GSpyNetTree: Un clasificador de señales astrofísicas y ruido de detector para candidatos de ondas gravitacionales de LIGO-Virgo

Esta tesis desarrolla un árbol de decisión de redes neuronales convolucionales (CNNs), llamada GSpyNetTree, usada por la colaboración LIGO-Virgo para distinguir señales de ondas gravitacionales de ruido de detector.

Autores:
Álvarez López, María Sofía
Tipo de recurso:
Trabajo de grado de pregrado
Fecha de publicación:
2023
Institución:
Universidad de los Andes
Repositorio:
Séneca: repositorio Uniandes
Idioma:
spa
OAI Identifier:
oai:repositorio.uniandes.edu.co:1992/68749
Acceso en línea:
http://hdl.handle.net/1992/68749
Palabra clave:
Machine Learning
Ondas gravitacionales
LIGO
Convolutional Neural Networks
CNNs
Ingeniería
Rights
openAccess
License
Attribution-NoDerivatives 4.0 Internacional
id UNIANDES2_2895ca7072e881026a734b24d2827aca
oai_identifier_str oai:repositorio.uniandes.edu.co:1992/68749
network_acronym_str UNIANDES2
network_name_str Séneca: repositorio Uniandes
repository_id_str
dc.title.none.fl_str_mv GSpyNetTree: Un clasificador de señales astrofísicas y ruido de detector para candidatos de ondas gravitacionales de LIGO-Virgo
title GSpyNetTree: Un clasificador de señales astrofísicas y ruido de detector para candidatos de ondas gravitacionales de LIGO-Virgo
spellingShingle GSpyNetTree: Un clasificador de señales astrofísicas y ruido de detector para candidatos de ondas gravitacionales de LIGO-Virgo
Machine Learning
Ondas gravitacionales
LIGO
Convolutional Neural Networks
CNNs
Ingeniería
title_short GSpyNetTree: Un clasificador de señales astrofísicas y ruido de detector para candidatos de ondas gravitacionales de LIGO-Virgo
title_full GSpyNetTree: Un clasificador de señales astrofísicas y ruido de detector para candidatos de ondas gravitacionales de LIGO-Virgo
title_fullStr GSpyNetTree: Un clasificador de señales astrofísicas y ruido de detector para candidatos de ondas gravitacionales de LIGO-Virgo
title_full_unstemmed GSpyNetTree: Un clasificador de señales astrofísicas y ruido de detector para candidatos de ondas gravitacionales de LIGO-Virgo
title_sort GSpyNetTree: Un clasificador de señales astrofísicas y ruido de detector para candidatos de ondas gravitacionales de LIGO-Virgo
dc.creator.fl_str_mv Álvarez López, María Sofía
dc.contributor.advisor.none.fl_str_mv Núñez Castro, Haydemar María
dc.contributor.author.none.fl_str_mv Álvarez López, María Sofía
dc.contributor.researchgroup.es_CO.fl_str_mv COMIT
dc.subject.keyword.none.fl_str_mv Machine Learning
Ondas gravitacionales
LIGO
Convolutional Neural Networks
CNNs
topic Machine Learning
Ondas gravitacionales
LIGO
Convolutional Neural Networks
CNNs
Ingeniería
dc.subject.themes.es_CO.fl_str_mv Ingeniería
description Esta tesis desarrolla un árbol de decisión de redes neuronales convolucionales (CNNs), llamada GSpyNetTree, usada por la colaboración LIGO-Virgo para distinguir señales de ondas gravitacionales de ruido de detector.
