Photometric redshift estimation via deep learning

Abstract

The need to analyze the available large synoptic multi-band surveys drives the development of new data-analysis methods. Photometric redshift estimation is one field of application where such new methods improved the results, substantially. Up to now, the vast majority of applied redshift estimation methods have utilized photometric features. We aim to develop a method to derive probabilistic photometric redshift directly from multi-band imaging data, rendering pre-classification of objects and feature extraction obsolete. A modified version of a deep convolutional network was combined with a mixture density network. The estimates are expressed as Gaussian mixture models representing the probability density functions (PDFs) in the redshift space. In addition to the traditional scores, the continuous ranked probability score (CRPS) and the probability integral transform (PIT) were applied as performance criteria. We have adopted a feature based random forest and a plain mixture density network to compare performances on experiments with data from SDSS (DR9). We show that the proposed method is able to predict redshift PDFs independently from the type of source, for example galaxies, quasars or stars. Thereby the prediction performance is better than both presented reference methods and is comparable to results from the literature. The presented method is extremely general and allows us to solve of any kind of probabilistic regression problems based on imaging data, for example estimating metallicity or star formation rate of galaxies. This kind of methodology is tremendously important for the next generation of surveys.

16 pages, 12 figures, 6 tables. Accepted for publication on A&A

References in corpus (20)

• The Baryon Oscillation Spectroscopic Survey of SDSS-III
• The Ninth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-III Baryon Oscillation Spectroscopic Survey
• Bayesian photometric redshift estimation
• The Sloan Digital Sky Survey Quasar Catalog V. Seventh Data Release
• ANNz: estimating photometric redshifts using artificial neural networks
• Data Mining and Machine Learning in Astronomy
• Photometric redshift and classification for the XMM-COSMOS sources
• The Sloan Digital Sky Survey quasar catalog: ninth data release
• TPZ : Photometric redshift PDFs and ancillary information by using prediction trees and random forests
• ANNz2 - photometric redshift and probability distribution function estimation using machine learning
• Photometric redshifts for the SDSS Data Release 12
• Cosmology with photometric redshift surveys
• A Comparison of Six Photometric Redshift Methods Applied to 1.5 Million Luminous Red Galaxies
• Photometric redshifts for Quasars in multi band Surveys
• On the compared accuracy and reliability of spectroscopic and photometric redshift measurements
• A catalogue of photometric redshifts for the SDSS-DR9 galaxies
• Hierarchical progressive surveys. Multi-resolution HEALPix data structures for astronomical images, catalogues, and 3-dimensional data cubes
• Machine Learning based photometric redshifts for the KiDS ESO DR2 galaxies
• Astroinformatics of galaxies and quasars: a new general method for photometric redshifts estimation
• Finding New High-Redshift Quasars by Asking the Neighbours

Cited by in corpus (82)

