The miniJPAS survey quasar selection II: Machine learning classification with photometric measurements and uncertainties

Abstract

Astrophysical surveys rely heavily on the classification of sources as stars, galaxies or quasars from multi-band photometry. Surveys in narrow-band filters allow for greater discriminatory power, but the variety of different types and redshifts of the objects present a challenge to standard template-based methods. In this work, which is part of larger effort that aims at building a catalogue of quasars from the miniJPAS survey, we present a Machine Learning-based method that employs Convolutional Neural Networks (CNNs) to classify point-like sources including the information in the measurement errors. We validate our methods using data from the miniJPAS survey, a proof-of-concept project of the J-PAS collaboration covering $\sim$ 1 deg${}^2$ of the northern sky using the 56 narrow-band filters of the J-PAS survey. Due to the scarcity of real data, we trained our algorithms using mocks that were purpose-built to reproduce the distributions of different types of objects that we expect to find in the miniJPAS survey, as well as the properties of the real observations in terms of signal and noise. We compare the performance of the CNNs with other well-established Machine Learning classification methods based on decision trees, finding that the CNNs improve the classification when the measurement errors are provided as inputs. The predicted distribution of objects in miniJPAS is consistent with the putative luminosity functions of stars, quasars and unresolved galaxies. Our results are a proof-of-concept for the idea that the J-PAS survey will be able to detect unprecedented numbers of quasars with high confidence.

arXiv comment16 pages, 15 figures, published by MNRAS

References in corpus (44)

• XGBoost: A Scalable Tree Boosting System
• The Wide-field Infrared Survey Explorer (WISE): Mission Description and Initial On-orbit Performance
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The 2dF Galaxy Redshift Survey: Power-spectrum analysis of the final dataset and cosmological implications
• The Baryon Oscillation Spectroscopic Survey of SDSS-III
• The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Cosmological Implications from two Decades of Spectroscopic Surveys at the Apache Point observatory
• Spectroscopic Target Selection in the Sloan Digital Sky Survey: The Quasar Sample
• The WiggleZ Dark Energy Survey: Joint measurements of the expansion and growth history at z < 1
• The SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Overview and Early Data
• The DEEP2 Galaxy Redshift Survey: Design, Observations, Data Reduction, and Redshifts
• Extragalactic Science, Cosmology and Galactic Archaeology with the Subaru Prime Focus Spectrograph (PFS)
• The All-wavelength Extended Groth Strip International Survey (AEGIS) Data Sets
• Cosmology from cosmic shear power spectra with Subaru Hyper Suprime-Cam first-year data
• The COMBO-17 Survey: Evolution of the Galaxy Luminosity Function from 25,000 Galaxies with 0.2<z<1.2
• The Sloan Digital Sky Survey Quasar Catalog: twelfth data release
• Measurement of BAO correlations at $z=2.3$ with SDSS DR12 \lya-Forests
• The clustering of the SDSS-IV extended Baryon Oscillation Spectroscopic Survey DR14 quasar sample: First measurement of Baryon Acoustic Oscillations between redshift 0.8 and 2.2
• Efficient Photometric Selection of Quasars from the Sloan Digital Sky Survey: II. ~1,000,000 Quasars from Data Release Six
• Baryon acoustic oscillations from the complete SDSS-III Ly$\alpha$-quasar cross-correlation function at $z=2.4$
• The 2dF-SDSS LRG and QSO Survey: the QSO luminosity function at 0.4<z<2.6
• The SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Quasar Target Selection
• Probabilistic Random Forest: A machine learning algorithm for noisy datasets
• Photometric redshifts from SDSS images using a Convolutional Neural Network
• The miniJPAS survey: a preview of the Universe in 56 colours
• The Extended Baryon Oscillation Spectroscopic Survey: Variability Selection and Quasar Luminosity Function
• Deblending and Classifying Astronomical Sources with Mask R-CNN Deep Learning
• Application of Convolutional Neural Networks for Stellar Spectral Classification
• Precise photometric redshifts with a narrow-band filter set: The PAU Survey at the William Herschel Telescope
• SPIDERS: Selection of spectroscopic targets using AGN candidates detected in all-sky X-ray surveys
• The miniJPAS survey: star-galaxy classification using machine learning
• Learning the Relationship between Galaxies Spectra and their Star Formation Histories using Convolutional Neural Networks and Cosmological Simulations
• J-PLUS: photometric calibration of large area multi-filter surveys with stellar and white dwarf loci
• QuasarNET: Human-level spectral classification and redshifting with Deep Neural Networks
• On the discovery of stars, quasars, and galaxies in the Southern Hemisphere with S-PLUS DR2
• Data augmentation for machine learning redshifts applied to SDSS galaxies
• Photometric selection and redshifts for quasars in the Kilo-Degree Survey Data Release 4
• Catalog of quasars from the Kilo-Degree Survey Data Release 3
• WEAVE-QSO: A Massive Intergalactic Medium Survey for the William Herschel Telescope
• The PAU Survey: star-galaxy classification with multi narrow-band data
• ELDAR, a new method to identify AGN in multi-filter surveys: the ALHAMBRA test-case
• Spectroscopic QUasar Extractor and redshift (z) EstimatorSQUEzE I: Methodology
• Black hole virial masses from single-epoch photometry: the miniJPAS test case
• The information of attribute uncertainties: what convolutional neural networks can learn about errors in input data
• A Convolutional Neural Network Approach to Supernova Time-Series Classification

Cited by in corpus (8)

• The wide-field, multiplexed, spectroscopic facility WEAVE: Survey design, overview, and simulated implementation
• The miniJPAS survey quasar selection III: Classification with artificial neural networks and hybridisation
• The miniJPAS Survey: The radial distribution of star formation rates in faint X-ray active galactic nuclei
• Exploring the spatially-resolved capabilities of the J-PAS survey with Py2DJPAS
• Improved source classification and performance analysis using Gaia DR3
• The miniJPAS survey quasar selection IV: Classification and redshift estimation with SQUEzE
• The miniJPAS survey quasar selection V: combined algorithm
• The miniJPAS survey: Dissecting galaxy properties across environments with spatially resolved photometry