DeepStreaks: identifying fast-moving objects in the Zwicky Transient Facility data with deep learning
ABSTRACT We present DeepStreaks, a convolutional-neural-network, deep-learning system designed to efficiently identify streaking fast-moving near-Earth objects that are detected in the data of the Zwicky Transient Facility (ZTF), a wide-field, time-domain survey using a dedicated 47 deg2 camera atta...
Gespeichert in:
| Veröffentlicht in: | Monthly notices of the Royal Astronomical Society 2019-07, Vol.486 (3), p.4158-4165 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 4165 |
|---|---|
| container_issue | 3 |
| container_start_page | 4158 |
| container_title | Monthly notices of the Royal Astronomical Society |
| container_volume | 486 |
| creator | Duev, Dmitry A Mahabal, Ashish Ye, Quanzhi Tirumala, Kushal Belicki, Justin Dekany, Richard Frederick, Sara Graham, Matthew J Laher, Russ R Masci, Frank J Prince, Thomas A Riddle, Reed Rosnet, Philippe Soumagnac, Maayane T |
| description | ABSTRACT
We present DeepStreaks, a convolutional-neural-network, deep-learning system designed to efficiently identify streaking fast-moving near-Earth objects that are detected in the data of the Zwicky Transient Facility (ZTF), a wide-field, time-domain survey using a dedicated 47 deg2 camera attached to the Samuel Oschin 48-inch Telescope at the Palomar Observatory in California, United States. The system demonstrates a 96–98 per cent true positive rate, depending on the night, while keeping the false positive rate below 1 per cent. The sensitivity of DeepStreaks is quantified by the performance on the test data sets as well as using known near-Earth objects observed by ZTF. The system is deployed and adapted for usage within the ZTF Solar system framework and has significantly reduced human involvement in the streak identification process, from several hours to typically under 10 min per day. |
| doi_str_mv | 10.1093/mnras/stz1096 |
| format | Article |
| fullrecord | <record><control><sourceid>oup_TOX</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_hal_02153085v1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><oup_id>10.1093/mnras/stz1096</oup_id><sourcerecordid>10.1093/mnras/stz1096</sourcerecordid><originalsourceid>FETCH-LOGICAL-c343t-6e885b684a78d4cf20406382038fd9c43f0cb04678a7ca3a0980920187a6277e3</originalsourceid><addsrcrecordid>eNqFkM9PwjAYhhujiYgevfeoh8nXdes6bwRBTEg8iBcvzUfXSWFspK2Q-dc7hHj19P3I8z6Hl5BbBg8Mcj7Y1A79wIfv7hJnpMe4SKM4F-Kc9AB4GsmMsUty5f0KABIeix4xT8Zs34IzuPaP1BamDrZsbf1JS_Qh2jS7w94sVkYHT21Nw9LQj73V65bOHdbedgk6QW0rG1paYEC6t2FJi85LK4Ou7gTX5KLEypub0-yT98l4PppGs9fnl9FwFmme8BAJI2W6EDLBTBaJLmNIQHAZA5dlkeuEl6AXkIhMYqaRI-QS8hiYzFDEWWZ4n9wfvUus1NbZDbpWNWjVdDhThx_ELOUg0x3r2OjIatd470z5F2CgDn2q3z7Vqc-Ovzvyzdf2H_QHnBF4dw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>DeepStreaks: identifying fast-moving objects in the Zwicky Transient Facility data with deep learning</title><source>Oxford Journals Open Access Collection</source><creator>Duev, Dmitry A ; Mahabal, Ashish ; Ye, Quanzhi ; Tirumala, Kushal ; Belicki, Justin ; Dekany, Richard ; Frederick, Sara ; Graham, Matthew J ; Laher, Russ R ; Masci, Frank J ; Prince, Thomas A ; Riddle, Reed ; Rosnet, Philippe ; Soumagnac, Maayane T</creator><creatorcontrib>Duev, Dmitry A ; Mahabal, Ashish ; Ye, Quanzhi ; Tirumala, Kushal ; Belicki, Justin ; Dekany, Richard ; Frederick, Sara ; Graham, Matthew J ; Laher, Russ R ; Masci, Frank J ; Prince, Thomas A ; Riddle, Reed ; Rosnet, Philippe ; Soumagnac, Maayane T</creatorcontrib><description>ABSTRACT
