive media based on convolutional neural networks. In the process of electromagnetic parameters inversion, the forward algorithm is used to obtain the scattered electric field values of the dispersive media, and the backward algorithm transforms the original inverse scattering problem into a regression estimation problem through the convolutional neural network. The real and imaginary parts of the scattered electric field values of the dispersive media radiated by TM waves of different frequencies are extracted as the sample information and the input of the convolutional neural network, and the electromagnetic parameters of the dispersive media are taken as the output. After proper training, the electromagnetic parameters of the dispersive medium cylinder in free space are reconstructed. The comparison with the inversion results of BP neural network verifies the effectiveness and accuracy of the method in this paper.