Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry

In the era of large sky surveys, photometric redshifts (photo-z) represent crucial information for galaxy evolution and cosmology studies. In this work, we propose a new Machine Learning (ML) tool called Galaxy morphoto-Z with neural Networks (GaZNet-1), which uses both images and multi-band photome...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-07
Main Authors: Li, Rui, Napolitano, Nicola R, Feng, Haicheng, Li, Ran, Amaro, Valeria, Xie, Linghua, Tortora, Crescenzo, Bilicki, Maciej, Brescia, Massimo, Cavuoti, Stefano, Radovich, Mario
Format: Article
Language:English
Subjects:
Active galactic nuclei
Cosmology
Galactic evolution
Galaxies
Infrared astronomy
Infrared photometry
Machine learning
Neural networks
Outliers (statistics)
Photometry
Red shift
Sky surveys (astronomy)
Stars & galaxies
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Li, Rui
Napolitano, Nicola R
Feng, Haicheng
Li, Ran
Amaro, Valeria
Xie, Linghua
Tortora, Crescenzo
Bilicki, Maciej
Brescia, Massimo
Cavuoti, Stefano
Radovich, Mario
description In the era of large sky surveys, photometric redshifts (photo-z) represent crucial information for galaxy evolution and cosmology studies. In this work, we propose a new Machine Learning (ML) tool called Galaxy morphoto-Z with neural Networks (GaZNet-1), which uses both images and multi-band photometry measurements to predict galaxy redshifts, with accuracy, precision and outlier fraction superior to standard methods based on photometry only. As a first application of this tool, we estimate photo-z of a sample of galaxies in the Kilo-Degree Survey (KiDS). GaZNet-1 is trained and tested on \(\sim140 000\) galaxies collected from KiDS Data Release 4 (DR4), for which spectroscopic redshifts are available from different surveys. This sample is dominated by bright (MAG\(\_\)AUTO\(
doi_str_mv 10.48550/arxiv.2205.10720
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2668587742</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2668587742</sourcerecordid><originalsourceid>FETCH-LOGICAL-a950-25f83e27104ac688fa0d3ff11a2486dec97590fcc19e53158d1b797551a642c83</originalsourceid><addsrcrecordid>eNotjT1PwzAYhC0kJKrSH8BmiQWGBPt1nDgjqqBUqoChU5fqxbFblyQujkNbfj3hY7q7R6c7Qq44SzMlJbvDcHSfKQCTKWcFsDMyAiF4ojKACzLpuh1jDPICpBQjcpxhjccTbXzYb330yYoeXNzS1vQBa_ps4sGH947ezHA1hO42pfOUvuyja9yXqShqPRT1iWJbUd_H2plA7UCi8-1gfEPnDW5cu_ltvP58NCaG0yU5t1h3ZvKvY7J8fFhOn5LFy2w-vV8kWEqWgLRKGCg4y1DnSllklbCWc4RM5ZXRZSFLZrXmpZGCS1Xxt2JgkmOegVZiTK7_ZvfBf_Smi-ud70M7PK4hz5VURZGB-AYv2140</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2668587742</pqid></control><display><type>article</type><title>Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry</title><source>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</source><creator>Li, Rui ; Napolitano, Nicola R ; Feng, Haicheng ; Li, Ran ; Amaro, Valeria ; Xie, Linghua ; Tortora, Crescenzo ; Bilicki, Maciej ; Brescia, Massimo ; Cavuoti, Stefano ; Radovich, Mario</creator><creatorcontrib>Li, Rui ; Napolitano, Nicola R ; Feng, Haicheng ; Li, Ran ; Amaro, Valeria ; Xie, Linghua ; Tortora, Crescenzo ; Bilicki, Maciej ; Brescia, Massimo ; Cavuoti, Stefano ; Radovich, Mario</creatorcontrib><description>In the era of large sky surveys, photometric redshifts (photo-z) represent crucial information for galaxy evolution and cosmology studies. In this work, we propose a new Machine Learning (ML) tool called Galaxy morphoto-Z with neural Networks (GaZNet-1), which uses both images and multi-band photometry measurements to predict galaxy redshifts, with accuracy, precision and outlier fraction superior to standard methods based on photometry only. As a first application of this tool, we estimate photo-z of a sample of galaxies in the Kilo-Degree Survey (KiDS). GaZNet-1 is trained and tested on \(\sim140 000\) galaxies collected from KiDS Data Release 4 (DR4), for which spectroscopic redshifts are available from different surveys. This sample is dominated by bright (MAG\(\_\)AUTO\(&lt;21\)) and low redshift (\(z &lt; 0.8\)) systems, however, we could use \(\sim\) 6500 galaxies in the range \(0.8 &lt; z &lt; 3\) to effectively extend the training to higher redshift. The inputs are the r-band galaxy images plus the 9-band magnitudes and colours, from the combined catalogs of optical photometry from KiDS and near-infrared photometry from the VISTA Kilo-degree Infrared survey. By combining the images and catalogs, GaZNet-1 can achieve extremely high precision in normalized median absolute deviation (NMAD=0.014 for lower redshift and NMAD=0.041 for higher redshift galaxies) and low fraction of outliers (\(0.4\)\% for lower and \(1.27\)\% for higher redshift galaxies). Compared to ML codes using only photometry as input, GaZNet-1 also shows a \(\sim 10-35\)% improvement in precision at different redshifts and a \(\sim\) 45% reduction in the fraction of outliers. We finally discuss that, by correctly separating galaxies from stars and active galactic nuclei, the overall photo-z outlier fraction of galaxies can be cut down to \(0.3\)\%.