Photometric redshifts from SDSS images using a Convolutional Neural Network

Abstract

We developed a Deep Convolutional Neural Network (CNN), used as a classifier, to estimate photometric redshifts and associated probability distribution functions (PDF) for galaxies in the Main Galaxy Sample of the Sloan Digital Sky Survey at z < 0.4. Our method exploits all the information present in the images without any feature extraction. The input data consist of 64x64 pixel ugriz images centered on the spectroscopic targets, plus the galactic reddening value on the line-of-sight. For training sets of 100k objects or more ($\ge$ 20% of the database), we reach a dispersion ${\sigma }_{MAD}$<0.01, significantly lower than the current best one obtained from another machine learning technique on the same sample. The bias is lower than 0.0001, independent of photometric redshift. The PDFs are shown to have very good predictive power. We also find that the CNN redshifts are unbiased with respect to galaxy inclination, and that ${\sigma }_{MAD}$ decreases with the signal-to-noise ratio (SNR), achieving values below 0.007 for SNR >100, as in the deep stacked region of Stripe 82. We argue that for most galaxies the precision is limited by the SNR of SDSS images rather than by the method. The success of this experiment at low redshift opens promising perspectives for upcoming surveys.

arXiv commentSubmitted to A&A, Comments welcome, Model and Example available at "https://github.com/jpasquet/Photoz

References in corpus (31)

• Maps of Dust IR Emission for Use in Estimation of Reddening and CMBR Foregrounds
• The Eleventh and Twelfth Data Releases of the Sloan Digital Sky Survey: Final Data from SDSS-III
• EAZY: A Fast, Public Photometric Redshift Code
• Accurate photometric redshifts for the CFHT Legacy Survey calibrated using the VIMOS VLT Deep Survey
• The Eighth Data Release of the Sloan Digital Sky Survey: First Data from SDSS-III
• Bayesian photometric redshift estimation
• Measuring and Modelling the Redshift Evolution of Clustering: the Hubble Deep Field North
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Improved background subtraction for the Sloan Digital Sky Survey images
• ANNz: estimating photometric redshifts using artificial neural networks
• Representations of celestial coordinates in FITS
• Caltech Faint Galaxy Redshift Survey X: A Redshift Survey in the Region of the Hubble Deep Field North
• Photometric Redshifts for Hyper Suprime-Cam Subaru Strategic Program Data Release 1
• CFHTLenS: Improving the quality of photometric redshifts with precision photometry
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• TPZ : Photometric redshift PDFs and ancillary information by using prediction trees and random forests
• Encoding the infrared excess (IRX) in the NUVrK color diagram for star-forming galaxies
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Photometric redshifts for the SDSS Data Release 12
• Photometric redshift estimation via deep learning
• Insights into the content and spatial distribution of dust from the integrated spectral properties of galaxies
• Precision photometric redshift calibration for galaxy-galaxy weak lensing
• Deep Recurrent Neural Networks for Supernovae Classification
• A General Study of the Influence of Catastrophic Photometric Redshift Errors on Cosmology with Cosmic Shear Tomography
• Deep learning Approach for Classifying, Detecting and Predicting Photometric Redshifts of Quasars in the Sloan Digital Sky Survey Stripe 82
• On the realistic validation of photometric redshifts, or why Teddy will never be Happy
• Exhausting the Information: Novel Bayesian Combination of Photometric Redshift PDFs
• A cooperative approach among methods for photometric redshifts estimation: an application to KiDS data
• Weighing the Universe with Photometric Redshift Surveys and the Impact on Dark Energy Forecasts
• Effect of Inclination of Galaxies on Photometric Redshift
• An Improved Photometric Calibration of the Sloan Digital Sky Survey Imaging Data

Cited by in corpus (106)

