2003/11/30 by Adrian A. Collister, Adrian A. Collister, Ofer Lahav · 10 citations
Computer Science · Physics and Astronomy · #Astronomy and Astrophysical Research #Galaxies: Formation, Evolution, Phenomena #Gaussian Processes and Bayesian Inference #astro-ph
paper · pdf · doi:10.1086/383254
published as Publ.Astron.Soc.Pac.116:345-351,2004 · 6 pages, 6 figures. Replaced to match version accepted by PASP (minor changes to original submission). The ANNz package may be obtained from http://www.ast.cam.ac.uk/~aac
arxiv created 2004/02/27 · openalex publication_date 2004/04/01 · arxiv updated 2009/12/01 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/30
We introduce ANN z , a freely available software package for photometric redshift estimation using artificial neural networks. ANN z learns the relation between photometry and redshift from an appropriate training set of galaxies for which the redshift is already known. Where a large and representative training set is available, ANN z is a highly competitive tool when compared with traditional template‐fitting methods. The ANN z package is demonstrated on the Sloan Digital Sky Survey Data Release 1, and for this particular data set the rms redshift error in the range 0≲z≲0.7 is σ rms = 0.023. Nonideal conditions (spectroscopic sets that are small or brighter than the photometric set for which redshifts are required) are simulated, and the impact on the photometric redshift accuracy is assessed. 2