{"id":"https://openalex.org/W2201763571","doi":"https://doi.org/10.1109/bigdata.2015.7363778","title":"Spatially clustered join on heterogeneous scientific data sets","display_name":"Spatially clustered join on heterogeneous scientific data sets","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2201763571","doi":"https://doi.org/10.1109/bigdata.2015.7363778","mag":"2201763571"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101687868","display_name":"Bin Dong","orcid":"https://orcid.org/0000-0002-0725-0833"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bin Dong","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062233562","display_name":"Suren Byna","orcid":"https://orcid.org/0000-0003-3048-3448"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Surendra Byna","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043129695","display_name":"Kesheng Wu","orcid":"https://orcid.org/0000-0002-6907-3393"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kesheng Wu","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101687868"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":1.7517,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8698493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"44","issue":null,"first_page":"371","last_page":"380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9990000128746033,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9984999895095825,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8314580321311951},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6111587285995483},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.5782744288444519},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.5424005389213562},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5122565627098083},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4977905750274658},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.4645148813724518},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.45044058561325073},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4410941004753113},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43491944670677185},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.431969553232193},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.4136647582054138},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3813523054122925},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13906961679458618}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8314580321311951},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6111587285995483},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.5782744288444519},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.5424005389213562},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5122565627098083},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4977905750274658},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.4645148813724518},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.45044058561325073},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4410941004753113},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43491944670677185},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.431969553232193},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.4136647582054138},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3813523054122925},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13906961679458618},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2015.7363778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.714.7052","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.714.7052","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://sdm.lbl.gov/%7Esbyna/research/papers/201510-BigData-SpatialCluster.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W597956076","https://openalex.org/W1569878055","https://openalex.org/W1586179960","https://openalex.org/W1961332808","https://openalex.org/W1986056848","https://openalex.org/W1993172344","https://openalex.org/W2002779106","https://openalex.org/W2013896112","https://openalex.org/W2014830756","https://openalex.org/W2021593960","https://openalex.org/W2032756564","https://openalex.org/W2036090066","https://openalex.org/W2048026762","https://openalex.org/W2053087996","https://openalex.org/W2060098952","https://openalex.org/W2084757499","https://openalex.org/W2124105793","https://openalex.org/W2125184461","https://openalex.org/W2138143219","https://openalex.org/W2140980002","https://openalex.org/W2155603580","https://openalex.org/W2156077349","https://openalex.org/W2161692763","https://openalex.org/W2295596515","https://openalex.org/W2413469520","https://openalex.org/W2498603544","https://openalex.org/W2990075684","https://openalex.org/W4247616591","https://openalex.org/W6770669002"],"related_works":["https://openalex.org/W2556786504","https://openalex.org/W2152149667","https://openalex.org/W4244527061","https://openalex.org/W2469357693","https://openalex.org/W3125756434","https://openalex.org/W1977383094","https://openalex.org/W2572349046","https://openalex.org/W1779612025","https://openalex.org/W2413368787","https://openalex.org/W1515213763"],"abstract_inverted_index":{"In":[0,124],"the":[1,18,78,100,195],"era":[2],"of":[3,20,77,207],"data-intensive":[4],"scientific":[5,32,118,176,247],"discovery,":[6],"data":[7,21,33,41,68,82,86,104,137,141,153,177,204,215,243,265],"analysis":[8,34,119],"is":[9,35,52,74],"critical":[10],"for":[11,182,246],"scientists":[12],"to":[13,36,80,84,92,98,131,139,148,179,198,229,258],"identify":[14],"essential":[15],"information":[16,38],"from":[17,39,142],"mountains":[19],"generated":[22,217],"by":[23,218,249],"large-scale":[24,268],"simulations":[25],"or":[26,91],"experiments.":[27],"A":[28],"generic":[29],"operation":[30,51,65],"in":[31,46,58,70,211,262],"combine":[37],"multiple":[40,67],"sets,":[42],"which":[43],"are":[44],"stored":[45],"heterogeneous":[47],"ile":[48,200],"formats.":[49],"This":[50],"typically":[53],"known":[54,156,166],"as":[55,108,122,157,167],"a":[56,63,88,95,135,149,152,162,219,240,267],"Join":[57,170],"database":[59],"management":[60,244],"field.":[61],"Currently,":[62],"join":[64,101,163],"involving":[66],"sets":[69,216],"different":[71,143],"file":[72,144],"formats":[73,145],"time-consuming":[75],"because":[76],"need":[79],"prepare":[81],"(i.e.,":[83],"convert":[85],"into":[87,94],"uniform":[89,150],"format":[90,201],"ingest":[93],"database)":[96],"and":[97,161,189,203,213],"run":[99],"algorithms.":[102],"Furthermore,":[103],"processing":[105,164,184],"languages,":[106],"such":[107,121],"SQL":[109],"(Structured":[110],"Query":[111],"Language),":[112],"can":[113],"not":[114],"easily":[115],"express":[116],"typical":[117],"tasks":[120],"interpolation.":[123],"this":[125],"paper,":[126],"we":[127],"propose":[128],"three":[129],"techniques":[130,174,210],"address":[132],"these":[133,173],"challenges:":[134],"two-level":[136],"model":[138],"process":[140],"without":[146,194],"converting":[147],"format,":[151],"organization":[154],"structure":[155],"Multi-Dimensional":[158],"Binning":[159],"(MDBin),":[160],"algorithm":[165],"Spatially":[168],"Clustered":[169],"(SCJoin).":[171],"Together,":[172],"allow":[175],"files":[178],"be":[180],"used":[181],"query":[183,191],"with":[185,235],"less":[186],"I/O":[187],"cost":[188,197],"fast":[190],"response":[192],"time":[193],"extra":[196],"perform":[199],"conversion":[202],"ingestion.":[205],"Evaluation":[206],"our":[208,236,255],"proposed":[209],"joining":[212],"interpolating":[214],"plasma":[220],"physics":[221],"simulation":[222],"studying":[223],"space":[224],"weather":[225],"phenomenon":[226],"showed":[227],"up":[228],"8X":[230],"improvement":[231],"over":[232],"FastQuery.":[233],"Querying":[234],"solution":[237],"outperforms":[238],"SciDB,":[239],"popular":[241],"array":[242],"system":[245],"data,":[248],"43X-143X.":[250],"We":[251],"also":[252],"demonstrate":[253],"that":[254],"methods":[256],"scale":[257],"64K":[259],"CPU":[260],"cores":[261],"analyzing":[263],"32TB":[264],"on":[266],"supercomputing":[269],"system.":[270]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}