{"id":"https://openalex.org/W4409255526","doi":"https://doi.org/10.1007/s41060-025-00751-w","title":"Leveraging active learning for ocean data quality assessment: reducing labeling workload and addressing severe data imbalance challenges","display_name":"Leveraging active learning for ocean data quality assessment: reducing labeling workload and addressing severe data imbalance challenges","publication_year":2025,"publication_date":"2025-04-08","ids":{"openalex":"https://openalex.org/W4409255526","doi":"https://doi.org/10.1007/s41060-025-00751-w"},"language":"en","primary_location":{"id":"doi:10.1007/s41060-025-00751-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-025-00751-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-025-00751-w.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s41060-025-00751-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100368028","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-7799-876X"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Na Li","raw_affiliation_strings":["MultiScale Networked Systems (MNS), University of Amsterdam, Lab42, Amsterdam, 1098XH, North Holland, Netherlands"],"affiliations":[{"raw_affiliation_string":"MultiScale Networked Systems (MNS), University of Amsterdam, Lab42, Amsterdam, 1098XH, North Holland, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090417231","display_name":"Yiyang Qi","orcid":"https://orcid.org/0009-0000-3105-806X"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yiyang Qi","raw_affiliation_strings":["MultiScale Networked Systems (MNS), University of Amsterdam, Lab42, Amsterdam, 1098XH, North Holland, Netherlands"],"affiliations":[{"raw_affiliation_string":"MultiScale Networked Systems (MNS), University of Amsterdam, Lab42, Amsterdam, 1098XH, North Holland, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073878572","display_name":"Ruyue Xin","orcid":"https://orcid.org/0000-0001-5821-4835"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ruyue Xin","raw_affiliation_strings":["MultiScale Networked Systems (MNS), University of Amsterdam, Lab42, Amsterdam, 1098XH, North Holland, Netherlands"],"affiliations":[{"raw_affiliation_string":"MultiScale Networked Systems (MNS), University of Amsterdam, Lab42, Amsterdam, 1098XH, North Holland, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056039834","display_name":"Peide Zhu","orcid":"https://orcid.org/0000-0002-9801-8473"},"institutions":[{"id":"https://openalex.org/I4210112943","display_name":"Department of Virology","ror":"https://ror.org/01xx2ne27","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I157536573","https://openalex.org/I4210096427","https://openalex.org/I4210112943"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Peide Zhu","raw_affiliation_strings":["LifeWatch ERIC Virtual Lab and Innovation Center (VLIC), Lab42, Amsterdam, 1098XH, North Holland, Netherlands"],"affiliations":[{"raw_affiliation_string":"LifeWatch ERIC Virtual Lab and Innovation Center (VLIC), Lab42, Amsterdam, 1098XH, North Holland, Netherlands","institution_ids":["https://openalex.org/I4210112943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068341719","display_name":"Zhiming Zhao","orcid":"https://orcid.org/0000-0002-6717-9418"},"institutions":[{"id":"https://openalex.org/I4210112943","display_name":"Department of Virology","ror":"https://ror.org/01xx2ne27","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I157536573","https://openalex.org/I4210096427","https://openalex.org/I4210112943"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["FR","NL"],"is_corresponding":false,"raw_author_name":"Zhiming Zhao","raw_affiliation_strings":["LifeWatch ERIC Virtual Lab and Innovation Center (VLIC), Lab42, Amsterdam, 1098XH, North Holland, Netherlands","MultiScale Networked Systems (MNS), University of Amsterdam, Lab42, Amsterdam, 1098XH, North Holland, Netherlands"],"affiliations":[{"raw_affiliation_string":"LifeWatch ERIC Virtual Lab and Innovation Center (VLIC), Lab42, Amsterdam, 1098XH, North Holland, Netherlands","institution_ids":["https://openalex.org/I4210112943"]},{"raw_affiliation_string":"MultiScale Networked Systems (MNS), University of Amsterdam, Lab42, Amsterdam, 1098XH, North Holland, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100368028"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":2.2283,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88063355,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"20","issue":"5","first_page":"4777","last_page":"4798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.7232888340950012},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5469563007354736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5430201888084412},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5162336826324463},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38029924035072327},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.16022229194641113},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12378087639808655}],"concepts":[{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7232888340950012},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5469563007354736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5430201888084412},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5162336826324463},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38029924035072327},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.16022229194641113},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12378087639808655},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s41060-025-00751-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-025-00751-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-025-00751-w.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},{"id":"pmh:oai:dare.uva.nl:openaire/f3baf601-2ab9-499e-8289-51458b5e37bc","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/leveraging-active-learning-for-ocean-data-quality-assessment(f3baf601-2ab9-499e-8289-51458b5e37bc).