Using neural networks to estimate redshift distributions. An application to CFHTLenS

Abstract

We present a novel way of using neural networks (NN) to estimate the redshift distribution of a galaxy sample. We are able to obtain a probability density function (PDF) for each galaxy using a classification neural network. The method is applied to 58714 galaxies in CFHTLenS that have spectroscopic redshifts from DEEP2, VVDS and VIPERS. Using this data we show that the stacked PDF's give an excellent representation of the true $N(z)$ using information from 5, 4 or 3 photometric bands. We show that the fractional error due to using N(z_(phot)) instead of N(z_(truth)) is <=1 on the lensing power spectrum P_(kappa) in several tomographic bins. Further we investigate how well this method performs when few training samples are available and show that in this regime the neural network slightly overestimates the N(z) at high z. Finally the case where the training sample is not representative of the full data set is investigated. An IPython notebook accompanying this paper is made available here: https://bitbucket.org/christopher_bonnett/nn_notebook

References in corpus (11)

• The All-wavelength Extended Groth Strip International Survey (AEGIS) Data Sets
• Report of the Dark Energy Task Force
• Calibrating Redshift Distributions Beyond Spectroscopic Limits with Cross-Correlations
• The Zurich Extragalactic Bayesian Redshift Analyzer (ZEBRA) and its first application: COSMOS
• The VIMOS Public Extragalactic Survey (VIPERS): First Data Release of 57 204 spectroscopic measurements
• The Vimos VLT Deep Survey: Global properties of 20000 galaxies in the I_AB<=22.5 WIDE survey
• SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
• Photometric redshifts: estimating their contamination and distribution using clustering information
• New Approaches To Photometric Redshift Prediction Via Gaussian Process Regression In The Sloan Digital Sky Survey
• Photometric redshifts with Quasi Newton Algorithm (MLPQNA). Results in the PHAT1 contest
• Dark energy constraints and correlations with systematics from CFHTLS weak lensing, SNLS supernovae Ia and WMAP5

Cited by in corpus (54)

• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• redMaGiC: Selecting Luminous Red Galaxies from the DES Science Verification Data
• ANNz2 - photometric redshift and probability distribution function estimation using machine learning
• The DES Science Verification Weak Lensing Shear Catalogues
• Cosmology from Cosmic Shear with DES Science Verification Data
• Redshift distributions of galaxies in the DES Science Verification shear catalogue and implications for weak lensing
• Cluster Mass Calibration at High Redshift: HST Weak Lensing Analysis of 13 Distant Galaxy Clusters from the South Pole Telescope Sunyaev-Zel'dovich Survey
• SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
• Cosmic Shear Measurements with DES Science Verification Data
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Evaluation of probabilistic photometric redshift estimation approaches for The Rubin Observatory Legacy Survey of Space and Time (LSST)
• METAPHOR: A machine learning based method for the probability density estimation of photometric redshifts
• The PAU Survey: Early demonstration of photometric redshift performance in the COSMOS field
• Extragalactic Radio Continuum Surveys and the Transformation of Radio Astronomy
• Anomaly detection for machine learning redshifts applied to SDSS galaxies
• Photometric Redshift Estimation with a Convolutional Neural Network: NetZ
• Redshift inference from the combination of galaxy colors and clustering in a hierarchical Bayesian model
• Galaxy-Galaxy Lensing in the DES Science Verification Data
• Cross-correlation of gravitational lensing from DES Science Verification data with SPT and Planck lensing
• A Unified Analysis of Four Cosmic Shear Surveys
• Morpho-z: improving photometric redshifts with galaxy morphology
• A machine learning approach to galaxy properties: joint redshift-stellar mass probability distributions with Random Forest
• Redshift inference from the combination of galaxy colors and clustering in a hierarchical Bayesian model $-$ Application to realistic $N$-body simulations
• Horizon-AGN virtual observatory -- 2: Template-free estimates of galaxy properties from colours
• Weak Lensing Tomographic Redshift Distribution Inference for the Hyper Suprime-Cam Subaru Strategic Program three-year shape catalogue
• The PAU Survey: Photometric redshifts using transfer learning from simulations
• Cross-Correlation Redshift Calibration Without Spectroscopic Calibration Samples in DES Science Verification Data
• Weak-lensing shear measurement with machine learning: teaching artificial neural networks about feature noise
• Weak Lensing Analysis of SPT selected Galaxy Clusters using Dark Energy Survey Science Verification Data
• Photometric redshifts with machine learning, lights and shadows on a complex data science use case
• Stacking for machine learning redshifts applied to SDSS galaxies
• A Unified Framework for Constructing, Tuning and Assessing Photometric Redshift Density Estimates in a Selection Bias Setting
• Statistical analysis of probability density functions for photometric redshifts through the KiDS-ESO-DR3 galaxies
• Implications of a wavelength dependent PSF for weak lensing measurements
• PhotoRedshift-MML: a multimodal machine learning method for estimating photometric redshifts of quasars
• A Composite Likelihood Approach for Inference under Photometric Redshift Uncertainty
• Estimating redshift distributions using Hierarchical Logistic Gaussian processes
• Galaxy bias from galaxy-galaxy lensing in the DES Science Verification Data
• Testing the accuracy of 3D-HST photometric redshift estimates as reference samples for deep weak lensing studies
• The 2-degree Field Lensing Survey: photometric redshifts from a large new training sample to r<19.5
• Machine-learning computation of distance modulus for local galaxies
• Self-consistent redshift estimation using correlation functions without a spectroscopic reference sample
• Correcting cosmological parameter biases for all redshift surveys induced by estimating and reweighting redshift distributions
• Convolutional Neural Networks for Spectroscopic Redshift Estimation on Euclid Data
• The PAU Survey: Photometric redshift estimation in deep wide fields
• Tuning target selection algorithms to improve galaxy redshift estimates
• The many flavours of photometric redshifts
• Rejection criteria based on outliers in the KiDS photometric redshifts and PDF distributions derived by machine learning
• Machine learning applications in astrophysics: Photometric redshift estimation
• CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation
• METAPHOR: Probability density estimation for machine learning based photometric redshifts
• Characterising Improvements in Photometric Redshift Probability Density Functions with Galaxy Morphology
• Probability density estimation of photometric redshifts based on machine learning
• Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods