{"id":"https://openalex.org/W4380591142","doi":"https://doi.org/10.1177/10943420231179417","title":"Black-box statistical prediction of lossy compression ratios for scientific data","display_name":"Black-box statistical prediction of lossy compression ratios for scientific data","publication_year":2023,"publication_date":"2023-06-14","ids":{"openalex":"https://openalex.org/W4380591142","doi":"https://doi.org/10.1177/10943420231179417"},"language":"en","primary_location":{"id":"doi:10.1177/10943420231179417","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420231179417","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1985174","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056940311","display_name":"Robert Underwood","orcid":"https://orcid.org/0000-0002-1464-729X"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robert Underwood","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091899229","display_name":"Julie Bessac","orcid":"https://orcid.org/0000-0001-6407-2423"},"institutions":[{"id":"https://openalex.org/I1297288678","display_name":"National Laboratory of the Rockies","ror":"https://ror.org/036266993","country_code":"US","type":"facility","lineage":["https://openalex.org/I1297288678","https://openalex.org/I1330989302","https://openalex.org/I2800842121"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie Bessac","raw_affiliation_strings":["National Renewable Energy Laboratory, Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"National Renewable Energy Laboratory, Golden, CO, USA","institution_ids":["https://openalex.org/I1297288678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078767195","display_name":"David Krasowska","orcid":"https://orcid.org/0000-0001-5411-4722"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Krasowska","raw_affiliation_strings":["Northwestern University, Evanston, IL, USA"],"affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003772863","display_name":"Jon C. Calhoun","orcid":"https://orcid.org/0000-0001-7191-4422"},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jon C Calhoun","raw_affiliation_strings":["Clemson University, Clemson, SC, USA"],"affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066430343","display_name":"Sheng Di","orcid":"https://orcid.org/0000-0002-7339-5256"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Di","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["Argonne National Laboratory, Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5056940311"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":1.722,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87297375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"37","issue":"3-4","first_page":"412","last_page":"433"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9993000030517578,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9993000030517578,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9965000152587891,"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/lossy-compression","display_name":"Lossy compression","score":0.9681606888771057},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.8190014362335205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6390581130981445},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6062960624694824},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5904139280319214},{"id":"https://openalex.org/keywords/gas-compressor","display_name":"Gas compressor","score":0.5812578201293945},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5607880353927612},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"Compression ratio","score":0.4946758449077606},{"id":"https://openalex.org/keywords/compressibility","display_name":"Compressibility","score":0.4929313659667969},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4504948854446411},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4191296398639679},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1663033664226532},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1244921088218689},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1116628646850586},{"id":"https://openalex.org/keywords/mechanics","display_name":"Mechanics","score":0.06912752985954285}],"concepts":[{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.9681606888771057},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.8190014362335205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6390581130981445},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6062960624694824},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5904139280319214},{"id":"https://openalex.org/C131097465","wikidata":"https://www.wikidata.org/wiki/Q178898","display_name":"Gas compressor","level":2,"score":0.5812578201293945},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5607880353927612},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.4946758449077606},{"id":"https://openalex.org/C84655787","wikidata":"https://www.wikidata.org/wiki/Q8067817","display_name":"Compressibility","level":2,"score":0.4929313659667969},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4504948854446411},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4191296398639679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1663033664226532},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1244921088218689},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1116628646850586},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.06912752985954285},{"id":"https://openalex.org/C511840579","wikidata":"https://www.wikidata.org/wiki/Q12757","display_name":"Internal