Morphology Classification and Photometric Redshift Measurement of Galaxies

Abstract

Based on the Sloan Digital Sky Survey Data Release 5 Galaxy Sample, we explore photometric morphology classification and redshift estimation of galaxies using photometric data and known spectroscopic redshifts. An unsupervised method, k-means algorithm, is used to separate the whole galaxy sample into early- and late-type galaxies. Then we investigate the photometric redshift measurement with different input patterns by means of artificial neural networks (ANNs) for the total sample and the two subsamples. The experimental result indicates that ANNs show better performance when the more parameters are applied in the training set, and the mixed accuracy ${\sigma }_{mix}=\sqrt{{\sigma }_{early}^2+{{\sigma }_{late}}^2}$ of photometric redshift estimation for the two subsets is superior to ${\sigma }_z$ for the overall sample alone. For the optimal result, the rms deviation of photometric redshifts for the mixed sample amounts to 0.0192, that for the overall sample is 0.0196, meanwhile, that for early- and late-type galaxies adds up to 0.0164 and 0.0217, respectively.

The paper contains 8 figures and 2 tables. Accepted by MNRAS

References in corpus (22)

• Maps of Dust IR Emission for Use in Estimation of Reddening and CMBR Foregrounds
• The Sloan Digital Sky Survey: Technical Summary
• Color Separation of Galaxy Types in the Sloan Digital Sky Survey Imaging Data
• ANNz: estimating photometric redshifts using artificial neural networks
• Statistical Properties of Bright Galaxies in the SDSS Photometric System
• Slicing Through Multicolor Space: Galaxy Redshifts From Broadband Photometry
• Photometric Redshifts for the SDSS Early Data Release
• Estimating photometric redshifts with artificial neural networks
• Photometric redshifts with the Multilayer Perceptron Neural Network: application to the HDF-S and SDSS
• Estimating Photometric Redshifts Using Support Vector Machines
• An Artificial Neural Network Approach to Classification of Galaxy Spectra
• Neural computation as a tool for galaxy classification : methods and examples
• A Catalog of Color-based Redshift Estimates for z <~ 4 Galaxies in the Hubble Deep Field
• Novel Methods for Predicting Photometric Redshifts from Broad Band Photometry using Virtual Sensors
• A Photometric Redshift Galaxy Catalog from the Red-Sequence Cluster Survey
• The Ultraviolet Luminosity Function of GALEX Galaxies at Photometric Redshifts Between 0.07 and 0.25
• Towards More Precise Photometric Redshifts: Calibration Via CCD Photometry
• Robust Machine Learning Applied to Astronomical Datasets II: Quantifying Photometric Redshifts for Quasars Using Instance-Based Learning
• Mining the SDSS archive. I. Photometric redshifts in the nearby universe
• Automated Clustering Algorithms for Classification of Astronomical Objects
• Kernel Regression For Determining Photometric Redshifts From Sloan Broadband Photometry
• Two novel approaches for photometric redshift estimation based on SDSS and 2MASS databases

Cited by in corpus (8)

• Data Mining and Machine Learning in Astronomy
• Selection of radio pulsar candidates using artificial neural networks
• Deep learning Approach for Classifying, Detecting and Predicting Photometric Redshifts of Quasars in the Sloan Digital Sky Survey Stripe 82
• Estimating Photometric Redshifts of Quasars via K-nearest Neighbor Approach Based on Large Survey Databases
• Photometric Redshift Estimation of BASS DR3 Quasars by Machine Learning
• Detection of Einstein Telescope gravitational wave signals from binary black holes using deep learning
• The effects of UV photometry and binary interactions on photometric redshift and galaxy morphology
• Non-Sequential Neural Network for Simultaneous, Consistent Classification and Photometric Redshifts of OTELO Galaxies