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.

Length of day (LOD), a fundamental component of Earth orientation parameters (EOP), reflects variations in Earth's rotation rate. Due to the influenced of atmospheric circulation, ocean currents, hydrological processes, and internal Earth dynamics, LOD exhibits complex nonlinear characteristics, making accurate prediction challenging Current LOD prediction models primarily depend on the high-precision, smoothed EOP C04 series provided by the IERS. However, this series has an inherent delay of approximately 30 days, causing it unsuitable for real-time applications such as interplanetary spacecraft tracking and navigation, GNSS meteorology, and real-time satellite orbit determination. To address these challenges, a novel approach based on a convolutional long short-term memory (ConvLSTM) method was proposed, which captures the time-varying characteristics of LOD by integrating IGS rapid products and effective angular momentum (EAM) datasets to improve the accuracy of near real-time LOD predictions. Results indicate that incorporating GNSS near real-time (NRT) data improves short-term (10–30 days) LOD prediction accuracy by 55.07%. By incorporating GNSS NRT data and EAM datasets, the ConvLSTM model significantly improves LOD prediction accuracy across various time scales. This enhancement not only strengthens Earth's rotation prediction models but also facilitates critical applications in real-time satellite orbit determination, extreme weather forecasting, and so on.