Predicting High-magnification Events in Microlensed Quasars in the Era of LSST using Recurrent Neural Networks
| Title: | Predicting High-magnification Events in Microlensed Quasars in the Era of LSST using Recurrent Neural Networks |
|---|---|
| Authors: | Fagin, Joshua, Paic, Eric, Neira, Favio, Best, Henry, Anguita, Timo, Millon, Martin, O'Dowd, Matthew, Sluse, Dominique, Vernardos, Georgios |
| Source: | The Astrophysical Journal, Volume 981, Number 1, February 2025 |
| Publication Year: | 2024 |
| Collection: | Astrophysics |
| Subject Terms: | Astrophysics - Astrophysics of Galaxies, Astrophysics - Instrumentation and Methods for Astrophysics |
| More Details: | Upcoming widefield surveys, such as the Rubin Observatory's Legacy Survey of Space and Time (LSST), will monitor thousands of strongly lensed quasars over a 10 yr period. Many of these monitored quasars will undergo high-magnification events (HMEs) through microlensing, as the accretion disk crosses a caustic, places of infinite magnification. Microlensing allows us to map the inner regions of the accretion disk as it crosses a caustic, even at large cosmological distances. The observational cadences of LSST are not ideal for probing the inner regions of the accretion disk, so there is a need to predict HMEs as early as possible, to trigger high-cadence multiband or spectroscopic follow-up observations. Here, we simulate a diverse and realistic sample of 10 yr quasar microlensing light curves to train a recurrent neural network to predict HMEs before they occur, by classifying the locations of the peaks at each time step. This is the first deep-learning approach for predicting HMEs. We give estimates of how well we expect to predict HME peaks during LSST and benchmark how our metrics change with different cadence strategies. With LSST-like observations, we can predict approximately 55% of HME peaks, corresponding to tens to hundreds per year and a false-positive rate of around 20% compared to the total number of HMEs. Our network can be continuously applied throughout the LSST survey, providing crucial alerts for optimizing follow-up resources. Comment: 16 pages, 6 figures |
| Document Type: | Working Paper |
| DOI: | 10.3847/1538-4357/adaebb |
| Access URL: | http://arxiv.org/abs/2409.08999 |
| Accession Number: | edsarx.2409.08999 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2409.08999 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20240913&spage=&pages=&title=Predicting High-magnification Events in Microlensed Quasars in the Era of LSST using Recurrent Neural Networks&atitle=Predicting%20High-magnification%20Events%20in%20Microlensed%20Quasars%20in%20the%20Era%20of%20LSST%20using%20Recurrent%20Neural%20Networks&aulast=Fagin%2C%20Joshua&id=DOI:10.3847/1538-4357/adaebb Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2409.08999 RelevancyScore: 1112 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1112.25695800781 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Predicting High-magnification Events in Microlensed Quasars in the Era of LSST using Recurrent Neural Networks – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Fagin%2C+Joshua%22">Fagin, Joshua</searchLink><br /><searchLink fieldCode="AR" term="%22Paic%2C+Eric%22">Paic, Eric</searchLink><br /><searchLink fieldCode="AR" term="%22Neira%2C+Favio%22">Neira, Favio</searchLink><br /><searchLink fieldCode="AR" term="%22Best%2C+Henry%22">Best, Henry</searchLink><br /><searchLink fieldCode="AR" term="%22Anguita%2C+Timo%22">Anguita, Timo</searchLink><br /><searchLink fieldCode="AR" term="%22Millon%2C+Martin%22">Millon, Martin</searchLink><br /><searchLink fieldCode="AR" term="%22O'Dowd%2C+Matthew%22">O'Dowd, Matthew</searchLink><br /><searchLink fieldCode="AR" term="%22Sluse%2C+Dominique%22">Sluse, Dominique</searchLink><br /><searchLink fieldCode="AR" term="%22Vernardos%2C+Georgios%22">Vernardos, Georgios</searchLink> – Name: TitleSource Label: Source Group: Src Data: The Astrophysical Journal, Volume 981, Number 1, February 2025 – Name: DatePubCY Label: Publication Year Group: Date Data: 2024 – Name: Subset Label: Collection Group: HoldingsInfo Data: Astrophysics – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Astrophysics+-+Astrophysics+of+Galaxies%22">Astrophysics - Astrophysics of Galaxies</searchLink><br /><searchLink fieldCode="DE" term="%22Astrophysics+-+Instrumentation+and+Methods+for+Astrophysics%22">Astrophysics - Instrumentation and Methods for Astrophysics</searchLink> – Name: Abstract Label: Description Group: Ab Data: Upcoming widefield surveys, such as the Rubin Observatory's Legacy Survey of Space and Time (LSST), will monitor thousands of strongly lensed quasars over a 10 yr period. Many of these monitored quasars will undergo high-magnification events (HMEs) through microlensing, as the accretion disk crosses a caustic, places of infinite magnification. Microlensing allows us to map the inner regions of the accretion disk as it crosses a caustic, even at large cosmological distances. The observational cadences of LSST are not ideal for probing the inner regions of the accretion disk, so there is a need to predict HMEs as early as possible, to trigger high-cadence multiband or spectroscopic follow-up observations. Here, we simulate a diverse and realistic sample of 10 yr quasar microlensing light curves to train a recurrent neural network to predict HMEs before they occur, by classifying the locations of the peaks at each time step. This is the first deep-learning approach for predicting HMEs. We give estimates of how well we expect to predict HME peaks during LSST and benchmark how our metrics change with different cadence strategies. With LSST-like observations, we can predict approximately 55% of HME peaks, corresponding to tens to hundreds per year and a false-positive rate of around 20% compared to the total number of HMEs. Our network can be continuously applied throughout the LSST survey, providing crucial alerts for optimizing follow-up resources.<br />Comment: 16 pages, 6 figures – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: DOI Label: DOI Group: ID Data: 10.3847/1538-4357/adaebb – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2409.08999" linkWindow="_blank">http://arxiv.org/abs/2409.08999</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2409.08999 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2409.08999 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3847/1538-4357/adaebb Subjects: – SubjectFull: Astrophysics - Astrophysics of Galaxies Type: general – SubjectFull: Astrophysics - Instrumentation and Methods for Astrophysics Type: general Titles: – TitleFull: Predicting High-magnification Events in Microlensed Quasars in the Era of LSST using Recurrent Neural Networks Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Fagin, Joshua – PersonEntity: Name: NameFull: Paic, Eric – PersonEntity: Name: NameFull: Neira, Favio – PersonEntity: Name: NameFull: Best, Henry – PersonEntity: Name: NameFull: Anguita, Timo – PersonEntity: Name: NameFull: Millon, Martin – PersonEntity: Name: NameFull: O'Dowd, Matthew – PersonEntity: Name: NameFull: Sluse, Dominique – PersonEntity: Name: NameFull: Vernardos, Georgios IsPartOfRelationships: – BibEntity: Dates: – D: 13 M: 09 Type: published Y: 2024 |
| ResultId | 1 |