publishDate 2023
dc.date.accessioned.none.fl_str_mv 2023-07-25T20:45:17Z
dc.date.available.none.fl_str_mv 2023-07-25T20:45:17Z
dc.date.issued.none.fl_str_mv 2023-07-16
dc.type.es_CO.fl_str_mv Trabajo de grado - Pregrado
dc.type.driver.none.fl_str_mv info:eu-repo/semantics/bachelorThesis
dc.type.version.none.fl_str_mv info:eu-repo/semantics/acceptedVersion
dc.type.coar.none.fl_str_mv http://purl.org/coar/resource_type/c_7a1f
dc.type.content.es_CO.fl_str_mv Text
dc.type.redcol.none.fl_str_mv http://purl.org/redcol/resource_type/TP
format http://purl.org/coar/resource_type/c_7a1f
status_str acceptedVersion
dc.identifier.uri.none.fl_str_mv http://hdl.handle.net/1992/68749
dc.identifier.instname.es_CO.fl_str_mv instname:Universidad de los Andes
dc.identifier.reponame.es_CO.fl_str_mv reponame:Repositorio Institucional Séneca
dc.identifier.repourl.es_CO.fl_str_mv repourl:https://repositorio.uniandes.edu.co/
url http://hdl.handle.net/1992/68749
identifier_str_mv instname:Universidad de los Andes
reponame:Repositorio Institucional Séneca
repourl:https://repositorio.uniandes.edu.co/
dc.language.iso.es_CO.fl_str_mv spa
language spa
dc.relation.references.es_CO.fl_str_mv B. P. Abbott et al. (LIGO Scientific Collaboration and Virgo Collaboration), «Observation of Gravitational Waves from a Binary Black Hole Merger», Phys. Rev. Lett. 116, 061102 (2016).
J. McIver y D. H. Shoemaker, «Discovering gravitational waves with Advanced LIGO», Contemporary Physics 61, 229-255 (2020).
M. Zevin et al., «Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science», Classical and Quantum Gravity 34, arXiv:1611.04596 [astro-ph, physics:gr-qc, physics:physics], 064003 (2017).
B. P. Abbott et al. (LIGO Scientific Collaboration and Virgo Collaboration), «GW150914: The Advanced LIGO Detectors in the Era of First Discoveries», Phys. Rev. Lett. 116, 131103 (2016).
B. P. Abbott et al. (LIGO Scientific Collaboration and Virgo Collaboration), «GWTC-1: A Gravitational-Wave Transient Catalog of Compact Binary Mergers Observed by LIGO and Virgo during the First and Second Observing Runs», en, 10.1103/PhysRevX.9.031040.
B. P. Abbott et al. (LIGO Scientific Collaboration and Virgo Collaboration), «GWTC-2: Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run», en, 10.1103/PhysRevX.11.021053.
B. P. Abbott et al. (LIGO Scientific Collaboration and Virgo Collaboration and KAGRA Collaboration), «GWTC-3: Compact Binary Coalescences Observed by LIGO and Virgo During the Second Part of the Third Observing Run», en, 10.48550/arXiv.2111.03606.
LIGO Scientific Collaboration and Virgo Collaboration, LIGO Laboratory at Caltech and MIT.
P. R. Saulson, Fundamentals of interferometric gravitational wave detectors (World Scientific, 1994).
The LIGO Scientific Collaboration, What is an interferometer?
J. Harms, «Terrestrial Gravity Fluctuations», Living Reviews in Relativity 22, arXiv:1507.05850 [gr-qc], 6 (2019).
The LIGO Scientific Collaboration and the Virgo Collaboration, «Characterization of transient noise in Advanced LIGO relevant to gravitational wave signal GW150914», Classical and Quantum Gravity 33, arXiv:1602.03844 [astro-ph, physics:gr-qc, physics:physics], 134001 (2016).
S. Anderson, K. Burtnyk y J. Kanner, LIGO-M1000066-v27: LIGO Data Management Plan, 2022.
B. Berger, «Identification and mitigation of Advanced LIGO noise sources», Journal of Physics: Conference Series 957, 012004 (2018)
D. Davis et al., «LIGO Detector Characterization in the Second and Third Observing Runs», Classical and Quantum Gravity 38, arXiv:2101.11673 [astro-ph, physics:gr-qc], 135014 (2021).
