Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices
Not on the map. Why?
Abstract (arXiv)
Spacecraft anomaly detection is critical for mission safety, yet deploying sophisticated models on-board presents significant challenges due to hardware constraints. This paper investigates three approaches for spacecraft telemetry anomaly detection -- forecasting & threshold, direct classification, and image classification -- and optimizes them for edge deployment using multi-objective neural architecture optimization on the European Space Agency Anomaly Dataset. Our baseline experiments demonstrate that forecasting & threshold achieves superior detection performance (92.7% Corrected Event-wise F0.5-score (CEF0.5)) [1] compared to alternatives. Through Pareto-optimal architecture optimization, we dramatically reduced computational requirements while maintaining capabilities -- the optimized forecasting & threshold model preserved 88.8% CEF0.5 while reducing RAM usage by 97.1% to just 59 KB and operations by 99.4%. Analysis of deployment viability shows our optimized models require just 0.36-6.25% of CubeSat RAM, making on-board anomaly detection practical even on highly constrained hardware. This research demonstrates that sophisticated anomaly detection capabilities can be successfully deployed within spacecraft edge computing constraints, providing near-instantaneous detection without exceeding hardware limitations or compromising mission safety.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 71 references that are in the map. First posted on arXiv 31 Mar 2026.
Builds on
22 of 71 references.
References · 22
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
- 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
- 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
- 2018Deep learning for time series classification: a reviewcited by 575
- 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
- 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
- 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
- 2016Time Series Classification from Scratch with Deep Neural Networks: A Strong Baselinecited by 358
- 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 148
- 2017LSTM Fully Convolutional Networks for Time Series Classificationcited by 135
10 more
- 2022Deep Learning for Time Series Anomaly Detection: A Surveycited by 130
- 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 60
- 2020μNAS: Constrained Neural Architecture Search for Microcontrollerscited by 54
- 2019Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matricescited by 32
- 2019XceptionTime: A Novel Deep Architecture based on Depthwise Separable Convolutions for Hand Gesture Classificationcited by 17
- 2024European Space Agency Benchmark for Anomaly Detection in Satellite Telemetrycited by 12
- 2020How many images do I need? Understanding how sample size per class affects deep learning model performance metrics for balanced designs in autonomous wildlife monitoringcited by 11
- 2015Spatially Encoding Temporal Correlations to Classify Temporal Data Using Convolutional Neural Networkscited by 8
- 2024A Comparison of Deep Learning Architectures for Spacecraft Anomaly Detectioncited by 2
- 2022Contextual Learning in Fourier Complex Field for VHR Remote Sensing Imagescited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.