Global Positioning System (GPS) has been confirmed to be a feasible tool to measure displacement of civil engineering structures. In this paper, we report on an analysis of annual deformations of a pumped-storage power station dam using historical GPS observations. Data spanning more than nine years are resolved using the GAMIT (GPS at MIT) software, and a GPS time-series method is employed to extract linear trends and annual cycle signals. It is evident that the monument located on the main dam has a linear trend, with rates of 1.0 mm/yr and 1.8 mm/yr in east and up directions, respectively. Annual cycles with amplitudes larger than 0.5 mm are shown in coordinate components at all monitoring stations. However, the annual amplitude can be 30–84% lower when a monitoring station whose monument materials and height are similar to other monitoring stations is chosen as the reference station. This suggests that differential thermal expansion of monuments could be 30% to 80% and even higher in baseline time series. A spurious offset style annual signal with 5 mm amplitude that is highly correlated with annual temperature variance is observed in the east–west direction of the monitoring station located at the east side of the reservoir. This suggests that upper ground layer movement correlated with temperature could be responsible for these annual cycles. Meanwhile, no periodic correlations are observed between the water level data and the baseline time series.

High-speed railway suspension bridges (HSRSBs) have been constructed with the new advancements in technology. The deformation prediction for HSRSBs is essential to their safety and maintenance. The conventional prediction methods are developed for bridges without high-speed railway. Different factors, including temperature (TEMP), time delay compensation (TDC), train live load (TLL), are considered in these methods. However, the train side (TS) and train instantaneous position (TIP) have a significant impact on deformation for HSRSBs, and they are not used in the prediction. More importantly, the coupling issue among different factors is so significant that it cannot be neglected. In this study, we propose a deformation prediction model based on a backpropagation (BP) neural network. This model uses different factors as model input, including TEMP, TDC, TLL, TS, and TIP. The coupling issue is addressed by using the new model. The new model was evaluated using a dataset of 10-day field measurements. It achieves a mean absolute error (MAE) of 8.81 mm, a mean relative error (MRE) of 9.82%, and coefficient of determination (R²) of 0.94. The new model will provide high-precision prediction for deformation and will be used in the development of an early warning system.