2022
Stevenson, Emma; Martinez, Riansares; Rodriguez-Fernandez, Victor; Camacho, David
Predicting the effects of kinetic impactors on asteroid deflection using end-to-end deep learning Proceedings Article
In: 2022 IEEE Congress on Evolutionary Computation (CEC), pp. 1-8, Padua, Italy, 2022.
Abstract | Links | BibTeX | Tags: Asteroid Deflection, Deep Learning, Planetary Defence, Self-supervised Learning, Time Series, Transformers
@inproceedings{9870215,
title = {Predicting the effects of kinetic impactors on asteroid deflection using end-to-end deep learning},
author = {Emma Stevenson and Riansares Martinez and Victor Rodriguez-Fernandez and David Camacho},
doi = {10.1109/CEC55065.2022.9870215},
year = {2022},
date = {2022-07-18},
urldate = {2022-07-18},
booktitle = {2022 IEEE Congress on Evolutionary Computation (CEC)},
pages = {1-8},
address = {Padua, Italy},
abstract = {One possible approach to deflect the trajectory of an asteroid on a collision course with the Earth, and prevent a potentially devastating impact, is the use of a kinetic impactor. The upcoming NASA DART and ESA Hera space missions will be the first to study and demonstrate this technique, by driving a spacecraft into the moon of a binary asteroid system with the aim of altering its momentum, and knocking it off course. In this work, we seek to predict critical parameters associated with such an impact, namely the momentum transfer efficiency and axial ratio of the target body, based on light curve data observed from ground before and after the impact in order to give insights into the real effect of the deflection effort. We present here our approach to this problem, which we address from a purely data-driven perspective based on simulated data provided as a part of the Andrea Milani Planetary Defence Challenge, organised by the EU H2020 Stardust-R research network in conjunction with ESA. Formulating the problem as a time series regression task, we develop an end-to-end deep learning pipeline in which we apply the latest advances in deep learning for time series, such as the use of the Transformer architecture as well as ensembling and self-supervised learning techniques. Exploiting these techniques for the challenge, we achieved second place out of the student teams, and fifth place overall without relying on any a priori knowledge of the physics of the asteroid system.},
keywords = {Asteroid Deflection, Deep Learning, Planetary Defence, Self-supervised Learning, Time Series, Transformers},
pubstate = {published},
tppubtype = {inproceedings}
}
One possible approach to deflect the trajectory of an asteroid on a collision course with the Earth, and prevent a potentially devastating impact, is the use of a kinetic impactor. The upcoming NASA DART and ESA Hera space missions will be the first to study and demonstrate this technique, by driving a spacecraft into the moon of a binary asteroid system with the aim of altering its momentum, and knocking it off course. In this work, we seek to predict critical parameters associated with such an impact, namely the momentum transfer efficiency and axial ratio of the target body, based on light curve data observed from ground before and after the impact in order to give insights into the real effect of the deflection effort. We present here our approach to this problem, which we address from a purely data-driven perspective based on simulated data provided as a part of the Andrea Milani Planetary Defence Challenge, organised by the EU H2020 Stardust-R research network in conjunction with ESA. Formulating the problem as a time series regression task, we develop an end-to-end deep learning pipeline in which we apply the latest advances in deep learning for time series, such as the use of the Transformer architecture as well as ensembling and self-supervised learning techniques. Exploiting these techniques for the challenge, we achieved second place out of the student teams, and fifth place overall without relying on any a priori knowledge of the physics of the asteroid system.
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.
2021
Stevenson, Emma; Rodriguez-Fernandez, Victor; Urrutxua, Hodei; Morand, Vincent; Camacho, David
Self-supervised machine learning based approach to orbit modelling applied to space traffic management Proceedings Article
In: 11th International Association for the Advancement of Space Safety Conference (IAASS), (Virtual), Osaka, Japan, 2021.
Abstract | BibTeX | Tags: Machine Learning, Orbits, Self-supervised Learning, Space Debris, Space Traffic Management
@inproceedings{stevenson2021_iaass,
title = {Self-supervised machine learning based approach to orbit modelling applied to space traffic management},
author = {Emma Stevenson and Victor Rodriguez-Fernandez and Hodei Urrutxua and Vincent Morand and David Camacho},
year = {2021},
date = {2021-10-01},
booktitle = {11th International Association for the Advancement of Space Safety Conference (IAASS)},
address = {(Virtual), Osaka, Japan},
abstract = {This paper presents a novel methodology for improving the performance of machine learning based space traffic management tasks through the use of a pre-trained orbit model. Taking inspiration from BERT-like self-supervised language models in the field of natural language processing, we introduce ORBERT, and demonstrate the ability of such a model to leverage large quantities of readily available orbit data to learn meaningful representations that can be used to aid in downstream tasks. As a proof of concept of this approach we consider the task of all vs. all conjunction screening, phrased here as a machine learning time series classification task. We show that leveraging unlabelled orbit data leads to improved performance, and that the proposed approach can be particularly beneficial for tasks where the availability of labelled data is limited.},
keywords = {Machine Learning, Orbits, Self-supervised Learning, Space Debris, Space Traffic Management},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper presents a novel methodology for improving the performance of machine learning based space traffic management tasks through the use of a pre-trained orbit model. Taking inspiration from BERT-like self-supervised language models in the field of natural language processing, we introduce ORBERT, and demonstrate the ability of such a model to leverage large quantities of readily available orbit data to learn meaningful representations that can be used to aid in downstream tasks. As a proof of concept of this approach we consider the task of all vs. all conjunction screening, phrased here as a machine learning time series classification task. We show that leveraging unlabelled orbit data leads to improved performance, and that the proposed approach can be particularly beneficial for tasks where the availability of labelled data is limited.