Publication

Abstract : Stellar classification is a very important field in astrophysics, in which the stars are classified according to their Photometric bandwidth and Redshift Data. This paper works on finding the best machine learning models for stellar classification of stars for the goal of civilian-led space development. Using a dataset that contains inputs such as photometric bandwidth and Redshift data, the comparison of multiple regression and classification algorithms is done. The models are then tested and evaluated using their performance evaluation metrics. The findings in this paper suggest that classification models such as LightGBM and Random Forest showcase the best implementation. The methods proposed are a scalable and efficient approach to stellar classification of stars and they help in the analysis of a wide range of celestial data using machine learning.