Ensemble Learning Based Models for Planet Classification

Xiyue Wang

2024

Abstract

Astronomers explore various phenomena and laws in the universe through observation, experimentation, and theoretical models to gain a deeper understanding of the structure, composition, and evolution of the universe. There are many unanswered questions in astronomy, such as how to properly classify planets. At the same time, appropriate classification methods can deepen people's understanding of astronomy. In the past, many scholars have speculated on classification criteria. The purpose of this study is to explore a satisfactory model for planet classification and provide a reliable reference for subsequent researchers. Furthermore, this article utilizes a variety of machine learning methods and deep learning models, including Linear Regression, Principal Component Analysis, Linear Support Vector Machine, Random Forest, XGBoost Regression and Artificial Neural Network. Among all models, ensemble learning methods Random Forest and XGBoost produce the best results, the former of which achieved an adjusted of 0.96 and XGBoost obtained an adjusted of 0.95. In addition, we make estimates for future research and provide improvements.

Paper Citation

in Harvard Style

Wang X. (2024). Ensemble Learning Based Models for Planet Classification. In Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA; ISBN 978-989-758-722-1, SciTePress, pages 60-67. DOI: 10.5220/0012992000004601

in Bibtex Style

@conference{iampa24,
author={Xiyue Wang},
title={Ensemble Learning Based Models for Planet Classification},
booktitle={Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA},
year={2024},
pages={60-67},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012992000004601},
isbn={978-989-758-722-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA
TI - Ensemble Learning Based Models for Planet Classification
SN - 978-989-758-722-1
AU - Wang X.
PY - 2024
SP - 60
EP - 67
DO - 10.5220/0012992000004601
PB - SciTePress