J. S. Areeda et al., LigoDV-web: Providing easy, secure and universal access to a large distributed scientific data store for the LIGO Scientific Collaboration, arXiv:1611.01089 [astro-ph, physics:gr-qc], nov. de 2016.
Jarov, S. et al., «A new method to distinguish gravitational-wave signals from detector glitches with Gravity Spy».
S. Alvarez-Lopez et al., GSpyNetTree: A signal-vs-glitch classifier for gravitational-wave event candidates, 2023.
A. Geron, Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow : 2nd ed., https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/ (O'Reilly Media, Inc., Mumbai, 2020).
A. C. Wilson et al., The Marginal Value of Adaptive Gradient Methods in Machine Learning, 2018.
D. Masters y C. Luschi, Revisiting Small Batch Training for Deep Neural Networks, 2018.
IBM, What are convolutional neural networks?
LIGO Scientific Collaboration, LIGO Algorithm Library - LALSuite, free software (GPL), 2018.
S. Husa et al., «Frequency-domain gravitational waves from nonprecessing black-hole binaries. I. New numerical waveforms and anatomy of the signal», Phys. Rev. D 93, 044006 (2016).
S. Khan et al., «Frequency-domain gravitational waves from nonprecessing black-hole binaries. II. A phenomenological model for the advanced detector era», Phys. Rev. D 93, 044007 (2016).
Pace A, Prestegard T, Moe B and Stephens B, «GraceDB Gravitational-Wave Candidate Event Database», https://gracedb.ligo.org/ (2020).
The LIGO Scientific Collaboration and The Virgo Collaboration, «LIGO/Virgo Alert System (LVAlert)»
M. Tan y Q. V. Le, EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, 2020.
C. Szegedy et al., «Rethinking the Inception Architecture for Computer Vision», en 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), págs. 2818-2826.
C. Szegedy et al., «Going deeper with convolutions», en 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015), págs. 1-9.
dc.rights.license.spa.fl_str_mv Attribution-NoDerivatives 4.0 Internacional
dc.rights.uri.*.fl_str_mv http://creativecommons.org/licenses/by-nd/4.0/
dc.rights.accessrights.spa.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.coar.spa.fl_str_mv http://purl.org/coar/access_right/c_abf2
rights_invalid_str_mv Attribution-NoDerivatives 4.0 Internacional
http://creativecommons.org/licenses/by-nd/4.0/
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.extent.es_CO.fl_str_mv 49 páginas
dc.format.mimetype.es_CO.fl_str_mv application/pdf
dc.publisher.es_CO.fl_str_mv Universidad de los Andes
dc.publisher.program.es_CO.fl_str_mv Ingeniería de Sistemas y Computación
dc.publisher.faculty.es_CO.fl_str_mv Facultad de Ingeniería
dc.publisher.department.es_CO.fl_str_mv Departamento de Ingeniería Sistemas y Computación
institution Universidad de los Andes
bitstream.url.fl_str_mv https://repositorio.uniandes.edu.co/bitstreams/b1e43b3b-200e-47da-8556-dfc231a0d387/download
https://repositorio.uniandes.edu.co/bitstreams/a2d8ceb4-20d7-4ad2-9217-e3d07d4a5f94/download
https://repositorio.uniandes.edu.co/bitstreams/be2618da-8b06-4c79-95d4-c86b8ee8ab2d/download
https://repositorio.uniandes.edu.co/bitstreams/d24034f0-d0ee-4b8c-b428-5360d5652ac9/download
https://repositorio.uniandes.edu.co/bitstreams/fa8310c4-b4e7-4c0c-af4b-cf5d7e95389c/download
https://repositorio.uniandes.edu.co/bitstreams/d8ba35c8-6d0f-42ed-adaa-d8a40a1cfb3c/download
