Performance Comparison of Supervised Machine Learning Methods in Classifying Celestial Objects

Abstract

In recent times, astronomy has entered a new era with rapidly growing data sources and advanced observation techniques. The construction of powerful telescopes has enabled the collection of spectral data from millions of celestial objects. However, the increasing number and variety of data have made it challenging to categorize these celestial objects. This study employs machine learning methods to address the fundamental problem of classifying stars, galaxies, and quasars in astronomy. The dataset underwent detailed preprocessing to identify effective features for classification. KNIME Analytics Platform was used for data analysis and visualization, facilitating rapid and efficient data analysis through its drag-and-drop interface. Among the machine learning methods used in our study—Decision Trees, Random Forest, and Naive Bayes—the highest accuracy rate of 97.86% was achieved with the Random Forest model. Notably, despite its lower overall performance compared to other models, the Naive Bayes classifier exhibited superior performance in distinguishing the STAR class, which is one of the study's interesting findings. Future studies aim to enhance model accuracy by using larger and more diverse datasets and exploring different machine learning algorithms. Additionally, the impact of deep learning methods on classification performance will be investigated.

Keywords

• Machine learning
• Classification
• Decision tree
• Naive Bayes
• Random forest

References

1. Brice MJ. 2019. Classification of stars from redshifted stellar spectra utilizing machine learning. MSc Thesis, Central Washington University, Computational Science, Washington, US, pp: 73.
2. Chen YC. 2018. Lecture 6: Density Estimation: Histogram and Kernel Density Estimator. URL= http://faculty.washington.edu/yenchic/18W_425/Lec6_hist_KDE.pdf (accessed date: May 10, 2024).
3. Clarke AO, Scaife AMM, Greenhalgh R, Griguta V. 2020. Identifying galaxies, quasars, and stars with machine learning: A new catalogue of classifications for 111 million SDSS sources without spectra. Astronomy Astrophys, 639: A84.
4. Erickson BJ, Kitamura F. 2021. Magician’s corner: 9. Performance metrics for machine learning models. Radiol Artif Intel, 3(3): e200126.
5. Fedesoriano. 2022. Stellar Classification Dataset-SDSS17. URL= https://www.kaggle.com/fedesoriano/stellar-classification-dataset-sdss17 (accessed date: May 15, 2024).
6. Fillbrunn A, Dietz C, Pfeuffer J, Rahn R, Landrum GA, Berthold MR. 2017. KNIME for reproducible cross-domain analysis of life science data. J Biotechnol, 261: 149-156.
7. Haghighi MHZ. 2023. Analyzing astronomical data with machine learning techniques. arXiv Preprint, arXiv: 2302.11573.
8. Hughes AC, Bailer-Jones CA, Jamal S. 2022. Quasar and galaxy classification using Gaia EDR3 and CatWise2020. Astronomy Astrophys, 668: A99.

9. Huichaqueo MO, Orrego RM. 2022. Automatic spectral classification of stars using machine learning: An approach based on the use of unbalanced data. Machine Learn Appl, 9(4): 01-16.
10. Kumar A, Gharat S. 2023. Star cassification: A deep learning approach for ıdentifying binary and exoplanet stars. arXiv Preprint, arXiv: 2301.13115.
11. Li J, Zhu Q, Wu Q, Zhang Z, Gong Y, He Z, Zhu F. 2021. SMOTE-NaN-DE: Addressing the noisy and borderline examples problem in imbalanced classification by natural neighbors and differential evolution. Know Based Syst, 223: 107056.
12. Mehta T, Bhuta N, Shinde S. 2022. Experimental analysis of stellar classification by using different machine learning algorithms. 2022 International Conference on Industry 4.0 Technology (I4Tech), September 23-24, Pune, India, pp: 1-8.
13. Mouchel‐Vallon C, Hodzic A. 2023. Toward emulating an explicit organic chemistry mechanism with random forest models. J Geophys Res Atmospheres, 128(10): e2022JD038227.
14. Omat D, Otey J, Al-Mousa A. 2022. Stellar objects classification using supervised machine learning techniques. International Arab Conference on Information Technology (ACIT), November 22-24, Abu Dhabi, United Arab Emirates, pp: 1-8.
15. Ramana PV. 2022. Naïve Bayes to machine learning approach for structural dynamic complications. ASPS Conf Proc, 1(4): 1283-1291.
16. Savyanavar AS, Mhala N, Sutar SH. 2023. Star-galaxy classification using machine learning algorithms and deep learning. Int J Info Technol Secur, 15(2): 87-96.
17. Thomas T, Vijayaraghavan P, Emmanuel A, Thomas S, Vijayaraghavan TP, Emmanuel S. 2020. Applications of decision trees. Machine Learn Appr Cyber Secur Analyt, 2020: 157-184.