2023
Stevenson, Emma; Rodríguez-Fernández, Víctor; Urrutxua, Hodei; Camacho, David
Benchmarking deep learning approaches for all-vs-all conjunction screening Journal Article
In: Advances in Space Research, 2023.
Abstract | Links | BibTeX | Tags: Conjunction Assessment, Deep Learning, Filtering, Machine Learning, Orbits, Space, Space Debris, Space Environment Management, Space Situational Awareness, Space Traffic Management, Time Series
@article{nokey,
title = {Benchmarking deep learning approaches for all-vs-all conjunction screening},
author = {Emma Stevenson and Víctor Rodríguez-Fernández and Hodei Urrutxua and David Camacho},
doi = {https://doi.org/10.1016/j.asr.2023.01.036},
year = {2023},
date = {2023-01-23},
urldate = {2023-01-23},
journal = {Advances in Space Research},
abstract = {The all-vs-all problem, for which conjunctions are screened for over all possible sets of catalogued objects, is crucial for space traffic management and space situational awareness, but is a computational challenge owing to the vast and growing number of possible conjunction pairs. In this work, we present the application of deep learning techniques to this problem, framing conjunction screening as a machine learning classification task. We investigate the performance of different input data representations and model architectures on a realistic all-vs-all dataset, generated using the CNES BAS3E space surveillance simulation framework, and consisting of 170 million object pairs over a 7-day screening period. These approaches are benchmarked against operationally used classical filters in both screening capability and computational efficiency, and the ability of deep learning algorithms to cope and aid with the scales required for current and future operational all-vs-all scenarios is demonstrated.},
keywords = {Conjunction Assessment, Deep Learning, Filtering, Machine Learning, Orbits, Space, Space Debris, Space Environment Management, Space Situational Awareness, Space Traffic Management, Time Series},
pubstate = {published},
tppubtype = {article}
}
The all-vs-all problem, for which conjunctions are screened for over all possible sets of catalogued objects, is crucial for space traffic management and space situational awareness, but is a computational challenge owing to the vast and growing number of possible conjunction pairs. In this work, we present the application of deep learning techniques to this problem, framing conjunction screening as a machine learning classification task. We investigate the performance of different input data representations and model architectures on a realistic all-vs-all dataset, generated using the CNES BAS3E space surveillance simulation framework, and consisting of 170 million object pairs over a 7-day screening period. These approaches are benchmarked against operationally used classical filters in both screening capability and computational efficiency, and the ability of deep learning algorithms to cope and aid with the scales required for current and future operational all-vs-all scenarios is demonstrated.
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.
Stevenson, Emma; Rodriguez-Fernandez, Victor; Urrutxua, Hodei; Camacho, David
Deep learning for all-vs-all conjunction detection Proceedings Article
In: 5th Workshop on Key Topics in Orbit Propagation Applied to Space Situational Awareness (KePASSA), Logroño, Spain, 2022.
Abstract | BibTeX | Tags: Conjunction Assessment, Deep Learning, Self-supervised Learning, Space Debris, Space Situational Awareness
@inproceedings{stevenson2022_kepassa,
title = {Deep learning for all-vs-all conjunction detection},
author = {Emma Stevenson and Victor Rodriguez-Fernandez and Hodei Urrutxua and David Camacho},
year = {2022},
date = {2022-06-01},
urldate = {2022-06-01},
booktitle = {5th Workshop on Key Topics in Orbit Propagation Applied to Space Situational Awareness (KePASSA)},
address = {Logroño, Spain},
abstract = {This paper explores the use of different deep learning techniques for detecting conjunction events in an efficient and accurate way for improved space situational awareness. Framing the problem as a machine learning classification task, we present the performance of different data representations and model architectures on a realistic all-vs-all dataset generated using the CNES BAS3E space surveillance simulation framework, and compare the approaches to operationally used classical filters in screening performance and computational efficiency. Finally, we also investigate a novel methodology for improving the performance and generalisation ability of the models using a pre-trained orbit model, ORBERT, based on self-supervised learning techniques.},
keywords = {Conjunction Assessment, Deep Learning, Self-supervised Learning, Space Debris, Space Situational Awareness},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper explores the use of different deep learning techniques for detecting conjunction events in an efficient and accurate way for improved space situational awareness. Framing the problem as a machine learning classification task, we present the performance of different data representations and model architectures on a realistic all-vs-all dataset generated using the CNES BAS3E space surveillance simulation framework, and compare the approaches to operationally used classical filters in screening performance and computational efficiency. Finally, we also investigate a novel methodology for improving the performance and generalisation ability of the models using a pre-trained orbit model, ORBERT, based on self-supervised learning techniques.