combustion engine","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/10943420231179417","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420231179417","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:osti.gov:1985174","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1985174","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},{"id":"pmh:oai:osti.gov:2426340","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2426340","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1985174","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1985174","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1319584452","display_name":null,"funder_award_id":"Exascale Computing Project (17-SC-20-SC)","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3647494545","display_name":null,"funder_award_id":"SHF-1910197, SHF- 1943114, OAC-2003709, OAC-210402","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7954425250","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1531312210","https://openalex.org/W1634005169","https://openalex.org/W1995372796","https://openalex.org/W2021436645","https://openalex.org/W2024165284","https://openalex.org/W2024523255","https://openalex.org/W2024697317","https://openalex.org/W2052440657","https://openalex.org/W2338569857","https://openalex.org/W2486202470","https://openalex.org/W2562764966","https://openalex.org/W2607969264","https://openalex.org/W2625759119","https://openalex.org/W2741341431","https://openalex.org/W2787894218","https://openalex.org/W2804010147","https://openalex.org/W2808348679","https://openalex.org/W2886627854","https://openalex.org/W2899412261","https://openalex.org/W2899601494","https://openalex.org/W2912174957","https://openalex.org/W2940637162","https://openalex.org/W2955516565","https://openalex.org/W2959531572","https://openalex.org/W2964023000","https://openalex.org/W2964219139","https://openalex.org/W2986205304","https://openalex.org/W3004782934","https://openalex.org/W3039051431","https://openalex.org/W3042625184","https://openalex.org/W3105622770","https://openalex.org/W3112717819","https://openalex.org/W3132028106","https://openalex.org/W3138054712","https://openalex.org/W3174738244","https://openalex.org/W3216211749","https://openalex.org/W4200044278","https://openalex.org/W4205502579","https://openalex.org/W4220987233","https://openalex.org/W4229015700","https://openalex.org/W4245988203","https://openalex.org/W4250557702","https://openalex.org/W4321636572"],"related_works":["https://openalex.org/W2385628723","https://openalex.org/W2547124190","https://openalex.org/W3180760233","https://openalex.org/W3035703949","https://openalex.org/W4247601675","https://openalex.org/W1970394887","https://openalex.org/W755971114","https://openalex.org/W2118338613","https://openalex.org/W1982468865","https://openalex.org/W3080614128"],"abstract_inverted_index":{"Lossy":[0],"compressors":[1,126],"are":[2,91,102],"increasingly":[3],"adopted":[4],"in":[5,31],"scientific":[6,44,67,129],"research,":[7],"tackling":[8],"volumes":[9],"of":[10,29,39,66,78,115,147,173],"data":[11,20],"from":[12],"experiments":[13],"or":[14,36],"parallel":[15],"numerical":[16],"simulations":[17],"and":[18,22,50,93,113,117,131,164],"facilitating":[19],"storage":[21],"movement.":[23],"In":[24],"contrast":[25],"with":[26],"the":[27,120,169],"notion":[28],"entropy":[30,116],"lossless":[32],"compression,":[33],"no":[34],"theoretical":[35],"data-based":[37],"quantification":[38],"lossy":[40,54,64,79],"compressibility":[41,65],"exists":[42],"for":[43,157,159,167],"data.":[45],"Users":[46],"rely":[47],"on":[48,99,104,127],"trial":[49],"error":[51,137],"to":[52,74],"assess":[53],"compression":[55,76,106,162],"performance.":[56],"As":[57],"a":[58,71,84,133,154,160,174],"strong":[59],"data-driven":[60],"effort":[61],"toward":[62],"quantifying":[63],"datasets,":[68],"we":[69],"provide":[70],"statistical":[72,95],"framework":[73,86],"predict":[75],"ratios":[77],"compressors.":[80],"Our":[81],"method":[82],"is":[83,142],"two-step":[85],"where":[87],"(i)":[88],"compressor-agnostic":[89],"predictors":[90,101,109],"computed":[92],"(ii)":[94],"prediction":[96,136],"models":[97],"relying":[98],"these":[100],"trained":[103],"observed":[105],"ratios.":[107],"Proposed":[108],"exploit":[110],"spatial":[111],"correlations":[112],"notions":[114],"lossyness":[118],"via":[119],"quantized":[121],"entropy.":[122],"We":[123],"study":[124],"8+":[125],"6":[128],"datasets":[130],"achieve":[132],"median":[134],"percentage":[135],"less":[138],"than":[139,145],"12%,":[140],"which":[141],"substantially":[143],"smaller":[144],"that":[146],"other":[148],"methods":[149],"while":[150],"achieving":[151],"at":[152],"least":[153],"8.8\u00d7":[155],"speedup":[156,166],"searching":[158],"specific":[161],"ratio":[163],"7.8\u00d7":[165],"determining":[168],"best":[170],"compressor":[171],"out":[172],"collection.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}