Search papers, labs, and topics across Lattice.
This paper explores three deep learning methods for spacecraft telemetry anomaly detection: forecasting&threshold, direct classification, and image classification, with a focus on edge deployment. Using multi-objective neural architecture optimization, the authors significantly reduce the computational footprint of these models while preserving anomaly detection performance on the ESA Anomaly Dataset. The optimized forecasting&threshold model achieves 88.8% CEF0.5 while reducing RAM usage to 59KB and operations by 99.4%, demonstrating the feasibility of on-board anomaly detection.
You can shrink a spacecraft anomaly detection model by 97% and still catch almost all the problems.
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.
