A study on data mining and fault prediction using long-term satellite telemetry

Dong-Hwan Yoon; Jiseung Ahn; Jingi Ju; Mincheol Shin; Jeongyeol Choe

doi:10.23386/joss.2026.3.1.004

All Issue

2026 Vol.3, Issue 1 Preview Page Next Page

A study on data mining and fault prediction using long-term satellite telemetry

30 June 2026. pp. 29-35

PDF XML

Abstract

As the number of operational satellites increases rapidly in the New Space era, there is a critical need for automated intelligent monitoring to manage multiple spacecraft with limited personnel. This paper presents a practical data-driven approach for anomaly detection and fault prediction based on long-term telemetry from the KOMPSAT-2 satellite. We developed a preprocessing pipeline to organize 16 years of telemetry (2006-2022), totaling 158 GB and approximately 2,900 channels, into a structured, analysis-ready dataset while addressing issues such as irregular sampling and missing values. In collaboration with domain experts, we reviewed 300 historical anomaly reports to identify and label key fault events. Considering the scarcity of labeled data in real-world operations, we evaluated several unsupervised techniques, including autoencoders and Isolation Forest, to identify off-nominal behaviors. Our findings show that the proposed approach successfully captured both known fault signatures and undocumented deviations, such as subtle signals from orbit maneuvers. These results demonstrate the potential of AI-based telemetry mining to provide early warnings and support satellite operations. This work establishes a foundational framework for intelligent fault detection systems, which will be essential for the efficient management of large satellite constellations in the future.

Keywords

KOMPSAT-2

Satellite telemetry

Data mining

Anomaly detection

Fault prediction

Spacecraft Health Management

References

M. Frąckiewicz, Mind-Blowing: Nearly 15,000 Satellites Are Whizzing Around Earth Right Now—Find Out Why It Matters! TS2 Space [Online], 2025. Available at: https://ts2.tech/en/mind-blowing-nearly-15000-satellites-are-whizzing-around-earth-right-now-find-out-why-it-matters/ [Accessed 11/06/2026].

A. Fejjari, A. Delavault, R. Camilleri, and G. Valentino, A Review of Anomaly Detection in Spacecraft Telemetry Data. Applied Sciences. 15(10), 2025, 5653. DOI: 10.3390/app15105653.

10.3390/app15105653

J. Murphy, M.D.M. Qureshi, J. O’Brien, and B. Mac Namee, Autonomous Satellite Health Monitoring using EIRSAT-1 Telemetry, Proceedings of the 32nd Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2024), CEUR Workshop Proceedings. 3910, 2025, pp. 279-289.

K. Hundman, V. Constantinou, C. Laporte, I. Colwell, and T. Söderström, Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding, Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ’18), 2018, pp. 387-395. DOI: 10.1145/3219819.3219845.

10.1145/3219819.3219845

M.A. Schwabacher, A Survey of Data-Driven Prognostics, AIAA Infotech@Aerospace Conference. AIAA 2005-7002, 2005. DOI: 10.2514/6.2005-7002.

10.2514/6.2005-7002

S. Tariq, S. Lee, Y. Shin, M.S. Lee, O. Jung, D. Chung, and S.S. Woo, Detecting Anomalies in Space Using Multivariate Convolutional LSTM with Mixtures of Probabilistic PCA, Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ’19), 2019, pp. 2123-2133. DOI: 10.1145/3292500.3330776.

10.1145/3292500.3330776

B. Ruszczak, K. Kotowski, D. Evans, and J. Nalepa, The OPS-SAT benchmark for detecting anomalies in satellite telemetry. Scientific Data. 12(1), 2025, Article 710. DOI: 10.1038/s41597-025-05035-3.

10.1038/s41597-025-05035-3

R. Mukai, Z. Towfic, M. Danos, M. Shihabi, and D. Bell, MSL Telecom Automated Anomaly Detection, 2020 IEEE Aerospace Conference, Big Sky, MT, USA, 7-14 March 2020. Pasadena, CA, USA: Jet Propulsion Laboratory, National Aeronautics and Space Administration, 2020. Persistent identifier: hdl:2014/52252.

10.1109/AERO47225.2020.9172573

B. Ruszczak, K. Kotowski, J. Andrzejewski, A. Musiał, D. Evans, V. Zelenevskiy, S. Bammens, R. Laurinovics, and J. Nalepa, Machine learning detects anomalies in OPS-SAT telemetry, Proceedings of the International Conference on Computational Science (ICCS 2023), Lecture Notes in Computer Science. 14073, 2023, pp. 295-306. DOI: 10.1007/978-3-031-35995-8_21.

10.1007/978-3-031-35995-8_21

S. Cuéllar, M. Santos, F. Alonso, E. Fabregas, and G. Farias, Explainable Anomaly Detection in Spacecraft Telemetry. Engineering Applications of Artificial Intelligence. 133, 2024, Article 108083. DOI: 10.1016/j.engappai.2024.108083.

10.1016/j.engappai.2024.108083

A.A. Diro, S. Kaisar, A.V. Vasilakos, A. Anwar, A. Nasirian, and G. Olani, Anomaly detection for space information networks: a survey of challenges, techniques, and future directions. Computers & Security. 139, 2024, Article 103705. DOI: 10.1016/j.cose.2024.103705.

10.1016/j.cose.2024.103705

Information

Publisher :Korean Academy of Space Security
Publisher(Ko) :한국우주안보학회
Journal Title :JOURNAL OF SPACE SECURITY
Journal Title(Ko) :한국우주안보학회지
Volume : 3
No :1
Pages :29-35
Received Date : 2026-01-26
Revised Date : 2026-05-20
Accepted Date : 2026-05-29
DOI :https://doi.org/10.23386/joss.2026.3.1.004

JOURNAL OF SPACE SECURITY ISSN:3058-5759(Print) 한국우주안보학회지

All Issue