Gravity Spy: lessons learned and a path forward. Zevin, M., Jackson, C. B., Doctor, Z., Wu, Y., Østerlund, C., Johnson, L. C., Berry, C. P., Crowston, K., Coughlin, S. B., Kalogera, V., Banagiri, S., Davis, D., Glanzer, J., Hao, R., Katsaggelos, A. K., Patane, O., Sanchez, J., Smith, J., Soni, S., Trouille, L., Walker, M., Aerith, I., Domainko, W., Baranowski, V. G., Niklasch, G., & Téglás, B. European Physical Journal Plus, 139(1):100, Springer Berlin Heidelberg Berlin/Heidelberg, 2024. doi abstract bibtex The Gravity Spy project aims to uncover the origins of glitches, transient bursts of noise that hamper analysis of gravitational-wave data. By using both the work of citizen-science volunteers and machine learning algorithms, the Gravity Spy project enables reliable classification of glitches. Citizen science and machine learning are intrinsically coupled within the Gravity Spy framework, with machine learning classifications providing a rapid first-pass classification of the dataset and enabling tiered volunteer training, and volunteer-based classifications verifying the machine classifications, bolstering the machine learning training set and identifying new morphological classes of glitches. These classifications are now routinely used in studies characterizing the performance of the LIGO gravitational-wave detectors. Providing the volunteers with a training framework that teaches them to classify a wide range of glitches, as well as additional tools to aid their investigations of interesting glitches, empowers them to make discoveries of new classes of glitches. This demonstrates that, when giving suitable support, volunteers can go beyond simple classification tasks to identify new features in data at a level comparable to domain experts. The Gravity Spy project is now providing volunteers with more complicated data that includes auxiliary monitors of the detector to identify the root cause of glitches.
@article{zevin2024gravity,
abstract = {The Gravity Spy project aims to uncover the origins of glitches, transient bursts of noise that hamper analysis of gravitational-wave data. By using both the work of citizen-science volunteers and machine learning algorithms, the Gravity Spy project enables reliable classification of glitches. Citizen science and machine learning are intrinsically coupled within the Gravity Spy framework, with machine learning classifications providing a rapid first-pass classification of the dataset and enabling tiered volunteer training, and volunteer-based classifications verifying the machine classifications, bolstering the machine learning training set and identifying new morphological classes of glitches. These classifications are now routinely used in studies characterizing the performance of the LIGO gravitational-wave detectors. Providing the volunteers with a training framework that teaches them to classify a wide range of glitches, as well as additional tools to aid their investigations of interesting glitches, empowers them to make discoveries of new classes of glitches. This demonstrates that, when giving suitable support, volunteers can go beyond simple classification tasks to identify new features in data at a level comparable to domain experts. The Gravity Spy project is now providing volunteers with more complicated data that includes auxiliary monitors of the detector to identify the root cause of glitches.},
archivePrefix = {arXiv},
arxivId = {2308.15530},
author = {Zevin, Michael and Jackson, Corey B. and Doctor, Zoheyr and Wu, Yunan and {\O}sterlund, Carsten and Johnson, L. Clifton and Berry, Christopher P.L. and Crowston, Kevin and Coughlin, Scott B. and Kalogera, Vicky and Banagiri, Sharan and Davis, Derek and Glanzer, Jane and Hao, Renzhi and Katsaggelos, Aggelos K. and Patane, Oli and Sanchez, Jennifer and Smith, Joshua and Soni, Siddharth and Trouille, Laura and Walker, Marissa and Aerith, Irina and Domainko, Wilfried and Baranowski, Victor Georges and Niklasch, Gerhard and T{\'{e}}gl{\'{a}}s, Barbara},
doi = {10.1140/epjp/s13360-023-04795-4},
eprint = {2308.15530},
issn = {21905444},