We present DeepStreaks, a convolutional-neural-network, deep-learning system designed to efficiently identify streaking fast-moving near-Earth objects that are detected in the data of the Zwicky Transient Facility (ZTF), a wide-field, time-domain survey using a dedicated 47 deg2 camera attached to the Samuel Oschin 48-inch Telescope at the Palomar Observatory in California, United States. The system demonstrates a 96–98 per cent true positive rate, depending on the night, while keeping the false positive rate below 1 per cent. The sensitivity of DeepStreaks is quantified by the performance on the test data sets as well as using known near-Earth objects observed by ZTF. The system is deployed and adapted for usage within the ZTF Solar system framework and has significantly reduced human involvement in the streak identification process, from several hours to typically under 10 min per day.</description><identifier>ISSN: 0035-8711</identifier><identifier>EISSN: 1365-2966</identifier><identifier>DOI: 10.1093/mnras/stz1096</identifier><language>eng</language><publisher>Oxford University Press</publisher><subject>Physics</subject><ispartof>Monthly notices of the Royal Astronomical Society, 2019-07, Vol.486 (3), p.4158-4165</ispartof><rights>2019 The Author(s) Published by Oxford University Press on behalf of the Royal Astronomical Society 2019</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c343t-6e885b684a78d4cf20406382038fd9c43f0cb04678a7ca3a0980920187a6277e3</citedby><cites>FETCH-LOGICAL-c343t-6e885b684a78d4cf20406382038fd9c43f0cb04678a7ca3a0980920187a6277e3</cites><orcidid>0000-0001-5060-8733 ; 0000-0002-0387-370X ; 0000-0002-3168-0139 ; 0000-0001-6753-1488 ; 0000-0002-8850-3627</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,1603,27923,27924</link.rule.ids><linktorsrc>$$Uhttps://dx.doi.org/10.1093/mnras/stz1096$$EView_record_in_Oxford_University_Press$$FView_record_in_$$GOxford_University_Press</linktorsrc><backlink>$$Uhttps://hal.science/hal-02153085$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Duev, Dmitry A</creatorcontrib><creatorcontrib>Mahabal, Ashish</creatorcontrib><creatorcontrib>Ye, Quanzhi</creatorcontrib><creatorcontrib>Tirumala, Kushal</creatorcontrib><creatorcontrib>Belicki, Justin</creatorcontrib><creatorcontrib>Dekany, Richard</creatorcontrib><creatorcontrib>Frederick, Sara</creatorcontrib><creatorcontrib>Graham, Matthew J</creatorcontrib><creatorcontrib>Laher, Russ R</creatorcontrib><creatorcontrib>Masci, Frank J</creatorcontrib><creatorcontrib>Prince, Thomas A</creatorcontrib><creatorcontrib>Riddle, Reed</creatorcontrib><creatorcontrib>Rosnet, Philippe</creatorcontrib><creatorcontrib>Soumagnac, Maayane T</creatorcontrib><title>DeepStreaks: identifying fast-moving objects in the Zwicky Transient Facility data with deep learning</title><title>Monthly notices of the Royal Astronomical Society</title><description>ABSTRACT
