Comparison of Ensemble and Linear Algorithms for SDSS17 Astronomical Object Classification Based on Visual Workflows

Authors

  • Muhammad Abdan Rafi Program Studi Sistem Komputer Universitas Komputer Indonesia
  • Hidayat Hidayat Universitas Komputer Indonesia image/svg+xml
  • Siti Ar-rachmi Ningrum Program Studi Sistem Komputer Universitas Komputer Indonesia
  • Febhi Aditiya Program Studi Sistem Komputer Universitas Komputer Indonesia

DOI:

https://doi.org/10.58466/5q5sc311

Abstract

Modern astronomical surveys such as the Sloan Digital Sky Survey (SDSS) generate mas-sive datasets that require efficient automated classification techniques. This study evaluates the performance of Random Forest, XGBoost, and Logistic Regression in classifying stars, galaxies, and quasars using the SDSS17 dataset. Unlike previous studies that primarily focused on classification accuracy, this research emphasizes model interpretability and data efficiency through a visual workflow approach implemented in Orange Data Mining. The experimental process includes data preprocessing, feature selection, and cross-validation on 100,000 samples. The results indicate that Random Forest achieved the best and most stable performance, reaching an accuracy of 97.7%. Learning curve analysis revealed model convergence when using approximately 60% of the train-ing data, indicating optimal computational efficiency. Furthermore, feature importance analysis identified redshift as the most influential feature, which is scientifically consistent with Hubble’s Law in distinguishing local and extragalactic objects. These findings demonstrate that ensemble-based models not only provide superior statistical performance but also offer meaningful astro-nomical explanations. The integration of performance evaluation and Explainable Artificial Intelli-gence (XAI) contributes to the development of transparent, interpretable, and reproducible astro-nomical classification systems.

References

[1] Abdurro’uf et al., “The Seventeenth Data Release of the Sloan Digital Sky Surveys: Complete Release of MaNGA, MaStar, and APOGEE-2 Data,” Astrophys. J. Suppl. Ser., vol. 259, no. 2, p. 35, 2022, doi: 10.3847/1538-4365/ac4414.

[2] O. J. Pérez Cruz, C. A. Martínez Pinto, S. G. Navarro Jiménez, L. J. Corral Escobedo, and M. M. Outeiro, “Analyzing Supervised Machine Learning Models for Classifying Astronomical Objects Using Gaia DR3 Spectral Features,” Appl. Sci., vol. 14, no. 19, 2024, doi: 10.3390/app14199058.

[3] J. V. Rodríguez, I. Rodríguez-Rodríguez, and W. L. Woo, “On the application of machine learning in astronomy and astrophysics: A text-mining-based scientometric analysis,” Wiley Interdiscip. Rev. Data Min. Knowl. Discov., vol. 12, no. 5, pp. 1–32, 2022, doi: 10.1002/widm.1476.

[4] J. L. Solorio-Ramírez, R. Jiménez-Cruz, Y. Villuendas-Rey, and C. Yáñez-Márquez, “Random forest Algorithm for the Classification of Spectral Data of Astronomical Objects,” Algorithms, vol. 16, no. 6, 2023, doi: 10.3390/a16060293.

[5] B. Arroquia-Cuadros, N. Sánchez, V. Gómez, P. Blay, V. Martinez-Badenes, and L. Nieves-Seoane, “Photometric classification of quasars from Alhamra survey using random forest,” Astron. Astrophys., vol. 673, no. 45531, pp. 1–7, 2023, doi: 10.1051/0004-6361/202245531.

[6] F. Z. Zeraatgari et al., “Machine learning-based photometric classification of galaxies , quasars , emission-line galaxies , and stars,” Mon. Not. R. Astron. Soc., vol. 4689, no. v, pp. 4677–4689, 2024.

[7] D. W. Hosmer, S. Lemeshow, and R. X. Sturdivant, Applied Logistic Regression, 3rd ed. John Wiley & Sons, Inc., Hoboken, New Jersey, 2013.

[8] G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning: With Applications in R. 2013.

[9] M. Wierzbiński, P. Pławiak, M. Hammad, and U. R. Acharya, “Development of accurate classification of heavenly bodies using novel machine learning techniques,” Soft Comput., vol. 25, no. 10, pp. 7213–7228, 2021, doi: 10.1007/s00500-021-05687-4.

[10] C. Molnar, “Interpretable machine learning: A guide for making black box models explainable . christophm. github. io/interpretable-ml-book,” Samek, W., Montavon, G., Lapuschkin, S., Anders, CJ, Müller, KR (2021). Explain. Deep neural networks beyond A Rev. methods Appl. Proc. IEEE, vol. 109, no. 3, pp. 247–278, 2022.

[11] S. M. Lundberg and S. I. Lee, “A unified approach to interpreting model predictions,” Adv. Neural Inf. Process. Syst., vol. 2017-Decem, no. Section 2, pp. 4766–4775, 2017.

[12] R. Dwivedi et al., “Explainable AI (XAI): Core Ideas, Techniques, and Solutions,” ACM Comput. Surv., vol. 55, no. 9, 2023, doi: 10.1145/3561048.

[13] L. Rimoldini et al., “Gaia Data Release 3: All-sky classification of 12.4 million variable sources into 25 classes,” Astron. Astrophys., vol. 674, no. 2018, 2023, doi: 10.1051/0004-6361/202245591.

[14] G. Li, Z. Lu, J. Wang, and Z. Wang, “Machine Learning in Stellar Astronomy: Progress up to 2024,” no. Ml, pp. 1–14, 2025.

[15] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition (Springer Series in Statistics). Springer, 2009.

[16] L. Breiman, “Random Forests,” Mach. Learn., vol. 45, pp. 5–32, 2001, doi: 10.1023/A:1010950718922.

[17] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., vol. 13-17-Augu, pp. 785–794, 2016, doi: 10.1145/2939672.2939785.

[18] Y. W. Wu, “Machine Learning Classification of Stars, Galaxies, and Quasars,” MATTER Int. J. Sci. Technol., vol. 6, no. 3, pp. 102–122, 2021, doi: 10.20319/mijst.2021.63.102122.

[19] M. A. H. Bin Muhamad Suwaid, M. ‘Ilyas A. Ab Karim, R. Hassan, and A. Abdul Aziz, “Automated Classification of Celestial Objects Using Machine Learning,” Int. J. Perceptive Cogn. Comput., vol. 11, no. 2, pp. 22–41, 2025, doi: 10.31436/ijpcc.v11i2.537.

[20] E. Scornet, “Trees, forests, and impurity-based variable importance in regression,” Ann. l’institut Henri Poincare Probab. Stat., vol. 59, no. 1, pp. 21–52, 2023, doi: 10.1214/21-AIHP1240.

[21] H. I. Aysel, X. Cai, and A. Prugel-Bennett, “Explainable Artificial Intelligence: Advancements and Limitations,” Appl. Sci., vol. 15, no. 13, pp. 1–26, 2025, doi: 10.3390/app15137261.

[22] P. A. C. Cunha and A. Humphrey, “Photometric redshift-aided classification using ensemble learning,” Astron. Astrophys., vol. 666, pp. 1–10, 2022, doi: 10.1051/0004-6361/202243135.

Published

2026-11-21

Issue

Section

Artikel

How to Cite

Comparison of Ensemble and Linear Algorithms for SDSS17 Astronomical Object Classification Based on Visual Workflows. (2026). Applied Information Technology and Computer Science (AICOMS), 5(1). https://doi.org/10.58466/5q5sc311

Most read articles by the same author(s)