{"id":"https://openalex.org/W2894676653","doi":"https://doi.org/10.1080/17538947.2018.1523957","title":"A hierarchical indexing strategy for optimizing Apache Spark with HDFS to efficiently query big geospatial raster data","display_name":"A hierarchical indexing strategy for optimizing Apache Spark with HDFS to efficiently query big geospatial raster data","publication_year":2018,"publication_date":"2018-10-04","ids":{"openalex":"https://openalex.org/W2894676653","doi":"https://doi.org/10.1080/17538947.2018.1523957","mag":"2894676653"},"language":"en","primary_location":{"id":"doi:10.1080/17538947.2018.1523957","is_oa":false,"landing_page_url":"https://doi.org/10.1080/17538947.2018.1523957","pdf_url":null,"source":{"id":"https://openalex.org/S199162493","display_name":"International Journal of Digital Earth","issn_l":"1753-8947","issn":["1753-8947","1753-8955"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Digital Earth","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"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/A5068236378","display_name":"Fei Hu","orcid":"https://orcid.org/0000-0001-5231-2303"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Hu","raw_affiliation_strings":["Center for Open-Source Data and AI Technologies, IBM, San\u00a0Francisco, CA, USA","NSF Spatiotemporal Innovation Center and Dept. of Geography and GeoInformation Sciences, George Mason University, Fairfax, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Open-Source Data and AI Technologies, IBM, San\u00a0Francisco, CA, USA","institution_ids":[]},{"raw_affiliation_string":"NSF Spatiotemporal Innovation Center and Dept. of Geography and GeoInformation Sciences, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048422487","display_name":"Chaowei Yang","orcid":"https://orcid.org/0000-0001-7768-4066"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chaowei Yang","raw_affiliation_strings":["NSF Spatiotemporal Innovation Center and Dept. of Geography and GeoInformation Sciences, George Mason University, Fairfax, VA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7768-4066","affiliations":[{"raw_affiliation_string":"NSF Spatiotemporal Innovation Center and Dept. of Geography and GeoInformation Sciences, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067064849","display_name":"Yongyao Jiang","orcid":"https://orcid.org/0000-0002-4591-483X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongyao Jiang","raw_affiliation_strings":["NSF Spatiotemporal Innovation Center and Dept. of Geography and GeoInformation Sciences, George Mason University, Fairfax, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSF Spatiotemporal Innovation Center and Dept. of Geography and GeoInformation Sciences, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051497691","display_name":"Yun Li","orcid":"https://orcid.org/0000-0002-3205-8464"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Li","raw_affiliation_strings":["NSF Spatiotemporal Innovation Center and Dept. of Geography and GeoInformation Sciences, George Mason University, Fairfax, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSF Spatiotemporal Innovation Center and Dept. of Geography and GeoInformation Sciences, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019995639","display_name":"Weiwei Song","orcid":"https://orcid.org/0000-0001-5089-4127"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiwei Song","raw_affiliation_strings":["NSF Spatiotemporal Innovation Center and Dept. of Geography and GeoInformation Sciences, George Mason University, Fairfax, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSF Spatiotemporal Innovation Center and Dept. of Geography and GeoInformation Sciences, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108701773","display_name":"Daniel Q. Duffy","orcid":null},"institutions":[{"id":"https://openalex.org/I1306266525","display_name":"Goddard Space Flight Center","ror":"https://ror.org/0171mag52","country_code":"US","type":"facility","lineage":["https://openalex.org/I1306266525","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Q. Duffy","raw_affiliation_strings":["Office of Computational and Information Sciences and Technology, NASA Goddard Space Flight Center, Greenbelt, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Office of Computational and Information Sciences and Technology, NASA Goddard Space Flight Center, Greenbelt, MD, USA","institution_ids":["https://openalex.org/I1306266525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028328772","display_name":"John L. Schnase","orcid":"https://orcid.org/0000-0001-7473-3977"},"institutions":[{"id":"https://openalex.org/I1306266525","display_name":"Goddard Space Flight Center","ror":"https://ror.org/0171mag52","country_code":"US","type":"facility","lineage":["https://openalex.org/I1306266525","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John L. Schnase","raw_affiliation_strings":["NASA Center for Climate Simulation, Goddard Space Flight Center, Greenbelt, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NASA Center for Climate Simulation, Goddard Space Flight Center, Greenbelt, MD, USA","institution_ids":["https://openalex.org/I1306266525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066382672","display_name":"Tsengdar Lee","orcid":"https://orcid.org/0000-0001-7900-0019"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsengdar Lee","raw_affiliation_strings":["Earth Science Division, NASA Headquarters, Washington, DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Earth Science Division, NASA Headquarters, Washington, DC, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5048422487"],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":{"value":2390,"currency":"USD","value_usd":2390},"apc_paid":null,"fwci":1.8282,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.86541849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"13","issue":"3","first_page":"410","last_page":"428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9909999966621399,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7766318321228027},{"id":"https://openalex.org/keywords/geospatial-analysis","display_name":"Geospatial analysis","score":0.7751336097717285},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7039699554443359},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6527597308158875},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6226878762245178},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5460687875747681},{"id":"https://openalex.org/keywords/raster-data","display_name":"Raster