Detecting Satellites in Radio-Frequency Data via Semi-Supervised Learning

2026-06-18

AI Summary

This study addresses the challenges of satellite signal detection and classification in radio frequency (RF) monitoring, where labeled data are scarce and observations are large-scale yet sparse. To overcome these limitations, the authors propose a semi-supervised learning framework that integrates non-negative matrix factorization with automatic rank selection (NMFk), expert-guided cluster interpretation, and a supervised classifier. By combining unsupervised factorization with domain knowledge, the approach enables interpretable and transferable RF signal analysis without requiring extensive labeled datasets. Experimental results demonstrate that the proposed pipeline effectively identifies satellite signals and accurately discriminates ionospheric background activity from other RF events, significantly improving detection accuracy and generalization performance under conditions of sparse annotations.

Abstract

Radio-frequency (RF) monitoring is essential for space domain awareness, but it often generates large, variable, and sparsely populated datasets with few labels. These observations can capture satellites, space debris, and the ionospheric background, yet interpreting them typically requires specialized subject-matter expertise. Supervised deep learning methods can perform well on labeled RF data, but they require many annotated examples and may need careful retraining as RF conditions change. Semi-supervised approaches offer a practical alternative for limited-data settings by using unlabeled observations to reveal latent patterns that experts can interpret. In this paper, we present a semi-supervised RF detection and classification workflow for satellite monitoring that combines Non-negative Matrix Factorization with automatic model determination (NMFk), expert-guided cluster interpretation, and classifier-based prediction. We first represent RF observations as a non-negative feature matrix and apply NMFk to estimate the number of clusters that best captures patterns in the unlabeled data. Subject-matter experts then assign physical meaning to the resulting clusters, including satellite detections, ionospheric environmental conditions, and other RF event categories. Finally, we train a classifier on these interpreted clusters to evaluate performance on a test set and categorize future observations. This pipeline reduces reliance on large pre-labeled datasets by pairing unsupervised factorization with expert interpretation, enabling an interpretable and transferable methodology for detecting, observing, and classifying behavior in RF data.

Problem

• satellite detection
• radio-frequency monitoring
• semi-supervised learning
• space domain awareness
• sparse labeling

Innovation

• semi-supervised learning
• Non-negative Matrix Factorization with automatic model determination (NMFk)
• radio-frequency monitoring
• expert-guided interpretation
• space domain awareness