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.2205.10720</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Active galactic nuclei ; Cosmology ; Galactic evolution ; Galaxies ; Infrared astronomy ; Infrared photometry ; Machine learning ; Neural networks ; Outliers (statistics) ; Photometry ; Red shift ; Sky surveys (astronomy) ; Stars &amp; galaxies</subject><ispartof>arXiv.org, 2022-07</ispartof><rights>2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2668587742?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,27925,37012,44590</link.rule.ids></links><search><creatorcontrib>Li, Rui</creatorcontrib><creatorcontrib>Napolitano, Nicola R</creatorcontrib><creatorcontrib>Feng, Haicheng</creatorcontrib><creatorcontrib>Li, Ran</creatorcontrib><creatorcontrib>Amaro, Valeria</creatorcontrib><creatorcontrib>Xie, Linghua</creatorcontrib><creatorcontrib>Tortora, Crescenzo</creatorcontrib><creatorcontrib>Bilicki, Maciej</creatorcontrib><creatorcontrib>Brescia, Massimo</creatorcontrib><creatorcontrib>Cavuoti, Stefano</creatorcontrib><creatorcontrib>Radovich, Mario</creatorcontrib><title>Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry</title><title>arXiv.org</title><description>In the era of large sky surveys, photometric redshifts (photo-z) represent crucial information for galaxy evolution and cosmology studies. In this work, we propose a new Machine Learning (ML) tool called Galaxy morphoto-Z with neural Networks (GaZNet-1), which uses both images and multi-band photometry measurements to predict galaxy redshifts, with accuracy, precision and outlier fraction superior to standard methods based on photometry only. As a first application of this tool, we estimate photo-z of a sample of galaxies in the Kilo-Degree Survey (KiDS). GaZNet-1 is trained and tested on \(\sim140 000\) galaxies collected from KiDS Data Release 4 (DR4), for which spectroscopic redshifts are available from different surveys. This sample is dominated by bright (MAG\(\_\)AUTO\(&lt;21\)) and low redshift (\(z &lt; 0.8\)) systems, however, we could use \(\sim\) 6500 galaxies in the range \(0.8 &lt; z &lt; 3\) to effectively extend the training to higher redshift. The inputs are the r-band galaxy images plus the 9-band magnitudes and colours, from the combined catalogs of optical photometry from KiDS and near-infrared photometry from the VISTA Kilo-degree Infrared survey. By combining the images and catalogs, GaZNet-1 can achieve extremely high precision in normalized median absolute deviation (NMAD=0.014 for lower redshift and NMAD=0.041 for higher redshift galaxies) and low fraction of outliers (\(0.4\)\% for lower and \(1.27\)\% for higher redshift galaxies). Compared to ML codes using only photometry as input, GaZNet-1 also shows a \(\sim 10-35\)% improvement in precision at different redshifts and a \(\sim\) 45% reduction in the fraction of outliers. We finally discuss that, by correctly separating galaxies from stars and active galactic nuclei, the overall photo-z outlier fraction of galaxies can be cut down to \(0.3\)\%.</description><subject>Active galactic nuclei</subject><subject>Cosmology</subject><subject>Galactic evolution</subject><subject>Galaxies</subject><subject>Infrared astronomy</subject><subject>Infrared photometry</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Outliers (statistics)</subject><subject>Photometry</subject><subject>Red shift</subject><subject>Sky surveys (astronomy)</subject><subject>Stars &amp; galaxies</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNotjT1PwzAYhC0kJKrSH8BmiQWGBPt1nDgjqqBUqoChU5fqxbFblyQujkNbfj3hY7q7R6c7Qq44SzMlJbvDcHSfKQCTKWcFsDMyAiF4ojKACzLpuh1jDPICpBQjcpxhjccTbXzYb330yYoeXNzS1vQBa_ps4sGH947ezHA1hO42pfOUvuyja9yXqShqPRT1iWJbUd_H2plA7UCi8-1gfEPnDW5cu_ltvP58NCaG0yU5t1h3ZvKvY7J8fFhOn5LFy2w-vV8kWEqWgLRKGCg4y1DnSllklbCWc4RM5ZXRZSFLZrXmpZGCS1Xxt2JgkmOegVZiTK7_ZvfBf_Smi-ud70M7PK4hz5VURZGB-AYv2140</recordid><startdate>20220720</startdate><enddate>20220720</enddate><creator>Li, Rui</creator><creator>Napolitano, Nicola R</creator><creator>Feng, Haicheng</creator><creator>Li, Ran</creator><creator>Amaro, Valeria</creator><creator>Xie, Linghua</creator><creator>Tortora, Crescenzo</creator><creator>Bilicki, Maciej</creator><creator>Brescia, Massimo</creator><creator>Cavuoti, Stefano</creator><creator>Radovich, Mario</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20220720</creationdate><title>Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry</title><author>Li, Rui ; Napolitano, Nicola R ; Feng, Haicheng ; Li, Ran ; Amaro, Valeria ; Xie, Linghua ; Tortora, Crescenzo ; Bilicki, Maciej ; Brescia, Massimo ; Cavuoti, Stefano ; Radovich, Mario</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a950-25f83e27104ac688fa0d3ff11a2486dec97590fcc19e53158d1b797551a642c83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Active galactic nuclei</topic><topic>Cosmology</topic><topic>Galactic evolution</topic><topic>Galaxies</topic><topic>Infrared astronomy</topic><topic>Infrared photometry</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Outliers (statistics)</topic><topic>Photometry</topic><topic>Red shift</topic><topic>Sky surveys (astronomy)</topic><topic>Stars &amp; galaxies</topic><toplevel>online_resources</toplevel><creatorcontrib>Li, Rui</creatorcontrib><creatorcontrib>Napolitano, Nicola R</creatorcontrib><creatorcontrib>Feng, Haicheng</creatorcontrib><creatorcontrib>Li, Ran</creatorcontrib><creatorcontrib>Amaro, Valeria</creatorcontrib><creatorcontrib>Xie, Linghua</creatorcontrib><creatorcontrib>Tortora, Crescenzo</creatorcontrib><creatorcontrib>Bilicki, Maciej</creatorcontrib><creatorcontrib>Brescia, Massimo</creatorcontrib><creatorcontrib>Cavuoti, Stefano</creatorcontrib><creatorcontrib>Radovich, Mario</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Rui</au><au>Napolitano, Nicola R</au><au>Feng, Haicheng</au><au>Li, Ran</au><au>Amaro, Valeria</au><au>Xie, Linghua</au><au>Tortora, Crescenzo</au><au>Bilicki, Maciej</au><au>Brescia, Massimo</au><au>Cavuoti, Stefano</au><au>Radovich, Mario</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry</atitle><jtitle>arXiv.org</jtitle><date>2022-07-20</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>In the era of large sky surveys, photometric redshifts (photo-z) represent crucial information for galaxy evolution and cosmology studies. In this work, we propose a new Machine Learning (ML) tool called Galaxy morphoto-Z with neural Networks (GaZNet-1), which uses both images and multi-band photometry measurements to predict galaxy redshifts, with accuracy, precision and outlier fraction superior to standard methods based on photometry only. As a first application of this tool, we estimate photo-z of a sample of galaxies in the Kilo-Degree Survey (KiDS). GaZNet-1 is trained and tested on \(\sim140 000\) galaxies collected from KiDS Data Release 4 (DR4), for which spectroscopic redshifts are available from different surveys. This sample is dominated by bright (MAG\(\_\)AUTO\(&lt;21\)) and low redshift (\(z &lt; 0.8\)) systems, however, we could use \(\sim\) 6500 galaxies in the range \(0.8 &lt; z &lt; 3\) to effectively extend the training to higher redshift. The inputs are the r-band galaxy images plus the 9-band magnitudes and colours, from the combined catalogs of optical photometry from KiDS and near-infrared photometry from the VISTA Kilo-degree Infrared survey. By combining the images and catalogs, GaZNet-1 can achieve extremely high precision in normalized median absolute deviation (NMAD=0.014 for lower redshift and NMAD=0.041 for higher redshift galaxies) and low fraction of outliers (\(0.4\)\% for lower and \(1.27\)\% for higher redshift galaxies). Compared to ML codes using only photometry as input, GaZNet-1 also shows a \(\sim 10-35\)% improvement in precision at different redshifts and a \(\sim\) 45% reduction in the fraction of outliers. We finally discuss that, by correctly separating galaxies from stars and active galactic nuclei, the overall photo-z outlier fraction of galaxies can be cut down to \(0.3\)\%.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.2205.10720</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2022-07
issn 2331-8422
language eng
recordid cdi_proquest_journals_2668587742
source Publicly Available Content Database (Proquest) (PQ_SDU_P3)
subjects Active galactic nuclei
Cosmology
Galactic evolution
Galaxies
Infrared astronomy
Infrared photometry
Machine learning
Neural networks
Outliers (statistics)
Photometry
Red shift
Sky surveys (astronomy)
Stars & galaxies
title Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T17%3A14%3A52IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Galaxy%20morphoto-Z%20with%20neural%20Networks%20(GaZNets).%20I.%20Optimized%20accuracy%20and%20outlier%20fraction%20from%20Imaging%20and%20Photometry&rft.jtitle=arXiv.org&rft.au=Li,%20Rui&rft.date=2022-07-20&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.2205.10720&rft_dat=%3Cproquest%3E2668587742%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-a950-25f83e27104ac688fa0d3ff11a2486dec97590fcc19e53158d1b797551a642c83%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2668587742&rft_id=info:pmid/&rfr_iscdi=true