{"id":"https://openalex.org/W4367032190","doi":"https://doi.org/10.1109/tkde.2023.3270101","title":"Data Lakes: A Survey of Functions and Systems","display_name":"Data Lakes: A Survey of Functions and Systems","publication_year":2023,"publication_date":"2023-04-25","ids":{"openalex":"https://openalex.org/W4367032190","doi":"https://doi.org/10.1109/tkde.2023.3270101"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2023.3270101","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3270101","pdf_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/10107808.pdf","source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/10107808.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046074866","display_name":"Rihan Hai","orcid":"https://orcid.org/0000-0002-3720-6585"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Rihan Hai","raw_affiliation_strings":["Department of Software Technology, Delft University of Technology, Delft, CD, Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Software Technology, Delft University of Technology, Delft, CD, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144380","display_name":"Christos Koutras","orcid":"https://orcid.org/0000-0003-3015-154X"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Christos Koutras","raw_affiliation_strings":["Department of Software Technology, Delft University of Technology, Delft, CD, Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Software Technology, Delft University of Technology, Delft, CD, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043782050","display_name":"Christoph Quix","orcid":"https://orcid.org/0000-0002-1698-4345"},"institutions":[{"id":"https://openalex.org/I4210110507","display_name":"Fraunhofer Institute for Applied Information Technology","ror":"https://ror.org/01ak24c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210110507","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4210113269","display_name":"Hochschule Niederrhein","ror":"https://ror.org/027b9qx26","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210113269"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Quix","raw_affiliation_strings":["Hochschule Niederrhein, Krefeld, Germany and Fraunhofer FIT, Hochschule Niederrhein University of Applied Sciences, Krefeld, Germany","Fraunhofer FIT, Sankt Augustin, Germany"],"affiliations":[{"raw_affiliation_string":"Hochschule Niederrhein, Krefeld, Germany and Fraunhofer FIT, Hochschule Niederrhein University of Applied Sciences, Krefeld, Germany","institution_ids":["https://openalex.org/I4210113269"]},{"raw_affiliation_string":"Fraunhofer FIT, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210110507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026501367","display_name":"Matthias Jarke","orcid":"https://orcid.org/0000-0001-6169-2942"},"institutions":[{"id":"https://openalex.org/I4210110507","display_name":"Fraunhofer Institute for Applied Information Technology","ror":"https://ror.org/01ak24c12","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210110507","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Jarke","raw_affiliation_strings":["RWTH Aachen University, Aachen, Germany","Fraunhofer FIT, Sankt Augustin, Germany"],"affiliations":[{"raw_affiliation_string":"RWTH Aachen University, Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Fraunhofer FIT, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210110507"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046074866"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":23.4588,"has_fulltext":true,"cited_by_count":94,"citation_normalized_percentile":{"value":0.99753268,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"35","issue":"12","first_page":"12571","last_page":"12590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7426638603210449},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40263134241104126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426638603210449},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40263134241104126}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tkde.2023.3270101","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3270101","pdf_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/10107808.pdf","source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/449116","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/449116","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"},{"id":"pmh:oai:tudelft.nl:uuid:3bf9e596-e126-4cdf-b4d4-55f17cd705d9","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:3bf9e596-e126-4cdf-b4d4-55f17cd705d9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1109/tkde.2023.3270101","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3270101","pdf_url":"https://ieeexplore.ieee.org/ielx7/69/4358933/10107808.pdf","source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2899823199","display_name":null,"funder_award_id":"90621612","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G4015090843","display_name":null,"funder_award_id":"HORIZON-CL4-2022-DATA-01","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5106512922","display_name":null,"funder_award_id":"Deutsche