The Earth rotation parameters (ERPs), including polar motion (PMX and PMY) and universal time (UT1-UTC), play a central role in functions such as monitoring the Earth’s rotation and high-precision navigation and positioning. Variations in ERPs reflect not only the overall state of movement of the Earth, but also the interactions among the atmosphere, ocean, and land on the spatial and temporal scales. In this paper, we estimated ERP series based on very long baseline interferometry (VLBI) observations between 2011–2020. The results show that the average root mean square errors (RMSEs) are 0.187 mas for PMX, 0.205 mas for PMY, and 0.022 ms for UT1-UTC. Furthermore, to explore the high-frequency variations in more detail, we analyzed the polar motion time series spectrum based on fast Fourier transform (FFT), and our findings show that the Chandler motion was approximately 426 days and that the annual motion was about 360 days. In addition, the results also validate the presence of a weaker retrograde oscillation with an amplitude of about 3.5 mas. This paper proposes a hybrid prediction model that combines convolutional neural network (CNN) and long short-term memory (LSTM) neural network: the CNN–LSTM model. The advantages can be attributed to the CNN’s ability to extract and optimize features related to polar motion series, and the LSTM’s ability to make medium- to long-term predictions based on historical time series. Compared with Bulletin A, the prediction accuracies of PMX and PMY are improved by 42% and 13%, respectively. Notably, the hybrid CNN–LSTM model can effectively improve the accuracy of medium- and long-term polar motion prediction.

The Earth rotation parameters (ERP) mainly including the displacement and rate of the earth's poles, UT1-UTC, length of day are estimated by processing the thirty-one IGS stations data from November 28, 2017 to December 12, 2017 with GAMIT. The ERP are obtained with VieVS3.2 by processing VLBI data observed on CONT17 campaign. The ERP results of GNSS and VLBI are combined in a weighted way, based on the Helemert variance component estimation and weighting method is proposed. The results show that the Root Mean Square(RMS) of the polar shift component in the X-direction is 0.000985 mas, the RMS of the polar shift component in the Y-direction is 0.000286 mas, and the RMS of UT1-UTC is 0.000690 ms, and the weighted accuracy is significantly better than that of the separate solutions of GNSS and VLBI, which can make up for the shortcoming of the single technique as GNSS and VLBI.

The Earth rotation parameters mainly include the displacement and rate of the Earth's poles, length of day, which can be estimated based on VLBI and GNSS. In order to obtain the ERP results with higher accuracy, two VLBI data processing schemes were compared. VLBI observations during 2008, 2011, 2014, and 2017 are processed with VieVS. In addition, the experiments to estimate ERP using CONT08, CONT11, CONT14, and CONT17 campaigns were also designed. The results showed that the higher accuracy of ERP were calculated using CONT campaigns. At the same time, ERP estimations using the 86 globally distributed GNSS observatories data during the same period were processed by GAMIT. The ERP results from the CONT campaigns and GNSS observations estimated were then combined in a weighted manner, based on the Helmert variance component estimation and the IERS14 C04 sequences, respectively. The weighted results showed that the Root Mean Square Error (RMSE) of polar motion was about between 0.05 and 0.10 mas, and the RMSE in UT1-UTC ranged from 0.005 and 0.02 ms.