• Neural networks for post-processing ensemble weather forecasts
• Probabilistic Random Forest: A machine learning algorithm for noisy datasets
• Photometric redshifts from SDSS images using a Convolutional Neural Network
• Probabilistic neural networks for fluid flow surrogate modeling and data recovery
• Euclid preparation: X. The Euclid photometric-redshift challenge
• 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
• Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
• Self-Supervised Representation Learning for Astronomical Images
• Photometric redshifts for the Kilo-Degree Survey. Machine-learning analysis with artificial neural networks
• Photometric Redshift Estimation with a Convolutional Neural Network: NetZ
• GalaxyNet: Connecting galaxies and dark matter haloes with deep neural networks and reinforcement learning in large volumes
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• Testing Convolutional Neural Networks for finding strong gravitational lenses in KiDS
• A machine learning approach to galaxy properties: joint redshift-stellar mass probability distributions with Random Forest
• Conditional Density Estimation Tools in Python and R with Applications to Photometric Redshifts and Likelihood-Free Cosmological Inference
• Using convolutional neural networks to predict galaxy metallicity from three-color images
• On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars
• Investigating Deep Learning Methods for Obtaining Photometric Redshift Estimations from Images
• XMMPZCAT: A catalogue of photometric redshifts for X-ray sources
• Quantifying Uncertainties on Fission Fragment Mass Yields With Mixture Density Networks
• Return of the features. Efficient feature selection and interpretation for photometric redshifts
• Quantifying Non-parametric Structure of High-redshift Galaxies with Deep Learning
• Photometric Redshifts from SDSS Images with an Interpretable Deep Capsule Network
• Weak-lensing shear measurement with machine learning: teaching artificial neural networks about feature noise
• Hubble Asteroid Hunter: II. Identifying strong gravitational lenses in HST images with crowdsourcing
• Revised extinctions and radii for 1.5 million stars observed by APOGEE, GALAH, and RAVE
• The Extremely Luminous Quasar Survey in the Pan-STARRS 1 Footprint (PS-ELQS)
• Benchmarking and Scalability of Machine Learning Methods for Photometric Redshift Estimation
• Photometric redshifts with machine learning, lights and shadows on a complex data science use case
• 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
• Statistical analysis of probability density functions for photometric redshifts through the KiDS-ESO-DR3 galaxies
• Assessing the performance of LTE and NLTE synthetic stellar spectra in a machine learning framework
• 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
• The High Cadence Transient Survey (HITS): Compilation and characterization of light-curve catalogs
• 21st Century Statistical and Computational Challenges in Astrophysics
• QSO photometric redshifts using machine learning and neural networks
• Augmenting machine learning photometric redshifts with Gaussian mixture models
• Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry
• Photometric identification of compact galaxies, stars and quasars using multiple neural networks
• PhotoRedshift-MML: a multimodal machine learning method for estimating photometric redshifts of quasars
• Evaluation of Machine Learning Techniques for Forecast Uncertainty Quantification
• Predicting the redshift of gamma-ray loud AGNs using Supervised Machine Learning: Part 2
• Predicting the redshift of gamma-ray loud AGNs using supervised machine learning
• Identifying MgII Narrow Absorption Lines with Deep Learning
• Morpho-Photometric Redshifts
• PhotoWeb redshift: boosting photometric redshift accuracy with large spectroscopic surveys
• GeneticKNN: A Weighted KNN Approach Supported by Genetic Algorithm for Photometric Redshift Estimation of Quasars
• HOLISMOKES -- XI. Evaluation of supervised neural networks for strong-lens searches in ground-based imaging surveys
• Deep Transfer Learning for Classification of Variable Sources
• Detection of Einstein Telescope gravitational wave signals from binary black holes using deep learning
• Machine-learning computation of distance modulus for local galaxies
• Galaxy Spectra neural Network (GaSNet). II. Using Deep Learning for Spectral Classification and Redshift Predictions
• ULISSE: A Tool for One-shot Sky Exploration and its Application to Active Galactic Nuclei Detection
• PICZL: Image-based Photometric Redshifts for AGN
• The PAU Survey: Background light estimation with deep learning techniques
• HOLISMOKES XIII: Strong-lens candidates at all mass scales and their environments from the Hyper-Suprime Cam and deep learning
• Intervening or associated? Machine learning classification of redshifted H I 21-cm absorption
• SDSS-IV MaNGA: Unveiling Galaxy Interaction by Merger Stages with Machine Learning
• Euclid preparation. LI. Forecasting the recovery of galaxy physical properties and their relations with template-fitting and machine-learning methods
• Estimation of Photometric Redshifts. II. Identification of Out-of-Distribution Data with Neural Networks
• Euclid preparation. LXVIII. Extracting physical parameters from galaxies with machine learning
• Quasar photometric redshifts from incomplete data using Deep Learning
• Gaussian Mixture Models for Blended Photometric Redshifts
• The many flavours of photometric redshifts
• AutoSourceID-FeatureExtractor. Optical image analysis using a two-step mean variance estimation network for feature estimation and uncertainty characterisation
• Machine learning applications in astrophysics: Photometric redshift estimation
• Comparison of outlier detection methods on astronomical image data
• CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation
• Unsupervised Domain Adaptation for Constraining Star Formation Histories
• A Concept of Assessment of LIV Tests with THESEUS Using the Gamma-Ray Bursts Detected by Fermi/GBM
• ULISSE: Determination of star-formation rate and stellar mass based on the one-shot galaxy imaging technique
• The S-PLUS Fornax Project (S+FP): An extragalactic catalog covering $\sim$ 5 virial radii around NGC 1399 with galaxy properties
• A Value-added Physical Properties Catalog for Low-redshift Galaxies from DESI Legacy Imaging Surveys DR10
• Mimicking the halo-galaxy connection using machine learning
• Predicting large scale cosmological structure evolution with generative adversarial network-based autoencoders
• Hybrid-z: Enhancing Kilo-Degree Survey bright galaxy sample photometric redshifts with deep learning
• TOPz: Photometric redshifts using template fitting applied to the GAMA survey
• DeepRed: an architecture for redshift estimation
• Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods
• CNN photometric redshifts in the SDSS at $r\le 20$
• Identifying AGN host galaxies by Machine Learning with HSC+WISE