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

Abstract

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.

Extracting photometric redshift from galaxy flux and image data using neural networks in the CSST survey

“…procedure. The SED templates applied are also from this catalog, and we extend these templates from ∼ 900 Å to ∼ 90 Å using the BC03 method (Bruzual & Charlot 2003) to include the fluxes of high-z galaxies in all CSST photometric bands, where details can be found in Cao et al (2018). About 100, 000 high quality galaxies with reliable photo-z measurement are selected.…”

Machine Learning for Observational Cosmology

“…Photometric redshift estimation is also a crucial task for galaxy surveys, and a wide range of ML applications have been explored (see Refs. [79,80] for recent development). ML can also be used to identify specific galaxy images such as strong gravitational lensing effect [81] and galaxy merger remnants [82], to detect anomalous objects [83], to deblend multiple objects [84,85], and to deconvolve point spread functions [86].…”

Exploring New Redshift Indicators for Radio-Powerful AGN

“…It represents the number of predictions that are too far away from the true value over the total number of prediction. There are several ways to define this value [51][52][53][54]. We will make use of the interpretation by Hildebrandt et al [51], which considers all predictions that fulfil the following condition to be outliers:…”