论文推荐|论文推荐|河南理工大学徐克科教授：顾及缺失数据和时变季节信号的大地测量时序高斯过程重建

Seasonal signals in satellite geodesy time series are mainly derived from a number of loading sources, such as atmospheric pressure and hydrological loading. The most common method for modeling the seasonal signal with quasi-period is to use the sine and cosine functions with the constant amplitude for approximation. However, due to the complexity of environmental changes, the time-varying period part is very difficult to model by the geometric or physical method. We present a machine learning method with Gaussian process to capture the quasi-periodic signals in the geodetic time series and optimize the estimation of model parameters by means of maximum likelihood estimation. We test the performance of the method using the synthetic time series by simulating the time-varying and quasi-periodic signals. The results show that the fitting residuals of the new model show a better random fluctuation, while the traditional models still leave the clear periodic systematics signals without being fully modeled. The new model illustrates a higher reliability of linear trend estimation, and a lower uncertainty and model fitting RMSE, even in time series with shorter time span. On the other hand, it shows a strong capacity to restore the missing data and predict the future changes in time series. The method is successfully applied to modeling the real coordinate time series of the GNSS site (BJFS) from IGS network, and the equivalent water height (EWH) time series in North China obtained from gravity satellites. Therefore, it is recommended as an alternative for precise model reconstruction and signals extraction of satellite geodesy time series, especially in modeling the complex time-varying signals, estimating the secular motion velocity, and recovering the large missing data.