A self-supervised framework for space object behaviour characterisation

Tools

Groves, Ian and Campbell, Andrew John and Fernandes, James and Rodríguez, Diego Ramírez and Murray, Paul and Vasile, Massimiliano and Nockles, Victoria (2025) A self-supervised framework for space object behaviour characterisation. Other. arXiv. (https://doi.org/10.48550/arXiv.2504.06176)

[thumbnail of Groves-etal-2025-A-self-supervised-framework-for-space-object-behaviour-characterisation]
Preview
 Text. Filename: Groves-etal-2025-A-self-supervised-framework-for-space-object-behaviour-characterisation.pdf
Final Published Version
License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 logo
Download (4MB)| Preview

Abstract

Foundation Models, pre-trained on large unlabelled datasets before task-specific fine-tuning, are increasingly being applied to specialised domains. Recent examples include ClimaX for climate and Clay for satellite Earth observation, but a Foundation Model for Space Object Behavioural Analysis has not yet been developed. As orbital populations grow, automated methods for characterising space object behaviour are crucial for space safety. We present a Space Safety and Sustainability Foundation Model focusing on space object behavioural analysis using light curves (LCs). We implemented a Perceiver-Variational Autoencoder (VAE) architecture, pre-trained with self-supervised reconstruction and masked reconstruction on 227,000 LCs from the MMT-9 observatory. The VAE enables anomaly detection, motion prediction, and LC generation. We fine-tuned the model for anomaly detection & motion prediction using two independent LC simulators (CASSANDRA and GRIAL respectively), using CAD models of boxwing, Sentinel-3, SMOS, and Starlink platforms. Our pre-trained model achieved a reconstruction error of 0.01%, identifying potentially anomalous light curves through reconstruction difficulty. After fine-tuning, the model scored 88% and 82% accuracy, with 0.90 and 0.95 ROC AUC scores respectively in both anomaly detection and motion mode prediction (sun-pointing, spin, etc.). Analysis of high-confidence anomaly predictions on real data revealed distinct patterns including characteristic object profiles and satellite glinting. Here, we demonstrate how self-supervised learning can simultaneously enable anomaly detection, motion prediction, and synthetic data generation from rich representations learned in pre-training. Our work therefore supports space safety and sustainability through automated monitoring and simulation capabilities.

ORCID iDs

Groves, Ian, Campbell, Andrew John ORCID logoORCID: https://orcid.org/0000-0002-4439-3630, Fernandes, James, Rodríguez, Diego Ramírez, Murray, Paul ORCID logoORCID: https://orcid.org/0000-0002-6980-9276, Vasile, Massimiliano ORCID logoORCID: https://orcid.org/0000-0001-8302-6465 and Nockles, Victoria;
CORE (COnnecting REpositories)