journal = {European Physical Journal Plus},
number = {1},
pages = {100},
publisher = {Springer Berlin Heidelberg Berlin/Heidelberg},
title = {{Gravity Spy: lessons learned and a path forward}},
volume = {139},
year = {2024}
}
Downloads: 0
{"_id":"Aq76QuBi9jbvxHGmA","bibbaseid":"zevin-jackson-doctor-wu-sterlund-johnson-berry-crowston-etal-gravityspylessonslearnedandapathforward-2024","author_short":["Zevin, M.","Jackson, C. B.","Doctor, Z.","Wu, Y.","Østerlund, C.","Johnson, L. C.","Berry, C. P.","Crowston, K.","Coughlin, S. B.","Kalogera, V.","Banagiri, S.","Davis, D.","Glanzer, J.","Hao, R.","Katsaggelos, A. K.","Patane, O.","Sanchez, J.","Smith, J.","Soni, S.","Trouille, L.","Walker, M.","Aerith, I.","Domainko, W.","Baranowski, V. G.","Niklasch, G.","Téglás, B."],"bibdata":{"bibtype":"article","type":"article","abstract":"The Gravity Spy project aims to uncover the origins of glitches, transient bursts of noise that hamper analysis of gravitational-wave data. By using both the work of citizen-science volunteers and machine learning algorithms, the Gravity Spy project enables reliable classification of glitches. Citizen science and machine learning are intrinsically coupled within the Gravity Spy framework, with machine learning classifications providing a rapid first-pass classification of the dataset and enabling tiered volunteer training, and volunteer-based classifications verifying the machine classifications, bolstering the machine learning training set and identifying new morphological classes of glitches. These classifications are now routinely used in studies characterizing the performance of the LIGO gravitational-wave detectors. Providing the volunteers with a training framework that teaches them to classify a wide range of glitches, as well as additional tools to aid their investigations of interesting glitches, empowers them to make discoveries of new classes of glitches. This demonstrates that, when giving suitable support, volunteers can go beyond simple classification tasks to identify new features in data at a level comparable to domain experts. The Gravity Spy project is now providing volunteers with more complicated data that includes auxiliary monitors of the detector to identify the root cause of glitches.","archiveprefix":"arXiv","arxivid":"2308.15530","author":[{"propositions":[],"lastnames":["Zevin"],"firstnames":["Michael"],"suffixes":[]},{"propositions":[],"lastnames":["Jackson"],"firstnames":["Corey","B."],"suffixes":[]},{"propositions":[],"lastnames":["Doctor"],"firstnames":["Zoheyr"],"suffixes":[]},{"propositions":[],"lastnames":["Wu"],"firstnames":["Yunan"],"suffixes":[]},{"propositions":[],"lastnames":["Østerlund"],"firstnames":["Carsten"],"suffixes":[]},{"propositions":[],"lastnames":["Johnson"],"firstnames":["L.","Clifton"],"suffixes":[]},{"propositions":[],"lastnames":["Berry"],"firstnames":["Christopher","P.L."],"suffixes":[]},{"propositions":[],"lastnames":["Crowston"],"firstnames":["Kevin"],"suffixes":[]},{"propositions":[],"lastnames":["Coughlin"],"firstnames":["Scott","B."],"suffixes":[]},{"propositions":[],"lastnames":["Kalogera"],"firstnames":["Vicky"],"suffixes":[]},{"propositions":[],"lastnames":["Banagiri"],"firstnames":["Sharan"],"suffixes":[]},{"propositions":[],"lastnames":["Davis"],"firstnames":["Derek"],"suffixes":[]},{"propositions":[],"lastnames":["Glanzer"],"firstnames":["Jane"],"suffixes":[]},{"propositions":[],"lastnames":["Hao"],"firstnames":["Renzhi"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]},{"propositions":[],"lastnames":["Patane"],"firstnames":["Oli"],"suffixes":[]},{"propositions":[],"lastnames":["Sanchez"],"firstnames":["Jennifer"],"suffixes":[]},{"propositions":[],"lastnames":["Smith"],"firstnames":["Joshua"],"suffixes":[]},{"propositions":[],"lastnames":["Soni"],"firstnames":["Siddharth"],"suffixes":[]},{"propositions":[],"lastnames":["Trouille"],"firstnames":["Laura"],"suffixes":[]},{"propositions":[],"lastnames":["Walker"],"firstnames":["Marissa"],"suffixes":[]},{"propositions":[],"lastnames":["Aerith"],"firstnames":["Irina"],"suffixes":[]},{"propositions":[],"lastnames":["Domainko"],"firstnames":["Wilfried"],"suffixes":[]},{"propositions":[],"lastnames":["Baranowski"],"firstnames":["Victor","Georges"],"suffixes":[]},{"propositions":[],"lastnames":["Niklasch"],"firstnames":["Gerhard"],"suffixes":[]},{"propositions":[],"lastnames":["Téglás"],"firstnames":["Barbara"],"suffixes":[]}],"doi":"10.1140/epjp/s13360-023-04795-4","eprint":"2308.15530","issn":"21905444","journal":"European