Automatic Detection of Anomalies in Post-Processed Data Applied to UTC Time Transfer Links

Abstract

In this article, we present a method for identifying anomalies, particularly time steps, which can affect data. Recognition of these anomalies is essential for understanding the intrinsic nature of problems that may occasionally affect the data, and for guaranteeing system reliability and accuracy. The tool presented, based on the Kalman filter, is optimized to work with post-processed data which means that the dataset is available at the time the algorithm is run. The main aim is to retain as much data as possible, while detecting anomalies, and avoid deleting valuable data. The originality of this tool with respect to the already existing Kalman-filter-based tools for detecting anomalies is substantial, because its objective is not only to enable the system to run but also to avoid unnecessary deletion of valuable data. This tool is designed to accurately determine the date of occurrence and magnitude of these anomalies, focusing on time steps. The tool presented will be applied, by way of example, to the time links used in Coordinated Universal Time (UTC) as calculated by Bureau International des Poids et Measures (BIPM), Paris, France. In addition, the algorithm developed will enable the BIPM’s Time Department to be rapidly alerted to unexpected behavior that may compromise UTC performance. To guarantee the reliability and accuracy of UTC, rigorous data validation and rapid problem identification are essential.