• Euclid preparation: X. The Euclid photometric-redshift challenge
• Photometric Redshifts for Next-Generation Surveys
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Deblending and Classifying Astronomical Sources with Mask R-CNN Deep Learning
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• Self-Supervised Representation Learning for Astronomical Images
• Horizon-AGN virtual observatory - 1. SED-fitting performance and forecasts for future imaging surveys
• Photometric Redshift Estimation with a Convolutional Neural Network: NetZ
• The impact of the connectivity of the cosmic web on the physical properties of galaxies at its nodes
• AstroCLIP: A Cross-Modal Foundation Model for Galaxies
• Detecting outliers in astronomical images with deep generative networks
• Bright galaxy sample in the Kilo-Degree Survey Data Release 4: selection, photometric redshifts, and physical properties
• Deblending galaxy superpositions with branched generative adversarial networks
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• Optimized Photometric Redshifts for the Cosmic Assembly Near-Infrared Deep Extragalactic Legacy Survey (CANDELS)
• The Young Supernova Experiment Data Release 1 (YSE DR1): Light Curves and Photometric Classification of 1975 Supernovae
• A machine learning approach to galaxy properties: joint redshift-stellar mass probability distributions with Random Forest
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• Using convolutional neural networks to predict galaxy metallicity from three-color images
• Investigating Deep Learning Methods for Obtaining Photometric Redshift Estimations from Images
• Conditional Density Estimation Tools in Python and R with Applications to Photometric Redshifts and Likelihood-Free Cosmological Inference
• Pushing automated morphological classifications to their limits with the Dark Energy Survey
• Detecting solar system objects with convolutional neural networks
• ERGO-ML I: Inferring the assembly histories of IllustrisTNG galaxies from integral observable properties via invertible neural networks
• Machine Learning for Observational Cosmology
• Quantifying Non-parametric Structure of High-redshift Galaxies with Deep Learning
• Photometric Redshifts from SDSS Images with an Interpretable Deep Capsule Network
• Improving the reliability of photometric redshift with machine learning
• Photometric redshifts with machine learning, lights and shadows on a complex data science use case
• Benchmarking and Scalability of Machine Learning Methods for Photometric Redshift Estimation
• Photometric Redshifts with the LSST II: The Impact of Near-Infrared and Near-Ultraviolet Photometry
• Combining the CLAUDS & HSC-SSP surveys: U+grizy(+YJHKs) photometry and photometric redshifts for 18M galaxies in the 20 deg2 of the HSC-SSP Deep and ultraDeep fields
• SILVERRUSH X: Machine Learning-Aided Selection of $9318$ LAEs at $z=2.2$, $3.3$, $4.9$, $5.7$, $6.6$, and $7.0$ from the HSC SSP and CHORUS Survey Data
• Hubble Asteroid Hunter: I. Identifying asteroid trails in Hubble Space Telescope images
• Automatic detection of low surface brightness galaxies from SDSS images
• Extracting Photometric Redshift from Galaxy Flux and Image Data using Neural Networks in the CSST Survey
• Euclid preparation: XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning
• 21st Century Statistical and Computational Challenges in Astrophysics
• Comparison of Observed Galaxy Properties with Semianalytic Model Predictions using Machine Learning
• J-PAS: Measuring emission lines with artificial neural networks
• The HectoMAP Redshift Survey: First Data Release
• Photometric redshift estimates using Bayesian neural networks in the CSST survey
• PhotoRedshift-MML: a multimodal machine learning method for estimating photometric redshifts of quasars
• Photometric identification of compact galaxies, stars and quasars using multiple neural networks
• YOLO-CL: Galaxy cluster detection in the SDSS with deep machine learning
• Identification of Galaxy-Galaxy Strong Lens Candidates in the DECam Local Volume Exploration Survey Using Machine Learning
• Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry
• Connecting optical morphology, environment, and HI mass fraction for low-redshift galaxies using deep learning
• Deep learning for Sunyaev-Zel'dovich detection in Planck
• Deep-CEE I: Fishing for Galaxy Clusters with Deep Neural Nets
• B/PS bulges in DESI Legacy edge-on galaxies I: Sample building
• Machine Learning Approach to Integral Field Unit Spectroscopy Observations: I. HII Region Kinematics
• Euclid Preparation XXXIII. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong lensing events
