A Comparative Deep Learning Framework for Multivariate Time Series Anomaly Detection in Satellite Telemetry

Abstract

This study compares deep learning models for point-level anomaly detection in multichannel satellite telemetry data. Raw event-based telemetry was converted into segment-based multivariate time series without windowing or feature extraction, allowing models to learn system behavior at each time step. Preprocessing included channel alignment, training set-based normalization, missing value imputation, and temporal label smoothing, while Focal Loss and segment-level oversampling addressed class imbalance. Five architectures, BiLSTM, BiGRU, Transformer, Hybrid BiLSTM–Transformer, and Hybrid BiGRU–Transformer, were evaluated, with thresholds optimized on a validation set. The results show that hybrid models combining recurrent networks and attention mechanisms effectively capture both short- and long-term dependencies. The standalone BiGRU model achieves the highest overall classification performance in terms of F1 score and accuracy. In contrast, the Hybrid BiGRU–Transformer architecture does not outperform BiGRU in classification metrics but provides superior temporal stability, improved boundary sensitivity, and better interpretability in anomaly detection tasks.