A new quality monitoring method for real-time precise orbit and clock products

Abstract

Real-time precise orbit and clock products are prerequisites for Real-Time Precise Point Positioning (RT-PPP) and its related applications, such as time synchronization and disaster monitoring. While real-time products have achieved relatively high accuracy, occasional outliers and accuracy degradation significantly restricts the application of RT-PPP in safety-critical fields. Sub-meter anomalies or larger are typically manageable, as users can easily detect and exclude them through outlier detection in the preprocessing stage before positioning. However, handling small-scale anomalies solely with user-side data and algorithms poses challenges, which also affect the accuracy and reliability of positioning solutions. To address this, we propose a quality monitoring method for real-time precise satellite orbit and clock products. The method utilizes a quality monitoring network of well-distributed stations to validate real-time products continuously. The product quality monitoring server-side calculates both pseudorange and carrier-phase Quality Indicator (QI) for each satellite by using real-time statistics of residuals from quality monitoring network stations, supplemented by product error empirical models. Furthermore, the isolation Forest (iForest) algorithm is employed to detect outliers prior to real-time residual statistics, mitigating the impact of monitoring network or communication link failures on QI while slightly increasing the computational load. QI are broadcasted to users, aiding them in excluding satellites with lower accuracy or reducing the weighting of these satellites in the positioning solution. We conducted a 1 month quality monitoring of Centre National d’Etudes Spatiales real-time orbit and clock products in January 2023, using 30 continuous stations of the Crustal Movement Observation Network of China. The results indicate that the pseudorange QI is greater than 1 m, which can adequately bound the product errors but still exhibit considerable redundancy. In contrast, the carrier-phase QI is within 15 cm, significantly reducing redundancies. The carrier-phase QI can instantly and accurately reflect the accuracy changes of satellite orbit and clock products and bound more than 99.93% of the product errors. The addition of iForest outlier detection reduces the number of false alert epochs from 74 to 21, reducing the false alert probability by 68.9%. At the same time, the execution time per epoch slightly increased from 28.8 to 32.1 ms, representing an 11.0% increase. Importantly, this increase in execution time does not significantly impact the Time to Alert. In addition, QI can effectively detect step faults with amplitudes greater than 3 cm and ramp faults with slopes greater than 0.05 cm/s. QI shows an immediate increase when faults occur and quickly returns to normal after faults end.