https://repositorio.uniandes.edu.co/bitstreams/8e445e72-637b-4252-abb4-dc24995129bc/download
https://repositorio.uniandes.edu.co/bitstreams/dfa904c6-6a9c-49dd-8167-a11ca9e75b6a/download
bitstream.checksum.fl_str_mv f7d494f61e544413a13e6ba1da2089cd
adbbdbdc975ed84788366c52c1bb8d61
08b106dfeb12472e88207a069e15ba30
9ecfecc41421704f1ab4bde9f12751cf
a8362fb718d10281b5ed76c2b2017eab
03b504eb2d992cccccc4c047b0f4663b
423290a5cb4c3d3ed2f193a6e819041b
5aa5c691a1ffe97abd12c2966efcb8d6
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio institucional Séneca
repository.mail.fl_str_mv adminrepositorio@uniandes.edu.co
_version_ 1812133810638159872
spelling Attribution-NoDerivatives 4.0 Internacionalhttp://creativecommons.org/licenses/by-nd/4.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Núñez Castro, Haydemar María05768730-2a33-411e-b3b1-2f3a105e0b76600Álvarez López, María Sofía689609b1-ed8f-494f-b3c1-83538435b87e600COMIT2023-07-25T20:45:17Z2023-07-25T20:45:17Z2023-07-16http://hdl.handle.net/1992/68749instname:Universidad de los Andesreponame:Repositorio Institucional Sénecarepourl:https://repositorio.uniandes.edu.co/Esta tesis desarrolla un árbol de decisión de redes neuronales convolucionales (CNNs), llamada GSpyNetTree, usada por la colaboración LIGO-Virgo para distinguir señales de ondas gravitacionales de ruido de detector.Tras la primera detección de ondas gravitacionales (GWs), las colaboraciones LIGO y Virgo iniciaron un nuevo campo de la astronomía al proporcionar una nueva forma de entender el Universo. A pesar de haber alcanzado sensibilidades capaces de detectar la amplitud extremadamente pequeña de las ondas gravitacionales, los datos de los detectores LIGO y Virgo contienen frecuentes ráfagas de ruido transitorio no Gaussiano, comúnmente conocidas como "glitches", que a menudo imitan o se solapan con las señales de ondas gravitacionales. Dada la mayor tasa de eventos de GWs esperada en el actual periodo de observación (O4), que comenzó en mayo de 2023, el proceso de selección de candidatos a GWs, incluida la identificación de glitches que se solapan con GWs o son morfológicamente similares a ellas, requiere una mayor automatización. Este trabajo desarrolla GSpyNetTree, el "Gravity Spy Convolutional Neural Network Decision Tree": un clasificador multi-CNN multi-etiqueta que identifica con precisión los "glitches" presentes en cada detector de GWs en el momento de una GW candidata. GSpyNetTree ha sido entrenada para ser robusta frente a una amplia gama de ruido de fondo, nuevas fuentes de "glitches" y la probable aparición de "glitches" y GWs solapados.La mayor parte de los aspectos computacionales de esta tesis fueron desarrollados usando recursos computacionales proveídos por el Laboratorio LIGO y apoyados por los Grants de la National Science Foundation de Estados Unidos PHY-0757058 y PHY-0823459.Ingeniero de Sistemas y ComputaciónPregradoMachine Learning49 páginasapplication/pdfspaUniversidad de los AndesIngeniería de Sistemas y ComputaciónFacultad de IngenieríaDepartamento de Ingeniería Sistemas y ComputaciónGSpyNetTree: Un clasificador de señales astrofísicas y ruido de detector para candidatos de ondas gravitacionales de LIGO-VirgoTrabajo de grado - Pregradoinfo:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/acceptedVersionhttp://purl.org/coar/resource_type/c_7a1fTexthttp://purl.org/redcol/resource_type/TPMachine LearningOndas gravitacionalesLIGOConvolutional