Mining the SDSS archive. I. Photometric redshifts in the nearby universe.

In this paper we present a supervised neural network approach to the deter-mination of photometric redshifts. The method, even though of general validity, was fine tuned to match the characteristics of the Sloan Digital Sky Survey (S-DSS) and as base of ’a priori ’ knowledge, it exploits the rich wealth of spectro-scopic redshifts provided by this unique survey. In order to train, validate and test the networks, we used two galaxy samples drawn from the SDSS spectro-scopic dataset, namely: the general galaxy sample (GG) and the luminous red galaxies subsample (LRG). Due to the uneven distribution of measured redshifts in the SDSS spectroscopic subsample, the method consists of a two steps ap-proach. In the first step, objects are classified in nearby (z < 0.25) and distant (0.25 < z < 0.50), with an accuracy estimated in 97.52%. In the second step two different networks are separately trained on objects belonging to the two red-shift ranges. Using a standard Multi Layer Perceptron operated in a Bayesian framework, the optimal architectures were found to require 1 hidden layer of 24 (24) and 24 (25) neurons for the GG (LRG) sample. The presence of systematic deviations was then corrected by interpolating the resulting redshifts. The final results on the GG dataset give a robust σz 0.0208 over the redshift range [0.01, 0.48] and σz 0.0197 and σz 0.0238 for the nearby and distant samples respectively. For the LRG subsample we find instead a robust σz 0.0164 over the whole range, and σz 0.0160, σz 0.0183 for the nearby and distant samples respectively. After training, the networks have been applied to all objects in the SDSS Table GALAXY matching the same selection criteri