Photometric redshifts for the Kilo-Degree Survey. Machine-learning analysis with artificial neural networks

Abstract

We present a machine-learning photometric redshift analysis of the Kilo-Degree Survey Data Release 3, using two neural-network based techniques: ANNz2 and MLPQNA. Despite limited coverage of spectroscopic training sets, these ML codes provide photo-zs of quality comparable to, if not better than, those from the BPZ code, at least up to zphot<0.9 and r<23.5. At the bright end of r<20, where very complete spectroscopic data overlapping with KiDS are available, the performance of the ML photo-zs clearly surpasses that of BPZ, currently the primary photo-z method for KiDS. Using the Galaxy And Mass Assembly (GAMA) spectroscopic survey as calibration, we furthermore study how photo-zs improve for bright sources when photometric parameters additional to magnitudes are included in the photo-z derivation, as well as when VIKING and WISE infrared bands are added. While the fiducial four-band ugri setup gives a photo-z bias $\delta z=-2e-4$ and scatter ${\sigma }_z<0.022$ at mean z = 0.23, combining magnitudes, colours, and galaxy sizes reduces the scatter by ~7% and the bias by an order of magnitude. Once the ugri and IR magnitudes are joined into 12-band photometry spanning up to 12 $\mu$, the scatter decreases by more than 10% over the fiducial case. Finally, using the 12 bands together with optical colours and linear sizes gives $\delta z<4e-5$ and ${\sigma }_z<0.019$. This paper also serves as a reference for two public photo-z catalogues accompanying KiDS DR3, both obtained using the ANNz2 code. The first one, of general purpose, includes all the 39 million KiDS sources with four-band ugri measurements in DR3. The second dataset, optimized for low-redshift studies such as galaxy-galaxy lensing, is limited to r<20, and provides photo-zs of much better quality than in the full-depth case thanks to incorporating optical magnitudes, colours, and sizes in the GAMA-calibrated photo-z derivation.

arXiv commentA&A, in press. Data available from the KiDS website http://kids.strw.leidenuniv.nl/DR3/ml-photoz.php#annz2

References in corpus (92)