data","score":0.5143545866012573},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.43136218190193176},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4192945063114166},{"id":"https://openalex.org/keywords/raster-graphics","display_name":"Raster graphics","score":0.4005391597747803},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39583781361579895},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.22677090764045715},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17257905006408691},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.12146136164665222},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10937181115150452},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.09142604470252991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766318321228027},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.7751336097717285},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7039699554443359},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6527597308158875},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6226878762245178},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5460687875747681},{"id":"https://openalex.org/C2692088","wikidata":"https://www.wikidata.org/wiki/Q182270","display_name":"Raster data","level":3,"score":0.5143545866012573},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.43136218190193176},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4192945063114166},{"id":"https://openalex.org/C181844469","wikidata":"https://www.wikidata.org/wiki/Q182270","display_name":"Raster graphics","level":2,"score":0.4005391597747803},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39583781361579895},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.22677090764045715},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17257905006408691},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.12146136164665222},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10937181115150452},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.09142604470252991},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/17538947.2018.1523957","is_oa":false,"landing_page_url":"https://doi.org/10.1080/17538947.2018.1523957","pdf_url":null,"source":{"id":"https://openalex.org/S199162493","display_name":"International Journal of Digital Earth","issn_l":"1753-8947","issn":["1753-8947","1753-8955"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Digital Earth","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:55ec0b4052244cffb8f279db316b35b4","is_oa":false,"landing_page_url":"https://doaj.org/article/55ec0b4052244cffb8f279db316b35b4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Digital Earth, Vol 13, Iss 3, Pp 410-428 (2020)","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6689570972","display_name":null,"funder_award_id":"NNX15AM85G","funder_id":"https://openalex.org/F4320306101","funder_display_name":"National Aeronautics and Space Administration"}],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1448378977","https://openalex.org/W2008196645","https://openalex.org/W2014830756","https://openalex.org/W2029084939","https://openalex.org/W2095483845","https://openalex.org/W2098994245","https://openalex.org/W2149173084","https://openalex.org/W2151135734","https://openalex.org/W2153226019","https://openalex.org/W2185162820","https://openalex.org/W2298833372","https://openalex.org/W2345500432","https://openalex.org/W2527514331","https://openalex.org/W2547221248","https://openalex.org/W2548753368","https://openalex.org/W2564060673","https://openalex.org/W2792297482","https://openalex.org/W2795901271","https://openalex.org/W2963097326"],"related_works":["https://openalex.org/W1997953140","https://openalex.org/W4245508207","https://openalex.org/W2996808565","https://openalex.org/W2371122778","https://openalex.org/W1488652151","https://openalex.org/W2026066822","https://openalex.org/W2768758348","https://openalex.org/W3102510374","https://openalex.org/W2558523485","https://openalex.org/W2954918491"],"abstract_inverted_index":{"Earth":[0],"observations":[1],"and":[2,38,89,103,160,171],"model":[3],"simulations":[4],"are":[5,153],"generating":[6],"big":[7,20,49,191],"multidimensional":[8],"array-based":[9],"raster":[10,21,30,109],"data.":[11],"However,":[12],"it":[13],"is":[14],"difficult":[15],"to":[16,24,60,105,128,140,180,188],"efficiently":[17,47],"query":[18,143,194],"these":[19],"data":[22,31,35,40,82,91,110,127,132,137,148,193],"due":[23],"the":[25,28,39,71,80,86,95,118,125,142,157,164],"inconsistency":[26],"among":[27],"geospatial":[29,50,108,131,192],"model,":[32,37],"distributed":[33,43,182],"physical":[34],"storage":[36],"pipeline":[41],"in":[42],"computing":[44,186],"frameworks.":[45],"To":[46],"process":[48],"data,":[51],"this":[52],"paper":[53],"proposes":[54],"a":[55,136],"three-layer":[56],"hierarchical":[57],"indexing":[58,175],"strategy":[59,139,176],"optimize":[61],"Apache":[62],"Spark":[63,102,169],"with":[64,166,195],"Hadoop":[65],"Distributed":[66],"File":[67],"System":[68],"(HDFS)":[69],"from":[70],"following":[72],"aspects:":[73],"(1)":[74],"improve":[75,130],"I/O":[76],"efficiency":[77],"by":[78,93,116,155,162],"adopting":[79],"chunking":[81],"structure;":[83],"(2)":[84],"keep":[85],"workload":[87],"balance":[88],"high":[90,147,196],"locality":[92],"building":[94,117],"global":[96],"index":[97,120,124],"(k-d":[98],"tree);":[99],"(3)":[100],"enable":[101],"HDFS":[104],"natively":[106,189],"support":[107,190],"formats":[111],"(e.g.,":[112],"HDF4,":[113],"NetCDF4,":[114],"GeoTiff)":[115],"local":[119],"(hash":[121],"table);":[122],"(4)":[123],"in-memory":[126],"further":[129],"queries;":[133],"(5)":[134],"develop":[135],"repartition":[138],"tune":[141],"parallelism":[144],"while":[145],"keeping":[146],"locality.":[149],"The":[150,173],"above":[151],"strategies":[152],"implemented":[154],"developing":[156],"customized":[158],"RDDs,":[159],"evaluated":[161],"comparing":[163],"performance":[165],"that":[167],"of":[168],"SQL":[170],"SciSpark.":[172],"proposed":[174],"can":[177],"be":[178],"applied":[179],"other":[181],"frameworks":[183],"or":[184],"cloud-based":[185],"systems":[187],"efficiency.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
