Machine learning meets the redshift evolution of the CMB temperature

We present a model independent and non-parametric reconstruction with a Machine Learning algorithm of the redshift evolution of the Cosmic Microwave Background (CMB) temperature from a wide redshift range z 0, 3 without assuming any dark energy model, an adiabatic universe or photon number conservation. In particular we use the genetic algorithms which avoid the dependency on an initial prior or a cosmological fiducial model. Through our reconstruction we constrain new physics at late times. We provide novel and updated estimates on the parameter from the parametrisation T (z) =T₀ (1+z) ^1-, the duality relation (z) and the cosmic opacity parameter (z). Furthermore we place constraints on a temporal varying fine structure constant, which would have signatures in a broad spectrum of physical phenomena such as the CMB anisotropies. Overall we find no evidence of deviations within the 1 region from the well established model, thus confirming its predictive potential.