Physical Journal Plus","number":"1","pages":"100","publisher":"Springer Berlin Heidelberg Berlin/Heidelberg","title":"Gravity Spy: lessons learned and a path forward","volume":"139","year":"2024","bibtex":"@article{zevin2024gravity,\nabstract = {The Gravity Spy project aims to uncover the origins of glitches, transient bursts of noise that hamper analysis of gravitational-wave data. By using both the work of citizen-science volunteers and machine learning algorithms, the Gravity Spy project enables reliable classification of glitches. Citizen science and machine learning are intrinsically coupled within the Gravity Spy framework, with machine learning classifications providing a rapid first-pass classification of the dataset and enabling tiered volunteer training, and volunteer-based classifications verifying the machine classifications, bolstering the machine learning training set and identifying new morphological classes of glitches. These classifications are now routinely used in studies characterizing the performance of the LIGO gravitational-wave detectors. Providing the volunteers with a training framework that teaches them to classify a wide range of glitches, as well as additional tools to aid their investigations of interesting glitches, empowers them to make discoveries of new classes of glitches. This demonstrates that, when giving suitable support, volunteers can go beyond simple classification tasks to identify new features in data at a level comparable to domain experts. The Gravity Spy project is now providing volunteers with more complicated data that includes auxiliary monitors of the detector to identify the root cause of glitches.},\narchivePrefix = {arXiv},\narxivId = {2308.15530},\nauthor = {Zevin, Michael and Jackson, Corey B. and Doctor, Zoheyr and Wu, Yunan and {\\O}sterlund, Carsten and Johnson, L. Clifton and Berry, Christopher P.L. and Crowston, Kevin and Coughlin, Scott B. and Kalogera, Vicky and Banagiri, Sharan and Davis, Derek and Glanzer, Jane and Hao, Renzhi and Katsaggelos, Aggelos K. and Patane, Oli and Sanchez, Jennifer and Smith, Joshua and Soni, Siddharth and Trouille, Laura and Walker, Marissa and Aerith, Irina and Domainko, Wilfried and Baranowski, Victor Georges and Niklasch, Gerhard and T{\\'{e}}gl{\\'{a}}s, Barbara},\ndoi = {10.1140/epjp/s13360-023-04795-4},\neprint = {2308.15530},\nissn = {21905444},\njournal = {European Physical Journal Plus},\nnumber = {1},\npages = {100},\npublisher = {Springer Berlin Heidelberg Berlin/Heidelberg},\ntitle = {{Gravity Spy: lessons learned and a path forward}},\nvolume = {139},\nyear = {2024}\n}\n","author_short":["Zevin, M.","Jackson, C. B.","Doctor, Z.","Wu, Y.","Østerlund, C.","Johnson, L. C.","Berry, C. P.","Crowston, K.","Coughlin, S. B.","Kalogera, V.","Banagiri, S.","Davis, D.","Glanzer, J.","Hao, R.","Katsaggelos, A. K.","Patane, O.","Sanchez, J.","Smith, J.","Soni, S.","Trouille, L.","Walker, M.","Aerith, I.","Domainko, W.","Baranowski, V. G.","Niklasch, G.","Téglás, B."],"key":"zevin2024gravity","id":"zevin2024gravity","bibbaseid":"zevin-jackson-doctor-wu-sterlund-johnson-berry-crowston-etal-gravityspylessonslearnedandapathforward-2024","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2024/05/IVPL_pubs_until_20240423-40b288e64aa42570.txt","dataSources":["teJzFLHexaz5AQW5z"],"keywords":[],"search_terms":["gravity","spy","lessons","learned","path","forward","zevin","jackson","doctor","wu","østerlund","johnson","berry","crowston","coughlin","kalogera","banagiri","davis","glanzer","hao","katsaggelos","patane","sanchez","smith","soni","trouille","walker","aerith","domainko","baranowski","niklasch","téglás"],"title":"Gravity Spy: lessons learned and a path forward","year":2024}