J/ApJS/272/4ivo://CDS.VizieR/J/ApJS/272/4doi:10.26093/cds/vizier.22720004CDSZhang P.Li B.Gui R.Xiong S.Zou Z.-C.Wang X.Li X.Cai Ce,Zhao YiZhang Y.Xue W.Zheng C.Zhao H.2025-07-16T20:14:39Z2024-09-30T14:44:24ZCDS support team

CDS, Observatoire de Strasbourg, 11 rue de l'Universite, F-67000 Strasbourg, France

cds-question@unistra.frgamma-ray-astronomygamma-ray-burstsastronomical-modelsastrometryTo investigate gamma-ray bursts (GRBs) in depth, it is crucial to develop an effective method for identifying GRBs accurately. Current criteria, e.g., onboard blind search, ground blind search, and target search, are limited by manually set thresholds and perhaps miss GRBs, especially for subthreshold events. We proposed a novel approach that utilizes convolutional neural networks (CNNs) to distinguish GRBs and non-GRBs directly. We structured three CNN models, plain-CNN, ResNet, and ResNet-CBAM, and endeavored to exercise fusing strategy models. Count maps of NaI detectors on board Fermi/Gamma-ray Burst Monitor were employed, as the input samples of data sets and models were implemented to evaluate their performance on different timescale data. The ResNet-CBAM model trained on the 64 ms data set achieves high accuracy overall, which includes residual and attention mechanism modules. The visualization methods of Grad-CAM and t-SNE explicitly displayed that the optimal model focuses on the key features of GRBs precisely. The model was applied to analyze 1 yr data, accurately identifying approximately 98% of GRBs listed in the Fermi burst catalog, eight out of nine subthreshold GRBs, and five GRBs triggered by other satellites, which demonstrated that the deep- learning methods could effectively distinguish GRBs from observational data. Besides, thousands of unknown candidates were retrieved and compared with the bursts of SGR J1935+2154, for instance, which exemplified the potential scientific value of these candidates indeed. Detailed studies on integrating our model into real-time analysis pipelines thus may improve their accuracy of inspection and provide valuable guidance for rapid follow-up observations of multiband telescopes.2024ApJS..272....4Zhttps://cdsarc.cds.unistra.fr/viz-bin/cat/J/ApJS/272/4CatalogResearchIsServedByTAP VizieR generic serviceIsServedByConesearch servicerelated-toJ/ApJ/896/L20 : Swift BAT gamma-ray burst durations (Jespersen+, 2020)J/ApJ/902/L43 : Fermi/GBM 2019 & 2020 bursts of SGR J1935+2154 (Lin+, 2020)J/MNRAS/492/1919 : Type I GRBs & the new classification method (Minaev+, 2020)J/ApJ/893/46 : 4th Fermi-GBM GRB catalog: 10 years (von Kienlin+, 2020)J/ApJ/893/77 : A comprehensive statistical study of GRBs (Wang+, 2020)J/ApJ/913/60 : GRB energetics from Fermi-GBM 10years (Poolakkil+, 2021)J/MNRAS/504/3084 : GRB detections in AstroSat CZTI (Abraham+, 2021)http://fermi.gsfc.nasa.gov/ssc/data/access/ : Fermi data access home pagehttps://cds.unistra.fr/vizier-org/licences_vizier.htmlhttps://vizier.cds.unistra.fr/viz-bin/VizieR-2?-source=J/ApJS/272/4https://vizier.iucaa.in/viz-bin/VizieR-2?-source=J/ApJS/272/4http://vizieridia.saao.ac.za/viz-bin/VizieR-2?-source=J/ApJS/272/4https://vizier.cds.unistra.fr/viz-bin/votable?-source=J/ApJS/272/4https://vizier.iucaa.in/viz-bin/votable?-source=J/ApJS/272/4http://vizieridia.saao.ac.za/viz-bin/votable?-source=J/ApJS/272/4GETtext/xml+votablehttps://tapvizier.cds.unistra.fr/TAPVizieR/tapCone search capability for table J/ApJS/272/4/table7 (The comparison result of the bursts found by our model and referred researches from SGR J1935+2154)https://vizier.cds.unistra.fr/viz-bin/conesearch/J/ApJS/272/4/table7?https://vizier.iucaa.in/viz-bin/conesearch/J/ApJS/272/4/table7?http://vizieridia.saao.ac.za/viz-bin/conesearch/J/ApJS/272/4/table7?GETtext/xml+votable180.050000true296.224.30.005555555555555556Cone search capability for table J/ApJS/272/4/table8 (Candidates with SNR {>=}5{sigma} of unknown events)https://vizier.cds.unistra.fr/viz-bin/conesearch/J/ApJS/272/4/table8?https://vizier.iucaa.in/viz-bin/conesearch/J/ApJS/272/4/table8?http://vizieridia.saao.ac.za/viz-bin/conesearch/J/ApJS/272/4/table8?GETtext/xml+votable180.050000true221.219.60.005555555555555556Cone