RAPID: Early Classification of Explosive Transients Using Deep Learning

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: id:"swepub:oai:DiVA.org:su-180672" > RAPID :

1 av 1
Föregående post
Nästa post
Till träfflistan

LIBRIS Formathandbok (Information om MARC21)

Fältnamn	Indikatorer	Metadata
000		03108naa a2200409 4500
001		oai:DiVA.org:su-180672
003		SwePub
008		200406s2019 \| \|\|\|\|\|\|\|\|\|\|\|000 \|\|eng\|
024	7	a https://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-1806722 URI
024	7	a https://doi.org/10.1088/1538-3873/ab16092 DOI
040		a (SwePub)su
041		a engb eng
042		9 SwePub
072	7	a ref2 swepub-contenttype
072	7	a art2 swepub-publicationtype
100	1	a Muthukrishna, Daniel4 aut
245	1 0	a RAPID :b Early Classification of Explosive Transients Using Deep Learning
264		c 2019-09-30
264	1	b IOP Publishing,c 2019
338		a print2 rdacarrier
520		a We present Real-time Automated Photometric IDentification (RAPID), a novel time series classification tool capable of automatically identifying transients from within a day of the initial alert, to the full lifetime of a light curve. Using a deep recurrent neural network with gated recurrent units (GRUs), we present the first method specifically designed to provide early classifications of astronomical timeseries data, typing 12 different transient classes. Our classifier can process light curves with any phase coverage, and it does not rely on deriving computationally expensive features from the data, making RAPID well suited for processing the millions of alerts that ongoing and upcoming wide-field surveys such as the Zwicky Transient Facility (ZTF), and the Large Synoptic Survey Telescope (LSST) will produce. The classification accuracy improves over the lifetime of the transient as more photometric data becomes available, and across the 12 transient classes, we obtain an average area under the receiver operating characteristic curve of 0.95 and 0.98 at early and late epochs, respectively. We demonstrate RAPID's ability to effectively provide early classifications of observed transients from the ZTF data stream. We have made RAPID available as an open-source software package(8) for machine-learning-based alert brokers to use for the autonomous and quick classification of several thousand light curves within a few seconds.
650	7	a NATURVETENSKAPx Fysik0 (SwePub)1032 hsv//swe
650	7	a NATURAL SCIENCESx Physical Sciences0 (SwePub)1032 hsv//eng
653		a methods: data analysis
653		a techniques: photometric
653		a virtual observatory tools
653		a (stars:) supernovae: general
700	1	a Narayan, Gautham4 aut
700	1	a Mandel, Kaisey S.4 aut
700	1	a Biswas, Rahulu Stockholms universitet,Fysikum,Oskar Klein-centrum för kosmopartikelfysik (OKC)4 aut0 (Swepub:su)rbisw
700	1	a Hložek, Renée4 aut
710	2	a Stockholms universitetb Fysikum4 org
773	0	t Publications of the Astronomical Society of the Pacificd : IOP Publishingg 131:1005q 131:1005x 0004-6280x 1538-3873
856	4	u https://arxiv.org/abs/1904.00014y arXiv:1904.00014
856	4	u http://arxiv.org/pdf/1904.00014
856	4 8	u https://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-180672
856	4 8	u https://doi.org/10.1088/1538-3873/ab1609

Hitta via bibliotek

Publications of the Astronomical Society of the Pacific (Sök värdpublikationen i LIBRIS)

Till lärosätets databas

1 av 1
Föregående post
Nästa post
Till träfflistan

Hitta mer i SwePub

Av författaren/redakt...: Muthukrishna, Da ...; Narayan, Gautham; Mandel, Kaisey S ...; Biswas, Rahul; Hložek, Renée

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Fysik

Artiklar i publikationen: Publications of ...

Av lärosätet: Stockholms universitet

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se