Detection of Black Holes from Stellar Datasets Using Machine Learning

One of the universe's most mysterious things is still black holes, due to their enormous gravity. Black holes are cosmic giants with enormous gravitational force that have event horizons beyond which light cannot escape. Because of the enormous timescales involved and the limitations of the present observational capabilities, it is challenging to directly observe the collapse of a large star into a black hole. Identifying black holes by traditional methods involves measuring their gravitational pull-on neighboring stars, spotting emissions from accretion disks around them, and obtaining gravity wave signatures. However, these approaches frequently depend on specialized tools. In astronomical research, machine learning has proven to be an effective tool, especially in the evaluation of large datasets and spotting minute trends. Here, machine learning has been used to categorize transitory astronomical occurrences, forecast star flares, and identify galaxies. Using machine learning methods, we trained multiple models to categorize possible black hole candidates based on stellar data analysis, this study expands this foundation. This research is based on astronomical concepts such as mass-radius correlations and star brightness using the old Morgan-Keenan (MK) classification system.