A novel AI temporal-spatial analysis approach for GNSS error source recognition

Global navigation satellite systems (GNSS) error source analysis is crucial for identifying factors that affect the accuracy of positioning, navigation, and timing services (PNT). Detecting and correcting these factors is essential for enhancing
overall service accuracy. Traditional methods primarily focus on surface-level receiver output data, which may overlook underlying factors. Additionally, analyzing daily generated data is expensive and requires advanced proficiency. This research uses a novel temporal-spatial analysis approach to analyze GNSS
error sources with artificial intelligence (AI) model support. We develop a noise segments dataset categorized into six types, with a particular focus on ionospheric disclosure, a deeper-level receiver data calculating PNT result. By applying clustering combined with a z-score normalization filter (ZFilter), we
identify highly consistent noise segments in daily data, which aids in understanding potential causes. We then employ a multi-model deep learning approach to classify the noise segments, as opposed to relying on a single baseline model. Additionally, we experiment with semi-supervised learning through pseudo-labeling to improve classification performance. Our experiments
show that our classifier achieves approximately 84% accuracy in identifying the noise segments.