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Li, N, Qi, Y, Xin, R, Zhu, P & Zhao, Z 2025, 'Leveraging active learning for ocean data quality assessment : reducing labeling workload and addressing severe data imbalance challenges', International Journal of Data Science and Analytics, vol. 20, no. 5, pp. 4777-4798. https://doi.org/10.1007/s41060-025-00751-w","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1007/s41060-025-00751-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-025-00751-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-025-00751-w.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2300613588","display_name":null,"funder_award_id":"860627","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G639993763","display_name":null,"funder_award_id":"101129751","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6801968305","display_name":"ENVironmental Research Infrastructures delivering an open access Hub and NEXT-level interdisciplinary research framework providing services for advancing science and society","funder_award_id":"101131141","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G724472640","display_name":"European Virtual Institute for Research Software Excellence","funder_award_id":"101129744","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8072458336","display_name":null,"funder_award_id":"101094227","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320325020","display_name":"LifeWatch \u2013 Niclas \u00d6berg Foundation","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409255526.pdf","grobid_xml":"https://content.openalex.org/works/W4409255526.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W2080021732","https://openalex.org/W2099550922","https://openalex.org/W2118978333","https://openalex.org/W2148143831","https://openalex.org/W2150900085","https://openalex.org/W2165837041","https://openalex.org/W2198764335","https://openalex.org/W2201182621","https://openalex.org/W2289669588","https://openalex.org/W2295598076","https://openalex.org/W2296719434","https://openalex.org/W2549804226","https://openalex.org/W2612634114","https://openalex.org/W2626931877","https://openalex.org/W2887831728","https://openalex.org/W2911293880","https://openalex.org/W2911495555","https://openalex.org/W2911964244","https://openalex.org/W2912083425","https://openalex.org/W2913130920","https://openalex.org/W2977942577","https://openalex.org/W2984303785","https://openalex.org/W2989219518","https://openalex.org/W3021412770","https://openalex.org/W3094509504","https://openalex.org/W3158273053","https://openalex.org/W3205626500","https://openalex.org/W4254182148","https://openalex.org/W4362673537","https://openalex.org/W4382516701","https://openalex.org/W4391094988","https://openalex.org/W6677457979","https://openalex.org/W6963601256"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2137479650","https://openalex.org/W2245479382","https://openalex.org/W3139296374","https://openalex.org/W4387803644","https://openalex.org/W4210350690"],"abstract_inverted_index":{"Abstract":[0],"Oceanic":[1],"research":[2],"initiatives":[3],"like":[4,92],"Argo,":[5],"GLOSS,":[6],"and":[7,17,35,40,78,179],"EMSO":[8],"aim":[9],"to":[10,64,107,172],"enhance":[11],"our":[12],"understanding":[13],"of":[14,26,76],"the":[15,24,123,142,174,185,191],"oceans":[16],"climate":[18],"through":[19],"extensive":[20],"data":[21,28,33,77,94,118,124,138,163,182,203],"collection.":[22],"Maintaining":[23],"quality":[25,50,204,210],"collected":[27],"is":[29,160],"essential":[30],"for":[31,86,97,120,151,177,197],"effective":[32,208],"analysis":[34],"real-world":[36],"applications.":[37],"While":[38],"automated":[39],"semi-automated":[41,209],"tests":[42],"can":[43,72],"provide":[44],"real-time":[45],"or":[46],"near-real-time":[47],"validation,":[48],"thorough":[49],"control":[51,211],"still":[52],"depends":[53],"on":[54,162],"operator":[55],"review.":[56],"Consequently,":[57],"current":[58],"Quality":[59],"Control":[60],"(QC)":[61],"processes":[62],"continue":[63],"be":[65],"labor-intensive.":[66],"Machine":[67],"Learning":[68],"(ML)":[69],"methods,":[70],"which":[71],"analyze":[73],"vast":[74],"amounts":[75],"learn":[79],"complex":[80],"patterns":[81],"autonomously,":[82],"offer":[83],"significant":[84,181],"potential":[85],"improving":[87],"QC":[88,109],"processes.":[89],"However,":[90],"challenges":[91],"severe":[93],"disproportion":[95],"persist":[96],"ML":[98],"approaches.":[99],"This":[100],"article":[101],"proposes":[102],"exploiting":[103],"active":[104,199],"learning":[105,200],"(AL)":[106],"assist":[108],"experts,":[110],"reducing":[111,155],"their":[112],"workload":[113,176],"by":[114,165],"proactively":[115],"selecting":[116],"informative":[117],"points":[119],"labeling.":[121],"Targeting":[122],"distribution":[125],"challenge,":[126],"AL,":[127,146],"coupled":[128],"with":[129],"imbalance-resilient":[130],"classifiers,":[131,153],"enhances":[132],"model":[133],"performance":[134],"in":[135,145,189,201],"recognizing":[136],"erroneous":[137],"points.":[139],"To":[140],"mitigate":[141],"cold-start":[143],"problem":[144],"we":[147],"propose":[148],"outlier":[149],"detection":[150],"initializing":[152],"significantly":[154],"annotation":[156],"costs.":[157],"Our":[158],"approach":[159],"tested":[161],"generated":[164],"5":[166],"Argo":[167],"floats,":[168],"demonstrating":[169],"its":[170],"feasibility":[171],"lessen":[173],"labeling":[175],"experts":[178],"tackle":[180],"imbalance.":[183],"Although":[184],"experiments":[186],"are":[187],"limited":[188],"scale,":[190],"findings":[192],"indicate":[193],"a":[194],"promising":[195],"outlook":[196],"using":[198],"ocean":[202],"assessment,":[205],"facilitating":[206],"an":[207],"framework.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
