Photometric Redshifts With Machine Learning, Lights and Shadows on a Complex Data Science Use Case

The importance of the current role of data-driven science is constantly increasing within Astrophysics, due to the huge amount of multi-wavelength data collected every day, characterized by complex and high-volume information requiring efficient and, as much as possible, automated exploration tools. Furthermore, to accomplish main and legacy science objectives of future or incoming large and deep survey projects, such as James Webb Space Telescope (JWST), James Webb Space Telescope (LSST), and Euclid, a crucial role is played by an accurate estimation of photometric redshifts, whose knowledge would permit the detection and analysis of extended and peculiar sources by disentangling low-z from high-z sources and would contribute to solve the modern cosmological discrepancies. The recent photometric redshift data challenges, organized within several survey projects, like LSST and Euclid, pushed the exploitation of the observed multi-wavelength and multi-dimensional data or ad hoc simulated data to improve and optimize the photometric redshifts prediction and statistical characterization based on both Spectral Energy Distribution (SED) template fitting and machine learning methodologies. They also provided a new impetus in the investigation of hybrid and deep learning techniques, aimed at conjugating the positive peculiarities of different methodologies, thus optimizing the estimation accuracy and maximizing the photometric range coverage, which are particularly important in the high-z regime, where the spectroscopic ground truth is poorly available. In such a context, we summarize what was learned and proposed in more than a decade of research.