Neural NetworksCNNsIngenieríaB. P. Abbott et al. (LIGO Scientific Collaboration and Virgo Collaboration), «Observation of Gravitational Waves from a Binary Black Hole Merger», Phys. Rev. Lett. 116, 061102 (2016).J. McIver y D. H. Shoemaker, «Discovering gravitational waves with Advanced LIGO», Contemporary Physics 61, 229-255 (2020).M. Zevin et al., «Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science», Classical and Quantum Gravity 34, arXiv:1611.04596 [astro-ph, physics:gr-qc, physics:physics], 064003 (2017).B. P. Abbott et al. (LIGO Scientific Collaboration and Virgo Collaboration), «GW150914: The Advanced LIGO Detectors in the Era of First Discoveries», Phys. Rev. Lett. 116, 131103 (2016).B. P. Abbott et al. (LIGO Scientific Collaboration and Virgo Collaboration), «GWTC-1: A Gravitational-Wave Transient Catalog of Compact Binary Mergers Observed by LIGO and Virgo during the First and Second Observing Runs», en, 10.1103/PhysRevX.9.031040.B. P. Abbott et al. (LIGO Scientific Collaboration and Virgo Collaboration), «GWTC-2: Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run», en, 10.1103/PhysRevX.11.021053.B. P. Abbott et al. (LIGO Scientific Collaboration and Virgo Collaboration and KAGRA Collaboration), «GWTC-3: Compact Binary Coalescences Observed by LIGO and Virgo During the Second Part of the Third Observing Run», en, 10.48550/arXiv.2111.03606.LIGO Scientific Collaboration and Virgo Collaboration, LIGO Laboratory at Caltech and MIT.P. R. Saulson, Fundamentals of interferometric gravitational wave detectors (World Scientific, 1994).The LIGO Scientific Collaboration, What is an interferometer?J. Harms, «Terrestrial Gravity Fluctuations», Living Reviews in Relativity 22, arXiv:1507.05850 [gr-qc], 6 (2019).The LIGO Scientific Collaboration and the Virgo Collaboration, «Characterization of transient noise in Advanced LIGO relevant to gravitational wave signal GW150914», Classical and Quantum Gravity 33, arXiv:1602.03844 [astro-ph, physics:gr-qc, physics:physics], 134001 (2016).S. Anderson, K. Burtnyk y J. Kanner, LIGO-M1000066-v27: LIGO Data Management Plan, 2022.B. Berger, «Identification and mitigation of Advanced LIGO noise sources», Journal of Physics: Conference Series 957, 012004 (2018)D. Davis et al., «LIGO Detector Characterization in the Second and Third Observing Runs», Classical and Quantum Gravity 38, arXiv:2101.11673 [astro-ph, physics:gr-qc], 135014 (2021).J. S. Areeda et al., LigoDV-web: Providing easy, secure and universal access to a large distributed scientific data store for the LIGO Scientific Collaboration, arXiv:1611.01089 [astro-ph, physics:gr-qc], nov. de 2016.Jarov, S. et al., «A new method to distinguish gravitational-wave signals from detector glitches with Gravity Spy».S. Alvarez-Lopez et al., GSpyNetTree: A signal-vs-glitch classifier for gravitational-wave event candidates, 2023.A. Geron, Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow : 2nd ed., https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/ (O'Reilly Media, Inc., Mumbai, 2020).A. C. Wilson et al., The Marginal Value of Adaptive Gradient Methods in Machine Learning, 2018.D. Masters y C. Luschi, Revisiting Small Batch Training for Deep Neural Networks, 2018.IBM, What are convolutional neural networks?LIGO Scientific Collaboration, LIGO Algorithm Library - LALSuite, free software (GPL), 2018.S. Husa et