Data-Rich Astronomy: Mining Sky Surveys with PhotoRApToR

TL;DR

This paper introduces PhotoRApToR, a Java-based desktop application designed for photometric redshift estimation and galaxy classification, leveraging machine learning to handle large astronomical datasets from modern sky surveys.

Contribution

It presents PhotoRApToR, a new tool tailored for regression and classification tasks in astronomy, utilizing the MLPQNA algorithm for improved analysis of sky survey data.

Findings

Successful application to SDSS galaxy data (DR9 and DR10)

Effective photometric redshift estimation and galaxy classification

Demonstrated utility of machine learning in data-rich astronomy

Abstract

In the last decade a new generation of telescopes and sensors has allowed the production of a very large amount of data and astronomy has become a data-rich science. New automatic methods largely based on machine learning are needed to cope with such data tsunami. We present some results in the fields of photometric redshifts and galaxy classification, obtained using the MLPQNA algorithm available in the DAMEWARE (Data Mining and Web Application Resource) for the SDSS galaxies (DR9 and DR10). We present PhotoRApToR (Photometric Research Application To Redshift): a Java based desktop application capable to solve regression and classification problems and specialized for photo-z estimation.