We present DeepStreaks, a convolutional-neural-network, deep-learning system designed to efficiently identify streaking fast-moving near-Earth objects that are detected in the data of the Zwicky Transient Facility (ZTF), a wide-field, time-domain survey using a dedicated 47 deg2 camera attached to the Samuel Oschin 48-inch Telescope at the Palomar Observatory in California, United States. The system demonstrates a 96–98 per cent true positive rate, depending on the night, while keeping the false positive rate below 1 per cent. The sensitivity of DeepStreaks is quantified by the performance on the test data sets as well as using known near-Earth objects observed by ZTF. The system is deployed and adapted for usage within the ZTF Solar system framework and has significantly reduced human involvement in the streak identification process, from several hours to typically under 10 min per day.</description><subject>Physics</subject><issn>0035-8711</issn><issn>1365-2966</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNqFkM9PwjAYhhujiYgevfeoh8nXdes6bwRBTEg8iBcvzUfXSWFspK2Q-dc7hHj19P3I8z6Hl5BbBg8Mcj7Y1A79wIfv7hJnpMe4SKM4F-Kc9AB4GsmMsUty5f0KABIeix4xT8Zs34IzuPaP1BamDrZsbf1JS_Qh2jS7w94sVkYHT21Nw9LQj73V65bOHdbedgk6QW0rG1paYEC6t2FJi85LK4Ou7gTX5KLEypub0-yT98l4PppGs9fnl9FwFmme8BAJI2W6EDLBTBaJLmNIQHAZA5dlkeuEl6AXkIhMYqaRI-QS8hiYzFDEWWZ4n9wfvUus1NbZDbpWNWjVdDhThx_ELOUg0x3r2OjIatd470z5F2CgDn2q3z7Vqc-Ovzvyzdf2H_QHnBF4dw</recordid><startdate>20190701</startdate><enddate>20190701</enddate><creator>Duev, Dmitry A</creator><creator>Mahabal, Ashish</creator><creator>Ye, Quanzhi</creator><creator>Tirumala, Kushal</creator><creator>Belicki, Justin</creator><creator>Dekany, Richard</creator><creator>Frederick, Sara</creator><creator>Graham, Matthew J</creator><creator>Laher, Russ R</creator><creator>Masci, Frank J</creator><creator>Prince, Thomas A</creator><creator>Riddle, Reed</creator><creator>Rosnet, Philippe</creator><creator>Soumagnac, Maayane T</creator><general>Oxford University Press</general><general>Oxford University Press (OUP): Policy P - Oxford Open Option A</general><scope>AAYXX</scope><scope>CITATION</scope><scope>1XC</scope><orcidid>https://orcid.org/0000-0001-5060-8733</orcidid><orcidid>https://orcid.org/0000-0002-0387-370X</orcidid><orcidid>https://orcid.org/0000-0002-3168-0139</orcidid><orcidid>https://orcid.org/0000-0001-6753-1488</orcidid><orcidid>https://orcid.org/0000-0002-8850-3627</orcidid></search><sort><creationdate>20190701</creationdate><title>DeepStreaks: identifying fast-moving objects in the Zwicky Transient Facility data with deep learning</title><author>Duev, Dmitry A ; Mahabal, Ashish ; Ye, Quanzhi ; Tirumala, Kushal ; Belicki, Justin ; Dekany, Richard ; Frederick, Sara ; Graham, Matthew J ; Laher, Russ R ; Masci, Frank J ; Prince, Thomas A ; Riddle, Reed ; Rosnet, Philippe ; Soumagnac, Maayane T</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c343t-6e885b684a78d4cf20406382038fd9c43f0cb04678a7ca3a0980920187a6277e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Physics</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Duev, Dmitry A</creatorcontrib><creatorcontrib>Mahabal, Ashish</creatorcontrib><creatorcontrib>Ye, Quanzhi</creatorcontrib><creatorcontrib>Tirumala, Kushal</creatorcontrib><creatorcontrib>Belicki, Justin</creatorcontrib><creatorcontrib>Dekany, Richard</creatorcontrib><creatorcontrib>Frederick, Sara</creatorcontrib><creatorcontrib>Graham, Matthew J</creatorcontrib><creatorcontrib>Laher, Russ R</creatorcontrib><creatorcontrib>Masci, Frank J</creatorcontrib><creatorcontrib>Prince, Thomas A</creatorcontrib><creatorcontrib>Riddle, Reed</creatorcontrib><creatorcontrib>Rosnet, Philippe</creatorcontrib><creatorcontrib>Soumagnac, Maayane