mlsanityData to 7 Oct 2026

The OPS-SAT benchmark for detecting anomalies in satellite telemetry

arXiv 2407.04730 ↗First posted 29 Jun 2024eess.SP cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Detecting anomalous events in satellite telemetry is a critical task in space operations. This task, however, is extremely time-consuming, error-prone and human dependent, thus automated data-driven anomaly detection algorithms have been emerging at a steady pace. However, there are no publicly available datasets of real satellite telemetry accompanied with the ground-truth annotations that could be used to train and verify anomaly detection supervised models. In this article, we address this research gap and introduce the AI-ready benchmark dataset (OPSSAT-AD) containing the telemetry data acquired on board OPS-SAT -- a CubeSat mission which has been operated by the European Space Agency which has come to an end during the night of 22--23 May 2024 (CEST). The dataset is accompanied with the baseline results obtained using 30 supervised and unsupervised classic and deep machine learning algorithms for anomaly detection. They were trained and validated using the training-test dataset split introduced in this work, and we present a suggested set of quality metrics which should be always calculated to confront the new algorithms for anomaly detection while exploiting OPSSAT-AD. We believe that this work may become an important step toward building a fair, reproducible and objective validation procedure that can be used to quantify the capabilities of the emerging anomaly detection techniques in an unbiased and fully transparent way.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 15 of its 56 references that are in the map. First posted on arXiv 29 Jun 2024.

Builds on

15 of 56 references.

References · 15

  1. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  2. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  3. 2019PyOD: A Python Toolbox for Scalable Outlier Detectioncited by 221
  4. 2020Deep Learning for Anomaly Detection: A Reviewcited by 159
  5. 2022ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functionscited by 153
  6. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 148
  7. 2020COPOD: Copula-Based Outlier Detectioncited by 143
  8. 2018Adversarially Learned Anomaly Detectioncited by 115
  9. 2019catch22: CAnonical Time-series CHaracteristicscited by 103
  10. 2022Deep Isolation Forest for Anomaly Detectioncited by 90
  11. 2018Generative Adversarial Active Learning for Unsupervised Outlier Detectioncited by 65
  12. 2019XGBOD: Improving Supervised Outlier Detection with Unsupervised Representation Learningcited by 42
3 more
  1. 2021LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networkscited by 42
  2. 2024European Space Agency Benchmark for Anomaly Detection in Satellite Telemetrycited by 12
  3. 2022An Anomaly Detection Method for Satellites Using Monte Carlo Dropoutcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2025On Revealing the Hidden Problem Structure in Real-World and Theoretical Problems Using Walsh Coefficient Influencecited by 2
  2. 2025Convolutional Autoencoders for Data Compression and Anomaly Detection in Small Satellite Technologiescited by 0
  3. 2026Towards Resilient Intrusion Detection in CubeSats: Challenges, TinyML Solutions, and Future Directionscited by 0
  4. 2026On-Orbit Space AI: Federated, Multi-Agent, and Collaborative Algorithms for Satellite Constellationscited by 0
  5. 2026A Hierarchical Ensemble Pipeline for Anomaly Detection in ESA Satellite Telemetrycited by 0
  6. 2026Syn2Logic: End-to-End Neuromorphic Design Automationcited by 0
  7. 2026Temporal and Multimodal Deep Learning for Cyberattack Detection in LEO Satellite Systemscited by 0