• Mixture Models for Photometric Redshifts
• PhotoWeb redshift: boosting photometric redshift accuracy with large spectroscopic surveys
• Photometric classification of HSC transients using machine learning
• 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 miniJPAS survey quasar selection II: Machine learning classification with photometric measurements and uncertainties
• Supernova search with active learning in ZTF DR3
• Improving machine learning-derived photometric redshifts and physical property estimates using unlabelled observations
• High-fidelity reproduction of central galaxy joint distributions with Neural Networks
• The miniJPAS survey quasar selection III: Classification with artificial neural networks and hybridisation
• Deep Learning in Wide-field Surveys: Fast Analysis of Strong Lenses in Ground-based Cosmic Experiments
• Enhanced Astronomical Source Classification with Integration of Attention Mechanisms and Vision Transformers
• Wasserstein distance as a new tool for discriminating cosmologies through the topology of large scale structure
• Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions
• PICZL: Image-based Photometric Redshifts for AGN
• Weak-lensing Mass Reconstruction of Galaxy Clusters with Convolutional Neural Network
• The PAU Survey: Background light estimation with deep learning techniques
• Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
• Euclid preparation. LI. Forecasting the recovery of galaxy physical properties and their relations with template-fitting and machine-learning methods
• Recovered SN Ia rate from simulated LSST images
• Real galaxy mergers from galaxy pair catalogs
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
• Euclid: Identifying the reddest high-redshift galaxies in the Euclid Deep Fields with gradient-boosted trees
• Estimating Photometric Redshifts for Galaxies from the DESI Legacy Imaging Surveys with Bayesian Neural Networks Trained by DESI EDR
• Impact of photometric redshifts on the galaxy power spectrum and BAO scale in the LSST survey
• Inferring redshift and galaxy properties via a multi-task neural net with probabilistic outputs: An application to simulated MOONS spectra
• Accurately Estimating Redshifts from CSST Slitless Spectroscopic Survey using Deep Learning
• Predicting bulge to total luminosity ratio of galaxies using deep learning
• Estimating Galactic Distances From Images Using Self-supervised Representation Learning
• Augmenting photometric redshift estimates using spectroscopic nearest neighbours
• AutoSourceID-FeatureExtractor. Optical image analysis using a two-step mean variance estimation network for feature estimation and uncertainty characterisation
• The optical luminosity function of LOFAR radio-selected quasars at $1.4\le z\le 5.0$ in the NDWFS-Boötes field
• Stellar Karaoke: deep blind separation of terrestrial atmospheric effects out of stellar spectra by velocity whitening
• CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation
• YOLO-CL cluster detection in the Rubin/LSST DC2 simulation
• The Galaxy Activity, Torus, and Outflow Survey (GATOS). Black hole mass estimation using machine learning
• Realizing the potential of astrostatistics and astroinformatics
• Euclid preparation. Estimating galaxy physical properties using CatBoost chained regressors with attention
• Interpreting deep learning-based stellar mass estimation via causal analysis and mutual information decomposition
• Investigation on deep learning-based galaxy image translation models
• Z-Sequence: Photometric redshift predictions for galaxy clusters with sequential random k-nearest neighbours
• ULISSE: Determination of star-formation rate and stellar mass based on the one-shot galaxy imaging technique
• Analyzing billion-objects catalog interactively: Apache Spark for physicists
• The line-of-sight analysis of spatial distribution of galaxies in the COSMOS2015 catalogue
• The S-PLUS Fornax Project (S+FP): An extragalactic catalog covering $\sim$ 5 virial radii around NGC 1399 with galaxy properties
• Construction of a far ultraviolet all sky map from an incomplete survey: Application of a deep learning algorithm
• TOPz: Photometric redshifts using template fitting applied to the GAMA survey
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations
• Extending the SAGA Survey (xSAGA) I: Satellite Radial Profiles as a Function of Host Galaxy Properties
• Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods
• A Value-added Physical Properties Catalog for Low-redshift Galaxies from DESI Legacy Imaging Surveys DR10
• DeepRed: an architecture for redshift estimation