2022
Stevenson, Emma; Rodriguez-Fernandez, Victor; Urrutxua, Hodei
Towards graph-based machine learning for conjunction assessment Proceedings Article
In: 2022 Advanced Maui Optical and Space Surveillance Technologies Conference (AMOS), Maui, Hawaii, USA, 2022.
Abstract | BibTeX | Tags: Conjunction Assessment, Deep Learning, Graph Neural Networks, Machine Learning, Space Debris, Space Situational Awareness
@inproceedings{stevenson2022_amos,
title = {Towards graph-based machine learning for conjunction assessment},
author = {Emma Stevenson and Victor Rodriguez-Fernandez and Hodei Urrutxua},
year = {2022},
date = {2022-09-19},
urldate = {2022-09-19},
booktitle = {2022 Advanced Maui Optical and Space Surveillance Technologies Conference (AMOS)},
address = {Maui, Hawaii, USA},
abstract = {In the face of increasing space traffic, the deployment of large constellations, and a growing debris field, identifying potentially catastrophic collisions is an increasingly daunting and computationally challenging task. In this work, we present a novel graph-based machine learning approach for detecting conjunctions between catalogued space objects to aid in this task. Modelling conjunction events as edges between pairs of object nodes, we introduce a graphical representation of the all-vs-all scenario (so-called as it considers conjunction events between all catalogued objects, both active and debris) that is able to profit from recent advancements in Graph Neural Networks, and make a step towards efficient, machine learning based conjunction assessment. For this, we develop a methodology to predict the existence of upcoming conjunction links over a given screening period, which we frame as a graph-to-graph link prediction task, and present some initial findings that demonstrate the learning potential of the proposed approach.},
keywords = {Conjunction Assessment, Deep Learning, Graph Neural Networks, Machine Learning, Space Debris, Space Situational Awareness},
pubstate = {published},
tppubtype = {inproceedings}
}
In the face of increasing space traffic, the deployment of large constellations, and a growing debris field, identifying potentially catastrophic collisions is an increasingly daunting and computationally challenging task. In this work, we present a novel graph-based machine learning approach for detecting conjunctions between catalogued space objects to aid in this task. Modelling conjunction events as edges between pairs of object nodes, we introduce a graphical representation of the all-vs-all scenario (so-called as it considers conjunction events between all catalogued objects, both active and debris) that is able to profit from recent advancements in Graph Neural Networks, and make a step towards efficient, machine learning based conjunction assessment. For this, we develop a methodology to predict the existence of upcoming conjunction links over a given screening period, which we frame as a graph-to-graph link prediction task, and present some initial findings that demonstrate the learning potential of the proposed approach.