T</creatorcontrib><collection>CrossRef</collection><collection>Hyper Article en Ligne (HAL)</collection><jtitle>Monthly notices of the Royal Astronomical Society</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Duev, Dmitry A</au><au>Mahabal, Ashish</au><au>Ye, Quanzhi</au><au>Tirumala, Kushal</au><au>Belicki, Justin</au><au>Dekany, Richard</au><au>Frederick, Sara</au><au>Graham, Matthew J</au><au>Laher, Russ R</au><au>Masci, Frank J</au><au>Prince, Thomas A</au><au>Riddle, Reed</au><au>Rosnet, Philippe</au><au>Soumagnac, Maayane T</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>DeepStreaks: identifying fast-moving objects in the Zwicky Transient Facility data with deep learning</atitle><jtitle>Monthly notices of the Royal Astronomical Society</jtitle><date>2019-07-01</date><risdate>2019</risdate><volume>486</volume><issue>3</issue><spage>4158</spage><epage>4165</epage><pages>4158-4165</pages><issn>0035-8711</issn><eissn>1365-2966</eissn><abstract>ABSTRACT
We present DeepStreaks, a convolutional-neural-network, deep-learning system designed to efficiently identify streaking fast-moving near-Earth objects that are detected in the data of the Zwicky Transient Facility (ZTF), a wide-field, time-domain survey using a dedicated 47 deg2 camera attached to the Samuel Oschin 48-inch Telescope at the Palomar Observatory in California, United States. The system demonstrates a 96–98 per cent true positive rate, depending on the night, while keeping the false positive rate below 1 per cent. The sensitivity of DeepStreaks is quantified by the performance on the test data sets as well as using known near-Earth objects observed by ZTF. The system is deployed and adapted for usage within the ZTF Solar system framework and has significantly reduced human involvement in the streak identification process, from several hours to typically under 10 min per day.</abstract><pub>Oxford University Press</pub><doi>10.1093/mnras/stz1096</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0001-5060-8733</orcidid><orcidid>https://orcid.org/0000-0002-0387-370X</orcidid><orcidid>https://orcid.org/0000-0002-3168-0139</orcidid><orcidid>https://orcid.org/0000-0001-6753-1488</orcidid><orcidid>https://orcid.org/0000-0002-8850-3627</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0035-8711 |
| ispartof | Monthly notices of the Royal Astronomical Society, 2019-07, Vol.486 (3), p.4158-4165 |
| issn | 0035-8711 1365-2966 |
| language | eng |
| recordid | cdi_hal_primary_oai_HAL_hal_02153085v1 |
| source | Oxford Journals Open Access Collection |
| subjects | Physics |
| title | DeepStreaks: identifying fast-moving objects in the Zwicky Transient Facility data with deep learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T03%3A42%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-oup_TOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=DeepStreaks:%20identifying%20fast-moving%20objects%20in%20the%20Zwicky%20Transient%20Facility%20data%20with%20deep%20learning&rft.jtitle=Monthly%20notices%20of%20the%20Royal%20Astronomical%20Society&rft.au=Duev,%20Dmitry%20A&rft.date=2019-07-01&rft.volume=486&rft.issue=3&rft.spage=4158&rft.epage=4165&rft.pages=4158-4165&rft.issn=0035-8711&rft.eissn=1365-2966&rft_id=info:doi/10.1093/mnras/stz1096&rft_dat=%3Coup_TOX%3E10.1093/mnras/stz1096%3C/oup_TOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_oup_id=10.1093/mnras/stz1096&rfr_iscdi=true |