Photometric Redshift Estimation with Galaxy Morphology Using Self-organizing Maps

We use multiband optical and near-infrared photometric observations of galaxies in the Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey to predict photometric redshifts using artificial neural networks. The multiband observations span from 0.39 to 8.0 mu m for a sample of similar to 1000 galaxies in the GOODS-S field for which robust size measurements are available from Hubble Space Telescope Wide Field Camera 3 observations. We use self-organizing maps (SOMs) to map the multidimensional photometric and galaxy size observations while taking advantage of existing spectroscopic redshifts at 0 z < 2 for independent training and testing sets. We show that use of photometric and morphological data led to redshift estimates comparable to redshift measurements from modeling of spectral energy distributions and from SOMs without morphological measurements.