al., «Frequency-domain gravitational waves from nonprecessing black-hole binaries. I. New numerical waveforms and anatomy of the signal», Phys. Rev. D 93, 044006 (2016).S. Khan et al., «Frequency-domain gravitational waves from nonprecessing black-hole binaries. II. A phenomenological model for the advanced detector era», Phys. Rev. D 93, 044007 (2016).Pace A, Prestegard T, Moe B and Stephens B, «GraceDB Gravitational-Wave Candidate Event Database», https://gracedb.ligo.org/ (2020).The LIGO Scientific Collaboration and The Virgo Collaboration, «LIGO/Virgo Alert System (LVAlert)»M. Tan y Q. V. Le, EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, 2020.C. Szegedy et al., «Rethinking the Inception Architecture for Computer Vision», en 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), págs. 2818-2826.C. Szegedy et al., «Going deeper with convolutions», en 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015), págs. 1-9.201729031PublicationCC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8799https://repositorio.uniandes.edu.co/bitstreams/b1e43b3b-200e-47da-8556-dfc231a0d387/downloadf7d494f61e544413a13e6ba1da2089cdMD52TEXTTesis Ing Sistemas GSpyNetTree Maria Sofia Alvarez Lopez.pdf.txtTesis Ing Sistemas GSpyNetTree Maria Sofia Alvarez Lopez.pdf.txtExtracted texttext/plain93565https://repositorio.uniandes.edu.co/bitstreams/a2d8ceb4-20d7-4ad2-9217-e3d07d4a5f94/downloadadbbdbdc975ed84788366c52c1bb8d61MD55Autorizacion tesis Sistemas Maria Sofia Alvarez Lopez 201729031.pdf.txtAutorizacion tesis Sistemas Maria Sofia Alvarez Lopez 201729031.pdf.txtExtracted texttext/plain1161https://repositorio.uniandes.edu.co/bitstreams/be2618da-8b06-4c79-95d4-c86b8ee8ab2d/download08b106dfeb12472e88207a069e15ba30MD57ORIGINALTesis Ing Sistemas GSpyNetTree Maria Sofia Alvarez Lopez.pdfTesis Ing Sistemas GSpyNetTree Maria Sofia Alvarez Lopez.pdfTrabajo de grado final aprobadoapplication/pdf40874871https://repositorio.uniandes.edu.co/bitstreams/d24034f0-d0ee-4b8c-b428-5360d5652ac9/download9ecfecc41421704f1ab4bde9f12751cfMD54Autorizacion tesis Sistemas Maria Sofia Alvarez Lopez 201729031.pdfAutorizacion tesis Sistemas Maria Sofia Alvarez Lopez 201729031.pdfHIDEapplication/pdf278273https://repositorio.uniandes.edu.co/bitstreams/fa8310c4-b4e7-4c0c-af4b-cf5d7e95389c/downloada8362fb718d10281b5ed76c2b2017eabMD53THUMBNAILTesis Ing Sistemas GSpyNetTree Maria Sofia Alvarez Lopez.pdf.jpgTesis Ing Sistemas GSpyNetTree Maria Sofia Alvarez Lopez.pdf.jpgIM Thumbnailimage/jpeg6285https://repositorio.uniandes.edu.co/bitstreams/d8ba35c8-6d0f-42ed-adaa-d8a40a1cfb3c/download03b504eb2d992cccccc4c047b0f4663bMD56Autorizacion tesis Sistemas Maria Sofia Alvarez Lopez 201729031.pdf.jpgAutorizacion tesis Sistemas Maria Sofia Alvarez Lopez 201729031.pdf.jpgIM Thumbnailimage/jpeg15839https://repositorio.uniandes.edu.co/bitstreams/8e445e72-637b-4252-abb4-dc24995129bc/download423290a5cb4c3d3ed2f193a6e819041bMD58LICENSElicense.txtlicense.txttext/plain; charset=utf-81810https://repositorio.uniandes.edu.co/bitstreams/dfa904c6-6a9c-49dd-8167-a11ca9e75b6a/download5aa5c691a1ffe97abd12c2966efcb8d6MD511992/68749oai:repositorio.uniandes.edu.co:1992/687492023-10-10 15:23:20.025http://creativecommons.org/licenses/by-nd/4.0/open.accesshttps://repositorio.uniandes.edu.coRepositorio institucional Sénecaadminrepositorio@uniandes.edu.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