• Maps of Dust IR Emission for Use in Estimation of Reddening and CMBR Foregrounds
• The NumPy array: a structure for efficient numerical computation
• The Sloan Digital Sky Survey: Technical Summary
• The Wide-field Infrared Survey Explorer (WISE): Mission Description and Initial On-orbit Performance
• The Baryon Oscillation Spectroscopic Survey of SDSS-III
• EAZY: A Fast, Public Photometric Redshift Code
• Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe
• Bayesian photometric redshift estimation
• The COSMOS2015 Catalog: Exploring the 1<z<6 Universe with half a million galaxies
• Galaxy and Mass Assembly (GAMA): survey diagnostics and core data release
• The Hyper Suprime-Cam SSP Survey: Overview and Survey Design
• KiDS-450: Cosmological parameter constraints from tomographic weak gravitational lensing
• The SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Overview and Early Data
• The DEEP2 Galaxy Redshift Survey: Design, Observations, Data Reduction, and Redshifts
• Galaxy And Mass Assembly (GAMA): end of survey report and data release 2
• The WiggleZ Dark Energy Survey: Survey Design and First Data Release
• The Thirteenth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-IV Survey MApping Nearby Galaxies at Apache Point Observatory
• ANNz: estimating photometric redshifts using artificial neural networks
• Gravitational Lensing Analysis of the Kilo Degree Survey
• The Kilo-Degree Survey
• The VIMOS Public Extragalactic Redshift Survey (VIPERS). An unprecedented view of galaxies and large-scale structure at 0.5<z<1.2
• CFHTLenS: Improving the quality of photometric redshifts with precision photometry
• KiDS-450 + 2dFLenS: Cosmological parameter constraints from weak gravitational lensing tomography and overlapping redshift-space galaxy clustering
• The first and second data releases of the Kilo-Degree Survey
• Faint Blue Galaxies
• Effect of Photometric Redshift Uncertainties on Weak Lensing Tomography
• PHAT: PHoto-z Accuracy Testing
• KiDS+GAMA: Cosmology constraints from a joint analysis of cosmic shear, galaxy-galaxy lensing and angular clustering
• Galaxy And Mass Assembly (GAMA): Mid-Infrared Properties and Empirical Relations from $WISE$
• 2MASS Photometric Redshift catalog: a comprehensive three-dimensional census of the whole sky
• The third data release of the Kilo-Degree Survey and associated data products
• redMaGiC: Selecting Luminous Red Galaxies from the DES Science Verification Data
• Estimating the Redshift Distribution of Faint Galaxy Samples
• WISE photometry for 400 million SDSS sources
• Mapping the Galaxy Color-Redshift Relation: Optimal Photometric Redshift Calibration Strategies for Cosmology Surveys
• Estimating photometric redshifts with artificial neural networks
• ANNz2 - photometric redshift and probability distribution function estimation using machine learning
• KiDS-450: The tomographic weak lensing power spectrum and constraints on cosmological parameters
• KiDS-450: Testing extensions to the standard cosmological model
• CFHTLenS: The relation between galaxy dark matter haloes and baryons from weak gravitational lensing
• Photometric redshifts for the SDSS Data Release 12
• Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
• ProFound: Source Extraction and Application to Modern Survey Data
• Photometric redshift analysis in the Dark Energy Survey Science Verification data
• Galaxy And Mass Assembly (GAMA): Accurate Panchromatic Photometry from Optical Priors using LAMBDAR
• Dark matter halo properties of GAMA galaxy groups from 100 square degrees of KiDS weak lensing data
• Photometric redshift estimation via deep learning
• Photometric Redshifts in the IRAC Shallow Survey
• The Complete Calibration of the Color-Redshift Relation (C3R2) Survey: Survey Overview and Data Release 1
• WISE x SuperCOSMOS photometric redshift catalog: 20 million galaxies over 3pi steradians
• ArborZ: Photometric Redshifts Using Boosted Decision Trees
• Estimating Photometric Redshifts Using Support Vector Machines
• UV-to-FIR analysis of Spitzer/IRAC sources in the Extended Groth Strip II: Photometric redshifts, Stellar masses and Star formation rates
• The Arizona CDFS Environment Survey (ACES): A Magellan/IMACS Spectroscopic Survey of the Chandra Deep Field South
• The stellar-to-halo mass relation of GAMA galaxies from 100 square degrees of KiDS weak lensing data
• Galaxy and Mass Assembly (GAMA): Exploring the WISE Cosmic Web in G12
• Spectroscopic Needs for Imaging Dark Energy Experiments: Photometric Redshift Training and Calibration
• First discoveries of z~6 quasars with the Kilo Degree Survey and VISTA Kilo-Degree Infrared Galaxy survey
• Photometric redshifts for Quasars in multi band Surveys
• A Bayesian Classifier for Photometric Redshifts: Identification of high redshift clusters
• The 2-degree Field Lensing Survey: design and clustering measurements
• Galaxy And Mass Assembly (GAMA): The galaxy luminosity function within the cosmic web
• METAPHOR: A machine learning based method for the probability density estimation of photometric redshifts
• Galaxy And Mass Assembly (GAMA): Curation and reanalysis of 16.6k redshifts in the G10/COSMOS region
• GaaP: PSF- and aperture-matched photometry using shapelets
• Star/galaxy separation at faint magnitudes: Application to a simulated Dark Energy Survey
• Feature importance for machine learning redshifts applied to SDSS galaxies
• Photometric Redshift Error Estimators
• Neural Networks and Photometric Redshifts
• The masses of satellites in GAMA galaxy groups from 100 square degrees of KiDS weak lensing data
• Morpho-z: improving photometric redshifts with galaxy morphology
• Halo ellipticity of GAMA galaxy groups from KiDS weak lensing
• New Approaches To Photometric Redshift Prediction Via Gaussian Process Regression In The Sloan Digital Sky Survey
• A KiDS weak lensing analysis of assembly bias in GAMA galaxy groups
• Improving Photometric Redshift Estimation using GPz: size information, post processing and improved photometry
• Machine Learning based photometric redshifts for the KiDS ESO DR2 galaxies
• 2dFLenS and KiDS: Determining source redshift distributions with cross-correlations
• Towards a census of super-compact massive galaxies in the Kilo Degree Survey
• Photometric redshift estimation based on data mining with PhotoRApToR
• GAz: A Genetic Algorithm for Photometric Redshift Estimation
• Combining Dark Energy Survey Science Verification Data with Near Infrared Data from the ESO VISTA Hemisphere Survey
• Photometric redshifts with Quasi Newton Algorithm (MLPQNA). Results in the PHAT1 contest
• Dependence of GAMA galaxy halo masses on the cosmic web environment from 100 square degrees of KiDS weak lensing data
• Analysis of a Custom Support Vector Machine for Photometric Redshift Estimation and the Inclusion of Galaxy Shape Information
• Searching for galaxy clusters in the Kilo-Degree Survey
• The Efficacy of Galaxy Shape Parameters in Photometric Redshift Estimation: A Neural Network Approach
• $\mu$--PhotoZ: Photometric Redshifts by Inverting the Tolman Surface Brightness Test
• A New Technique for Galaxy Photometric Redshifts in the Sloan Digital Sky Survey
• Mining the Kilo-Degree Survey for solar system objects
• DAMEWARE: A web cyberinfrastructure for astrophysical data mining
• The 2-degree Field Lensing Survey: photometric redshifts from a large new training sample to r<19.5
• Galaxy Zoo Morphology and Photometric Redshifts in the Sloan Digital Sky Survey

Cited by in corpus (55)