search capability for table J/ApJS/272/4/table9 (Candidates with SNR <5{sigma} of unknown events)https://vizier.cds.unistra.fr/viz-bin/conesearch/J/ApJS/272/4/table9?https://vizier.iucaa.in/viz-bin/conesearch/J/ApJS/272/4/table9?http://vizieridia.saao.ac.za/viz-bin/conesearch/J/ApJS/272/4/table9?GETtext/xml+votable180.050000true96.1-41.60.0055555555555555566/310 357 425 578 638 745 965 1671 1962 2177 2915 2942 3675 3887 4048 4200 4888 5996 6140 6306 7826 7850 7866 7973 8793 8855 8998 9053 9459 9550 9688 10203 10304 10316 11594 11939 11987 12457 12841 12930 12933 12936 12952 12965 12972 12975 12980 12988 13000 13045 13050 13161 13575 13596 13678 14325 14343 14355 14357-14358 14365 14368 14389 14779 14791 15191 15321 15606 15738 16024 16066 16744 17172 17322 17466-17467 17736 18036 18073 18143 18155 18341 18702 18765 19314 19465 19531 19558 19627 19730 19741 20354 20741 21153 21440 21826 21852 22088 22526 23540 23949 24023 24053 24285 24549 24638 26182 26667 26863 27553 28265 29342 29394 29798 30139 30508 30676 30680 30717 30977 30988 31760 32076 32095 32354 32368 32767 32920 33105 33861 33880 34070 34159 34429 35250 35417 35701 35765 36591 37029 37333 37389 37467 37492 37725 38041 38160 38323 39119 39179 39256 39549 39578 40413 40733 41082 41475 41522 41589 41844 42067 42364 43346 43631 43880 44017 44298 44476 44514 44668 46736 46802 47351 48169 48890https://cdsarc.cds.unistra.fr/viz-bin/moc/J/ApJS/272/4?format=asciiGamma-raydefaultJ/ApJS/272/4/table7The comparison result of the bursts found by our model and referred researches from SGR J1935+2154recnoRecord number assigned by the VizieR team. Should Not be used for identification.meta.recordintZ21In Zou+ (2021ApJ...923L..30Z) (Y=Yes; or N=No)meta.codecharR23In Rehan & Ibrahim (2023ApJ...950..121R)meta.codecharX22In Xie+ (2022MNRAS.517.3854X)meta.codecharStartStart time of T_90_; UTC hh:mm:ss.sssssss formattime.epochnullableT90[0.13/5.1] Time which ID emits from 5% of its total measured counts to 95% (see Appendix B)stime.intervalfloatIDSGR event identifier (YYMMDDA)meta.id;meta.maincharSNR[6.2/476.4] Signal-to-Noise in {sigma}stat.snrfloatRAJ2000[287/306] Right Ascension (J2000)degpos.eq.ra;meta.mainDEJ2000[13.8/28] Declination (J2000)degpos.eq.dec;meta.mainePos[0.6/11] Positional uncertainty (G1)degstat.error;posfloatDetDetectors (n0-nb) (1)meta.id;instrcharJ/ApJS/272/4/table8Candidates with SNR {>=}5{sigma} of unknown eventsrecnoRecord number assigned by the VizieR team. Should Not be used for identification.meta.recordintIDUnknown event identifier (YYMMDDA)meta.id;meta.maincharf_IDFlag(s) on ID (G2)meta.codecharT90FstStart time of T_90,F_ (UTC)time.epochnullableT90F[14.6/96] The duration of bursts or candidatesstime.durationfloatT90stStart time of T_90_ (UTC)time.epochnullableT90[0.13/83.2] Time where 5-95% of total measured counts emitedsphot.countfloatSNR[2/700] Signal-to-Noise in {sigma}stat.snrfloatRAJ2000Right Ascension (J2000)degpos.eq.ra;meta.mainDEJ2000Declination (J2000)degpos.eq.dec;meta.mainePos[0.6/84.2] Positional uncertainty (G1)degstat.error;posfloatJ/ApJS/272/4/table9Candidates with SNR <5{sigma} of unknown eventsrecnoRecord number assigned by the VizieR team. Should Not be used for identification.meta.recordintIDUnknown event identifier (YYMMDDA)meta.id;meta.maincharf_IDFlag(s) on ID (G2)meta.codecharT90FstStart time of T_90,F_ (UTC)time.epochnullableT90F[14.6/96] The duration of bursts or candidatesstime.durationfloatT90stStart time of T_90_ (UTC)time.epochnullableT90[0.13/83.2] Time where 5-95% of total measured counts emitedsphot.countfloatSNR[2/700] Signal-to-Noise in {sigma}stat.snrfloatRAJ2000Right Ascension (J2000)degpos.eq.ra;meta.mainDEJ2000Declination (J2000)degpos.eq.dec;meta.mainePos[0.6/84.2] Positional uncertainty (G1)degstat.error;posfloatJ/ApJS/272/4/table10Candidates without significant burst signal of unknown eventsrecnoRecord number assigned by the VizieR team. Should Not be used for identification.meta.recordintIDUnknown event identifier (YYMMDDA)meta.id;meta.maincharprimaryT90FstStart time of T_90,F_ (UTC)time.epochnullableT90F[2.8/105] The duration of bursts or candidatesstime.durationfloat