Applying Deep Learning to Anomaly Detection of Russian Satellite Activity for Indications Prior to Military Activity

2025-08-24

AI Summary

This work addresses the need for early warning of military conflicts by investigating whether Russian satellites exhibited detectable orbital anomalies prior to the invasion of Ukraine. Leveraging publicly available Two-Line Element (TLE) data, we establish a six-month baseline of nominal orbital behavior and propose a novel autoencoder architecture incorporating anchor-point loss. The model performs fine-grained anomaly detection via reconstruction error analysis across all six classical orbital elements (semi-major axis, eccentricity, inclination, etc.), enabling both precise localization of deviations and interpretable inference of potential intent. Compared against isolation forest, variational autoencoders (VAEs), and Kolmogorov–Arnold networks (KANs), our method achieves significantly higher anomaly detection accuracy and statistical significance. Experimental results reveal persistent, statistically significant deviations in multiple Russian satellites’ orbital elements 3–6 months before the invasion—constituting the first deep learning–based empirical evidence supporting space-based Indications and Warning (I&W). The approach advances both methodological innovation and strategic early-warning capability.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Deep Generative Models & Autoencoders
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

We apply deep learning techniques for anomaly detection to analyze activity of Russian-owned resident space objects (RSO) prior to the Ukraine invasion and assess the results for any findings that can be used as indications and warnings (I&W) of aggressive military behavior for future conflicts. Through analysis of anomalous activity, an understanding of possible tactics and procedures can be established to assess the existence of statistically significant changes in Russian RSO pattern of life/pattern of behavior (PoL/PoB) using publicly available two-line element (TLE) data. This research looks at statistical and deep learning approaches to assess anomalous activity. The deep learning methods assessed are isolation forest (IF), traditional autoencoder (AE), variational autoencoder (VAE), Kolmogorov Arnold Network (KAN), and a novel anchor-loss based autoencoder (Anchor AE). Each model is used to establish a baseline of on-orbit activity based on a five-year data sample. The primary investigation period focuses on the six months leading up to the invasion date of February 24, 2022. Additional analysis looks at RSO activity during an active combat period by sampling TLE data after the invasion date. The deep learning autoencoder models identify anomalies based on reconstruction errors that surpass a threshold sigma. To capture the nuance and unique characteristics of each RSO an individual model was trained for each observed space object. The research made an effort to prioritize explainability and interpretability of the model results thus each observation was assessed for anomalous behavior of the individual six orbital elements versus analyzing the input data as a single monolithic observation. The results demonstrate not only statistically significant anomalies of Russian RSO activity but also details anomalous findings to the individual orbital element.

Problem

• Detecting anomalous Russian satellite activity before military actions
• Assessing orbital behavior changes for conflict indications and warnings
• Applying deep learning to identify pre-invasion satellite pattern deviations

Innovation

• Deep learning autoencoder models detect anomalies
• Individual models trained for each satellite object
• Analyze orbital elements separately for explainability