Photometric Redshift Estimation on SDSS Data Using Random Forests

TL;DR

This paper presents a method using Random Forests to estimate galaxy redshifts from SDSS photometric data, achieving accurate and reliable results with well-characterized confidence intervals.

Contribution

The study introduces a novel application of Random Forests for photometric redshift estimation, providing precise and confidence-interval-based predictions.

Findings

Achieved tight RMS scatter limited by photometric errors

Produced nearly Gaussian error distributions for redshift estimates

Provided reliable, galaxy-specific confidence intervals

Abstract

Given multiband photometric data from the SDSS DR6, we estimate galaxy redshifts. We employ a Random Forest trained on color features and spectroscopic redshifts from 80,000 randomly chosen primary galaxies yielding a mapping from color to redshift such that the difference between the estimate and the spectroscopic redshift is small. Our methodology results in tight RMS scatter in the estimates limited by photometric errors. Additionally, this approach yields an error distribution that is nearly Gaussian with parameter estimates giving reliable confidence intervals unique to each galaxy photometric redshift.