Segregating Orbital Station Keeping Maneuvers of Non-Cooperative Space Objects using SMOTE based Imbalanced Learnin

Shivshankar, S and Ghose, D (2024) Segregating Orbital Station Keeping Maneuvers of Non-Cooperative Space Objects using SMOTE based Imbalanced Learnin. In: AIAA SciTech Forum and Exposition, 2024, 8 January 2024through 12 January 2024, Orlando, Florida..

PDF AIAA_Sci_ For_Exp_2024.pdf - Published Version Restricted to Registered users only Download (3MB) | Request a copy

Abstract

Understanding the behaviour of non-cooperative space objects is a critical requirement of Space Situational Awareness (SSA). Identifying maneuvers of non-cooperative space objects helps in analysing their behaviour. Since all maneuvers of non-cooperative space objects may not be threatening in nature, it is essential to segregate routine maneuvers needed by a satellite to maintain its orbit from anomalous and abnormal maneuvers which may be perceived as threat. In this paper, we present an approach to filter out benign and regular pattern-of-life maneuvers from the orbital data of non-cooperative space objects through machine learning (ML) based classification of publicly available orbital data of cooperative civilian satellites with their maneuver history published in the open domain. The main challenge in this task was that the routine pattern-of-life maneuvers of satellites are events of interest but are infrequent, and hence the non-maneuver class was observed to be far more numerous than the maneuver class label in the dataset. In this paper, Synthetic Minority Oversampling Techniques (SMOTE) have been used to handle the imbalance in dataset available for classification. Use cases of different missions of cooperative civilian satellites in LEO regime are evaluated and presented. The results on the relative comparison between the different SMOTE variants on different satellite datasets are also provided. © 2024 by S Shivshankar, Debasish Ghose.

Item Type:	Conference Paper
Publication:	AIAA SciTech Forum and Exposition, 2024
Publisher:	American Institute of Aeronautics and Astronautics Inc, AIAA
Additional Information:	The copyright for this article belongs to American Institute of Aeronautics and Astronautics Inc, AIAA.
Keywords:	Behavioral research; Classification (of information); Orbits, Class labels; Machine-learning; Non-cooperative; Orbital station; Orbitals; Regular patterns; Space objects; Space situational awareness; Station-keeping; Synthetic minority over-sampling techniques, Satellites
Department/Centre:	Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited:	25 Sep 2024 05:23
Last Modified:	25 Sep 2024 05:23
URI:	http://eprints.iisc.ac.in/id/eprint/85625

Actions (login required)

View Item