Modulation format identification (MFI) and optical performance monitoring (OPM) are essential for elastic optical networks. A method for joint modulation format identification and optical signal-to-noise ratio (OSNR) monitoring based on ternary neural networks was proposed. Further, a ternary neural network was established, and the constellation images after constant modulus algorithm (CMA) equalization were used as input features. Four commonly used modulation formats were distinguished, including dual-polarization (DP)-QPSK, 8QAM, 16QAM, and 64QAM. A 32G baud simulation system was constructed, and the results were analyzed. First, we determined the structure of a neural network using network depth, resolution, and sample length as the parameters. The values 4, 32, and 7000 were selected for the three parameters, respectively, based on the balance between resource consumption and accuracy. Then, the robustness of the system was analyzed. The results validate that the proposed method can tolerate the residual chromatic dispersion (from -200 ps/nm to 200 ps/nm) and fiber nonlinearity (from 500 km to 1500 km). Moreover, we compared the performance of the binarized neural network (BNN), ternary neural network (TNN), and full-precision neural network (FNN). The results indicate that the memory consumption and extraction time of the TNN are similar to those of the BNN, and the accuracy is further improved. Finally, an experiment was conducted to prove the practicality of the proposed method