Forschungsgemeinschaft (DFG","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5814583085","display_name":null,"funder_award_id":"39062161","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5987792135","display_name":null,"funder_award_id":"HORIZON-CL4-2022","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6024419964","display_name":null,"funder_award_id":"Deutsche Forschungsgemeinschaft (DFG)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6052429835","display_name":null,"funder_award_id":"(DFG)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6532048832","display_name":null,"funder_award_id":"101093164","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G69884316","display_name":null,"funder_award_id":"EXC-2023","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7300938430","display_name":null,"funder_award_id":"390621612","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","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/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367032190.pdf","grobid_xml":"https://content.openalex.org/works/W4367032190.grobid-xml"},"referenced_works_count":161,"referenced_works":["https://openalex.org/W67838171","https://openalex.org/W195157153","https://openalex.org/W203690387","https://openalex.org/W1549099081","https://openalex.org/W1610496399","https://openalex.org/W1624245830","https://openalex.org/W1870305865","https://openalex.org/W1928156542","https://openalex.org/W1963347892","https://openalex.org/W1981420413","https://openalex.org/W2008896880","https://openalex.org/W2035196713","https://openalex.org/W2040811166","https://openalex.org/W2066806792","https://openalex.org/W2101915266","https://openalex.org/W2108940005","https://openalex.org/W2119738171","https://openalex.org/W2121495183","https://openalex.org/W2127286934","https://openalex.org/W2139445852","https://openalex.org/W2140116426","https://openalex.org/W2148781362","https://openalex.org/W2152191782","https://openalex.org/W2186090720","https://openalex.org/W2186686397","https://openalex.org/W2260616469","https://openalex.org/W2284514301","https://openalex.org/W2294209438","https://openalex.org/W2424304400","https://openalex.org/W2425316268","https://openalex.org/W2438792749","https://openalex.org/W2493970676","https://openalex.org/W2506833998","https://openalex.org/W2530589556","https://openalex.org/W2563015575","https://openalex.org/W2563724055","https://openalex.org/W2566712162","https://openalex.org/W2574643375","https://openalex.org/W2575168421","https://openalex.org/W2594409358","https://openalex.org/W2594526919","https://openalex.org/W2612261081","https://openalex.org/W2636278499","https://openalex.org/W2750856415","https://openalex.org/W2751085111","https://openalex.org/W2752618741","https://openalex.org/W2757502305","https://openalex.org/W2762305470","https://openalex.org/W2765239181","https://openalex.org/W2767448088","https://openalex.org/W2767749111","https://openalex.org/W2782682955","https://openalex.org/W2783360436","https://openalex.org/W2783664759","https://openalex.org/W2795089200","https://openalex.org/W2798664493","https://openalex.org/W2804807208","https://openalex.org/W2805350385","https://openalex.org/W2807292920","https://openalex.org/W2882319491","https://openalex.org/W2883070524","https://openalex.org/W2883354997","https://openalex.org/W2889003264","https://openalex.org/W2889394422","https://openalex.org/W2889473110","https://openalex.org/W2889541271","https://openalex.org/W2893969867","https://openalex.org/W2896457183","https://openalex.org/W2906841437","https://openalex.org/W2912169643","https://openalex.org/W2921317508","https://openalex.org/W2945198755","https://openalex.org/W2948163032","https://openalex.org/W2950817225","https://openalex.org/W2953028579","https://openalex.org/W2955074528","https://openalex.org/W2962975498","https://openalex.org/W2963174348","https://openalex.org/W2963626623","https://openalex.org/W2966267176","https://openalex.org/W2966917845","https://openalex.org/W2967736654","https://openalex.org/W2967970042","https://openalex.org/W2968441198","https://openalex.org/W2968918513","https://openalex.org