Comparative Analysis of Machine Learning Models for Hazardous Asteroid Classification

Nandika P S, Lakshana S, Shruti Lakshmi V, Manju Venugopalan

2025

Abstract

Automating the classification of hazardous asteroids is crucial for planetary defense, enabling timely and accurate threat assessment. This study delves into leveraging machine learning models to classify hazardous asteroids comprehensively. Utilizing a dataset rich in features like absolute magnitude and orbital parameters, the research navigates through preprocessing, feature selection, model selection, and evaluation stages. Through meticulous preprocessing, the dataset is refined to ensure optimal performance in subsequent mod-elling endeavors. Sophisticated feature selection techniques identify the most discriminative features crucial for accurate asteroid classification. Various algorithms, including Decision Tree, AdaBoost, and CAT Boost, are evaluated across different metrics. AdaBoost and Random Forest emerges as a standout performer, demonstrating superior performance with an F1 score of 0.87 and 0.88 AdaBoost achieves an accuracy rate of 95 respectively, highlighting its robustness and potential as a formidable tool in planetary defense. These findings underscore the critical role of precise asteroid classification in mitigating potential threats to planetary safety by enabling proactive measures against identified hazardous asteroids.

Paper Citation

in Harvard Style

P S N., S L., V S. and Venugopalan M. (2025). Comparative Analysis of Machine Learning Models for Hazardous Asteroid Classification. In Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT; ISBN 978-989-758-763-4, SciTePress, pages 642-648. DOI: 10.5220/0013599400004664

in Bibtex Style

@conference{incoft25,
author={Nandika P S and Lakshana S and Shruti Lakshmi V and Manju Venugopalan},
title={Comparative Analysis of Machine Learning Models for Hazardous Asteroid Classification},
booktitle={Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT},
year={2025},
pages={642-648},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013599400004664},
isbn={978-989-758-763-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Futuristic Technology - Volume 2: INCOFT
TI - Comparative Analysis of Machine Learning Models for Hazardous Asteroid Classification
SN - 978-989-758-763-4
AU - P S N.
AU - S L.
AU - V S.
AU - Venugopalan M.
PY - 2025
SP - 642
EP - 648
DO - 10.5220/0013599400004664
PB - SciTePress