{"id":"https://openalex.org/W4417335732","doi":"https://doi.org/10.1145/3764919.3770886","title":"Geo-enrichment in a Data Lakehouse: Exploring Challenges and Opportunities","display_name":"Geo-enrichment in a Data Lakehouse: Exploring Challenges and Opportunities","publication_year":2025,"publication_date":"2025-11-03","ids":{"openalex":"https://openalex.org/W4417335732","doi":"https://doi.org/10.1145/3764919.3770886"},"language":"en","primary_location":{"id":"doi:10.1145/3764919.3770886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3764919.3770886","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM SIGSPATIAL International Workshop on Spatial Big Data and AI for Industrial Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3764919.3770886","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114759855","display_name":"Venkata Sudheer Siddabattula","orcid":"https://orcid.org/0009-0005-3832-2181"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Venkata Sudheer Siddabattula","raw_affiliation_strings":["Computer Science, University of Milan, Milan, Italy"],"raw_orcid":"https://orcid.org/0009-0005-3832-2181","affiliations":[{"raw_affiliation_string":"Computer Science, University of Milan, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fatima Hachem","orcid":"https://orcid.org/0000-0002-1286-7184"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fatima Hachem","raw_affiliation_strings":["Computer Science, University of Milan, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1286-7184","affiliations":[{"raw_affiliation_string":"Computer Science, University of Milan, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089929382","display_name":"Marco Mesiti","orcid":"https://orcid.org/0000-0001-5701-0080"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Mesiti","raw_affiliation_strings":["Computer Science, University of Milan, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0001-5701-0080","affiliations":[{"raw_affiliation_string":"Computer Science, University of Milan, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069133631","display_name":"Matteo Leo","orcid":"https://orcid.org/0000-0003-3398-7983"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matteo Leo","raw_affiliation_strings":["Exprivia Spa, Bari, Italy"],"raw_orcid":"https://orcid.org/0000-0003-3398-7983","affiliations":[{"raw_affiliation_string":"Exprivia Spa, Bari, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089306459","display_name":"Gabriel De La Rosa","orcid":"https://orcid.org/0009-0000-2141-8682"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giampiero Rosa","raw_affiliation_strings":["Exprivia Spa, Bari, Italy"],"raw_orcid":"https://orcid.org/0009-0000-2141-8682","affiliations":[{"raw_affiliation_string":"Exprivia Spa, Bari, Italy","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079937994","display_name":"Maria Luisa Damiani","orcid":"https://orcid.org/0000-0001-9587-308X"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Maria Luisa Damiani","raw_affiliation_strings":["Computer Science, University of Milan, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9587-308X","affiliations":[{"raw_affiliation_string":"Computer Science, University of Milan, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"90","last_page":"98"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.6047999858856201,"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":0.6047999858856201,"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/T10757","display_name":"Geographic Information Systems Studies","score":0.1981000006198883,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social 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":0.06400000303983688,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6740000247955322},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.565500020980835},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5436999797821045},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5245000123977661},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.4498000144958496},{"id":"https://openalex.org/keywords/data-virtualization","display_name":"Data virtualization","score":0.4032000005245209},{"id":"https://openalex.org/keywords/european-union","display_name":"European union","score":0.38019999861717224},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.3625999987125397},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.3582000136375427}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6740000247955322},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6705999970436096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5985000133514404},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.565500020980835},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5245000123977661},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.4498000144958496},{"id":"https://openalex.org/C80344994","wikidata":"https://www.wikidata.org/wiki/Q5227369","display_name":"Data virtualization","level":4,"score":0.4032000005245209},{"id":"https://openalex.org/C2910001868","wikidata":"https://www.wikidata.org/wiki/Q458","display_name":"European union","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C19443361","wikidata":"https://www.wikidata.org/wiki/Q5282533","display_name":"Disparate system","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2761000096797943},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C2780535194","wikidata":"https://www.wikidata.org/wiki/Q309901","display_name":"Open data","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C188981036","wikidata":"https://www.wikidata.org/wiki/Q1502855","display_name":"Spatial data infrastructure","level":3,"score":0.2508000135421753},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3764919.3770886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3764919.3770886","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM SIGSPATIAL International Workshop on Spatial Big Data and AI for Industrial Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:air.unimi.it:2434/1202950","is_oa":true,"landing_page_url":"https://hdl.handle.net/2434/1202950","pdf_url":null,"source":{"id":"https://openalex.org/S4306400516","display_name":"Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189158943","host_organization_name":"University of Milan","host_organization_lineage":["https://openalex.org/I189158943"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"doi:10.1145/3764919.3770886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3764919.3770886","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM SIGSPATIAL International Workshop on Spatial Big Data and AI for Industrial Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2128933163","https://openalex.org/W2897711619","https://openalex.org/W3023770275","https://openalex.org/W4229377031","https://openalex.org/W4321257284","https://openalex.org/W4367032190","https://openalex.org/W4385653220","https://openalex.org/W4396571402","https://openalex.org/W4398141811","https://openalex.org/W4399458779","https://openalex.org/W4400337099","https://openalex.org/W4401933721","https://openalex.org/W4402898151","https://openalex.org/W4404481617","https://openalex.org/W4405283898","https://openalex.org/W4408167042","https://openalex.org/W4409881395"],"related_works":[],"abstract_inverted_index":{"Data":[0],"lakehouses":[1],"are":[2],"modern":[3],"data":[4,20,26,59,99,112],"architectures":[5],"designed":[6],"to":[7,35,46,96],"support":[8],"the":[9,62,71,128,139,152,155],"integrated":[10],"management":[11],"and":[12,57,74,89,106,114],"analysis":[13],"of":[14,17,64,130,138,154],"large":[15],"volumes":[16],"heterogeneous,":[18],"business-oriented":[19],"on":[21,145],"distributed":[22],"platforms.":[23],"When":[24],"such":[25],"include":[27],"spatial":[28,131],"information,":[29],"a":[30,98,124,146],"key":[31,91],"question":[32],"is":[33,75,121],"how":[34],"semantically":[36],"integrate":[37],"it":[38],"with":[39,78,116],"other":[40],"sources":[41,113],"\u2014":[42,49],"an":[43],"operation":[44],"referred":[45],"as":[47,149],"geo-enrichment":[48,65,104],"thereby":[50],"creating":[51],"new":[52],"opportunities":[53],"for":[54,108],"more":[55],"effective":[56],"insightful":[58],"analysis.":[60],"Yet,":[61],"notion":[63],"has":[66],"received":[67],"limited":[68],"attention":[69],"in":[70,123,151],"academic":[72],"literature":[73],"often":[76],"associated":[77],"commercial":[79],"information":[80],"services.":[81],"In":[82],"this":[83],"paper,":[84],"we":[85],"present":[86],"our":[87],"vision":[88],"discuss":[90],"challenges,":[92],"particularly":[93],"those":[94],"related":[95],"defining":[97],"exploration":[100],"environment":[101],"that":[102],"provides":[103],"operators":[105],"tools":[107],"both":[109],"discovering":[110],"relevant":[111],"interacting":[115],"geo-enrichable":[117],"data.":[118],"Our":[119],"discussion":[120],"grounded":[122],"use":[125],"case":[126],"involving":[127],"integration":[129],"datasets":[132],"provided":[133],"by":[134],"Eurostat\u2014the":[135],"statistical":[136],"office":[137],"European":[140],"Union":[141],"(EU)\u2014within":[142],"Apache":[143],"Sedona":[144],"Spark":[147],"cluster,":[148],"adopted":[150],"context":[153],"EU-funded":[156],"GRINS":[157],"project.":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-12T00:00:00"}