• The fourth data release of the Kilo-Degree Survey: ugri imaging and nine-band optical-IR photometry over 1000 square degrees
• First measurement of the Hubble constant from a dark standard siren using the Dark Energy Survey galaxies and the LIGO/Virgo binary-black-hole merger GW170814
• The galaxy cluster mass scale and its impact on cosmological constraints from the cluster population
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• AMICO galaxy clusters in KiDS-DR3: sample properties and selection function
• Galaxy And Mass Assembly (GAMA): Assimilation of KiDS into the GAMA database
• The Weak Lensing Radial Acceleration Relation: Constraining Modified Gravity and Cold Dark Matter theories with KiDS-1000
• Studying galaxy troughs and ridges using Weak Gravitational Lensing with the Kilo-Degree Survey
• PS1-STRM: Neural network source classification and photometric redshift catalogue for PS1 $3\pi$ DR1
• Bright galaxy sample in the Kilo-Degree Survey Data Release 4: selection, photometric redshifts, and physical properties
• The miniJPAS survey: star-galaxy classification using machine learning
• KiDS-1000: Combined halo-model cosmology constraints from galaxy abundance, galaxy clustering and galaxy-galaxy lensing
• The PAU Survey: Photometric redshifts using transfer learning from simulations
• Catalog of quasars from the Kilo-Degree Survey Data Release 3
• Machine Learning for Observational Cosmology
• Weak-lensing shear measurement with machine learning: teaching artificial neural networks about feature noise
• Improving the reliability of photometric redshift with machine learning
• Photometric redshifts with machine learning, lights and shadows on a complex data science use case
• Galaxy populations in the Hydra I cluster from the VEGAS survey I. Optical properties of a large sample of dwarf galaxies
• GAlaxy Light profile convolutional neural NETworks (GaLNets). I. fast and accurate structural parameters for billion galaxy samples
• Statistical analysis of probability density functions for photometric redshifts through the KiDS-ESO-DR3 galaxies
• Monte Carlo Control Loops for cosmic shear cosmology with DES Year 1
• Luminous red galaxies in the Kilo Degree Survey: selection with broad-band photometry and weak lensing measurements
• Organised Randoms: Learning and correcting for systematic galaxy clustering patterns in KiDS using self-organising maps
• Identification of BASS DR3 Sources as Stars, Galaxies and Quasars by XGBoost
• Inferring galaxy dark halo properties from visible matter with Machine Learning
• The PAU Survey: narrowband photometric redshifts using Gaussian processes
• Measuring the Hubble Constant with cosmic chronometers: a machine learning approach
• Comparison of Observed Galaxy Properties with Semianalytic Model Predictions using Machine Learning
• Searching for AGN and Pulsar Candidates in 4FGL Unassociated Sources Using Machine Learning
• Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry
• Protocluster detection in simulations of HSC-SSP and the 10-year LSST forecast, using PCcones
• The PAU survey: Estimating galaxy photometry with deep learning
• Galaxy and Mass Assembly (GAMA): A $\text{WISE}$ study of the activity of emission-line systems in G23
• The miniJPAS survey: clusters and galaxy groups detection with AMICO
• Photometric redshifts and intrinsic alignments: degeneracies and biases in 3$\times$2pt analysis
• Self-calibration method for II and GI types of intrinsic alignments of galaxies
• An adapted filter function for density split statistics in weak lensing
• Morphology-assisted galaxy mass-to-light predictions using deep learning
• Estimation of Photometric Redshifts. I. Machine Learning Inference for Pan-STARRS1 Galaxies Using Neural Networks
• The PAU Survey: Background light estimation with deep learning techniques
• The alignment of galaxies at the Baryon Acoustic Oscillation scale
• Halo shapes constrained from a pure sample of central galaxies in KiDS-1000
• Improved photometric redshifts with colour-constrained galaxy templates for future wide-area surveys
• Enhancing Photometric Redshift Catalogs Through Color-Space Analysis: Application to KiDS-Bright Galaxies
• Predicting bulge to total luminosity ratio of galaxies using deep learning
• Radio-Optical Galaxy Shape and Shear Correlations in the COSMOS Field using 3 GHz VLA Observations
• CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation
• Intrinsic alignment from multiple shear estimates: A first application to data and forecasts for Stage IV
• Principal Components for Model-Agnostic Modified Gravity with 3x2pt
• Z-Sequence: Photometric redshift predictions for galaxy clusters with sequential random k-nearest neighbours
• Improving Photometric Redshifts by Merging Probability Density Functions from Template-Based and Machine Learning Algorithms
• The Fornax Deep Survey (FDS) with the VST: III. Low Surface Brightness (LSB) dwarfs and Ultra Diffuse Galaxies (UDGs) in the center of the Fornax cluster
• TOPz: Photometric redshifts using template fitting applied to the GAMA survey
• Hybrid-z: Enhancing Kilo-Degree Survey bright galaxy sample photometric redshifts with deep learning