View in EDS

Temporary Captures in Earth-Moon System: A Taxonomy Design using Machine Learning.

Saved in:
Bibliographic Details
Title: Temporary Captures in Earth-Moon System: A Taxonomy Design using Machine Learning.
Authors: Wolfe, Sean1 (AUTHOR), Emami, M. Reza1 (AUTHOR) reza.emami@utoronto.ca
Source: Journal of the Astronautical Sciences. Dec2024, Vol. 71 Issue 6, p1-45. 45p.
Abstract: A taxonomy design methodology is proposed for the classification and dynamic behaviour representation of the population of asteroids that are temporarily captured in the Earth-Moon system. Through numerical analysis using a database of over 20000 synthetic temporary captures, a critical review of current taxonomies is presented first, which suggests that there may not be a single taxonomy that can describe the population consistently and comprehensively. Therefore, the premise of the proposed methodology is that for every set of mission metrics defined for an exploration mission, a specific taxonomy should be designed that is viable for the sought mission. Given the mission metrics, the design methodology utilizes machine learning techniques to determine a set of features that can best describe the dynamic behaviour of the population of temporarily captured asteroids. A voting classifier is developed for the taxonomy design, using the histogram gradient boosting and random forest classifiers, through the analysis of various scenarios for feature selection. A case study illustrates the taxonomy design process, where viable features are selected out of a number of 50 features, given two mission metrics, namely, the minimum distance the asteroid reaches from Earth and the amount of time the asteroid remains inside the sphere with one Earth Hill radius. [ABSTRACT FROM AUTHOR]
Copyright of Journal of the Astronautical Sciences is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:A taxonomy design methodology is proposed for the classification and dynamic behaviour representation of the population of asteroids that are temporarily captured in the Earth-Moon system. Through numerical analysis using a database of over 20000 synthetic temporary captures, a critical review of current taxonomies is presented first, which suggests that there may not be a single taxonomy that can describe the population consistently and comprehensively. Therefore, the premise of the proposed methodology is that for every set of mission metrics defined for an exploration mission, a specific taxonomy should be designed that is viable for the sought mission. Given the mission metrics, the design methodology utilizes machine learning techniques to determine a set of features that can best describe the dynamic behaviour of the population of temporarily captured asteroids. A voting classifier is developed for the taxonomy design, using the histogram gradient boosting and random forest classifiers, through the analysis of various scenarios for feature selection. A case study illustrates the taxonomy design process, where viable features are selected out of a number of 50 features, given two mission metrics, namely, the minimum distance the asteroid reaches from Earth and the amount of time the asteroid remains inside the sphere with one Earth Hill radius. [ABSTRACT FROM AUTHOR]
ISSN:00219142
DOI:10.1007/s40295-024-00473-4