ANNz2 - photometric redshift and probability distribution function estimation using machine learning

TL;DR

ANNz2 is a machine learning software that improves photometric redshift estimation by generating accurate point estimates and full probability distribution functions, addressing issues of training sample incompleteness.

Contribution

It introduces a new implementation of photometric redshift estimation software with enhanced PDF generation and robustness features for incomplete training data.

Findings

Successfully applied to SDSS and BOSS data sets.

Used in Dark Energy Survey weak lensing analysis.

Provides reliable photo-z estimates with uncertainty quantification.

Abstract

We present ANNz2, a new implementation of the public software for photometric redshift (photo-z) estimation of Collister and Lahav (2004), which now includes generation of full probability distribution functions (PDFs). ANNz2 utilizes multiple machine learning methods, such as artificial neural networks and boosted decision/regression trees. The objective of the algorithm is to optimize the performance of the photo-z estimation, to properly derive the associated uncertainties, and to produce both single-value solutions and PDFs. In addition, estimators are made available, which mitigate possible problems of non-representative or incomplete spectroscopic training samples. ANNz2 has already been used as part of the first weak lensing analysis of the Dark Energy Survey, and is included in the experiment's first public data release. Here we illustrate the functionality of the code using data from the tenth data release of the Sloan Digital Sky Survey and the Baryon Oscillation Spectroscopic Survey. The code is available for download at https://github.com/IftachSadeh/ANNZ .