/W2970059736","https://openalex.org/W2970992672","https://openalex.org/W2971220290","https://openalex.org/W2981867761","https://openalex.org/W2982640240","https://openalex.org/W2982650128","https://openalex.org/W2997427139","https://openalex.org/W2997488476","https://openalex.org/W3007408226","https://openalex.org/W3008881932","https://openalex.org/W3013008430","https://openalex.org/W3014616325","https://openalex.org/W3025775630","https://openalex.org/W3026486734","https://openalex.org/W3028240514","https://openalex.org/W3031051334","https://openalex.org/W3032215537","https://openalex.org/W3033448144","https://openalex.org/W3038576231","https://openalex.org/W3084772717","https://openalex.org/W3085477028","https://openalex.org/W3090017266","https://openalex.org/W3110281774","https://openalex.org/W3137759927","https://openalex.org/W3139217633","https://openalex.org/W3143654509","https://openalex.org/W3146147323","https://openalex.org/W3146448298","https://openalex.org/W3159846444","https://openalex.org/W3164147145","https://openalex.org/W3164968002","https://openalex.org/W3166632383","https://openalex.org/W3168288096","https://openalex.org/W3168289090","https://openalex.org/W3174637548","https://openalex.org/W3176061300","https://openalex.org/W3185492633","https://openalex.org/W3188930300","https://openalex.org/W3192755710","https://openalex.org/W3196867679","https://openalex.org/W3196877232","https://openalex.org/W3197661828","https://openalex.org/W4213009331","https://openalex.org/W4214903737","https://openalex.org/W4255463977","https://openalex.org/W4281826654","https://openalex.org/W4287265847","https://openalex.org/W4292779060","https://openalex.org/W4296973065","https://openalex.org/W4298335024","https://openalex.org/W4321448337","https://openalex.org/W6602735986","https://openalex.org/W6607795440","https://openalex.org/W6636177537","https://openalex.org/W6640850735","https://openalex.org/W6649090136","https://openalex.org/W6679058633","https://openalex.org/W6686415897","https://openalex.org/W6723501177","https://openalex.org/W6732452405","https://openalex.org/W6735106364","https://openalex.org/W6747975844","https://openalex.org/W6749511090","https://openalex.org/W6754059519","https://openalex.org/W6755207826","https://openalex.org/W6758650106","https://openalex.org/W6763444804","https://openalex.org/W6774341788","https://openalex.org/W6778883912","https://openalex.org/W6787424232","https://openalex.org/W6791306458","https://openalex.org/W6791788910","https://openalex.org/W6795402801","https://openalex.org/W6799672518","https://openalex.org/W6809779322","https://openalex.org/W6843591696"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Data":[0],"lakes":[1,24],"are":[2,25],"becoming":[3],"increasingly":[4],"prevalent":[5],"for":[6,64,99,117,128],"big":[7],"data":[8,11,21,23,29,65,72,89,103,118,133,160],"management":[9],"and":[10,34,48,61,75,86,101,110,131,144,163],"analytics.":[12],"In":[13],"contrast":[14],"to":[15],"traditional":[16],"\u2018schema-on-write\u2019":[17],"approaches":[18,109],"such":[19],"as":[20],"warehouses,":[22],"repositories":[26],"storing":[27],"raw":[28],"in":[30,151],"its":[31],"original":[32],"formats":[33],"providing":[35],"a":[36,52,93,124],"common":[37],"access":[38],"interface.":[39],"Despite":[40],"the":[41,58,83,107,138,145,156],"strong":[42],"interest":[43],"raised":[44],"from":[45],"both":[46],"academia":[47],"industry,":[49],"there":[50],"is":[51,77],"large":[53],"body":[54],"of":[55,71,88,96,141,147,159],"ambiguity":[56],"regarding":[57],"definition,":[59],"functions":[60,116],"available":[62],"technologies":[63],"lakes.":[66,90,104,134],"A":[67],"complete,":[68],"coherent":[69],"picture":[70],"lake":[73,161],"challenges":[74,150],"solutions":[76,143],"still":[78],"missing.":[79],"This":[80],"survey":[81,123,153],"reviews":[82],"development,":[84],"architectures,":[85],"systems":[87,111],"We":[91,105,135],"provide":[92],"comprehensive":[94],"overview":[95],"research":[97,149,162],"questions":[98],"designing":[100],"building":[102],"classify":[106],"existing":[108,142],"based":[112],"on":[113],"their":[114],"provided":[115],"lakes,":[119],"which":[120],"makes":[121],"this":[122,152],"useful":[125],"technical":[126],"reference":[127],"designing,":[129],"implementing":[130],"deploying":[132],"hope":[136],"that":[137],"thorough":[139],"comparison":[140],"discussion":[146],"open":[148],"will":[154],"motivate":[155],"future":[157],"development":[158],"practice.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":41},{"year":2024,"cited_by_count":37},{"year":2023,"cited_by_count":10}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}