Abstract :
A complete and satisfactory understanding of the processes that led to the formation and evolution of the variety of today’s galaxy types is still beyond our reach. To solve this problem, we need both large datasets reaching high redshifts and novel methodologies for dealing with them. The recent cutting-edge Dark Energy Spectroscopic Instrument (DESI) has already observed ~20 million galaxies, more than the combination of any other previous study, and it is just starting. The first step is now to uncover intricate patterns and variations concealed within their spectra, enabling us to classify them into well-known categories such as passive, star-forming, and active galactic nuclei (AGN) galaxies. By harnessing the power of unsupervised machine-learning algorithms, we automate and enhance the process of categorizing galaxies transcending the limitations of standardly used classifications. This will not only help us unravel the secrets of galaxy evolution but will also provide us with a more refined understanding of the AGN population and its distinct characteristics among other galaxy classes.