{"id":"https://openalex.org/W4415626538","doi":"https://doi.org/10.1109/tpds.2025.3623935","title":"Scalable Hybrid Learning Techniques for Scientific Data Compression","display_name":"Scalable Hybrid Learning Techniques for Scientific Data Compression","publication_year":2025,"publication_date":"2025-10-28","ids":{"openalex":"https://openalex.org/W4415626538","doi":"https://doi.org/10.1109/tpds.2025.3623935"},"language":null,"primary_location":{"id":"doi:10.1109/tpds.2025.3623935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3623935","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Parallel and Distributed Systems","raw_type":"journal-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/A5073938611","display_name":"Tania Banerjee","orcid":"https://orcid.org/0000-0003-4737-0001"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tania Banerjee","raw_affiliation_strings":["University of Florida, Gainesville, FL, USA","University of Florida, USA"],"raw_orcid":"https://orcid.org/0000-0003-4737-0001","affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"University of Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108926899","display_name":"Jong Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jong Choi","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA","Oak Ridge National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-6459-6152","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057988780","display_name":"Jaemoon Lee","orcid":"https://orcid.org/0000-0002-9868-9410"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaemoon Lee","raw_affiliation_strings":["University of Florida, Gainesville, FL, USA","University of Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"University of Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063502813","display_name":"Qian Gong","orcid":"https://orcid.org/0000-0002-3570-4142"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Gong","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA","Oak Ridge National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-3570-4142","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063649910","display_name":"Jieyang Chen","orcid":"https://orcid.org/0000-0002-1905-9171"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jieyang Chen","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA","Oak Ridge National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0002-1905-9171","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030373337","display_name":"Scott Klasky","orcid":"https://orcid.org/0000-0003-3559-5772"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Klasky","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA","Oak Ridge National Laboratory, USA"],"raw_orcid":"https://orcid.org/0000-0003-3559-5772","affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059870257","display_name":"Anand Rangarajan","orcid":"https://orcid.org/0000-0001-8695-8436"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Rangarajan","raw_affiliation_strings":["University of Florida, Gainesville, FL, USA","University of Florida, USA"],"raw_orcid":"https://orcid.org/0000-0001-8695-8436","affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"University of Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077570468","display_name":"Sanjay Ranka","orcid":"https://orcid.org/0000-0003-4886-1988"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Ranka","raw_affiliation_strings":["University of Florida, Gainesville, FL, USA","University of Florida, USA"],"raw_orcid":"https://orcid.org/0000-0003-4886-1988","affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"University of Florida, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.275035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"1","first_page":"29","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.36090001463890076,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.36090001463890076,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.11270000040531158,"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":0.08739999681711197,"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":0.815500020980835},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.7749999761581421},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.6370999813079834},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.5116000175476074},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4528000056743622},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.45170000195503235},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.43299999833106995},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.4293000102043152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8407999873161316},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.815500020980835},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.7749999761581421},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.6370999813079834},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.5116000175476074},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.46140000224113464},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.45170000195503235},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39570000767707825},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.38769999146461487},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.35269999504089355},{"id":"https://openalex.org/C54243161","wikidata":"https://www.wikidata.org/wiki/Q39333","display_name":"Texture compression","level":5,"score":0.31850001215934753},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.263700008392334},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2556000053882599},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2025.3623935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3623935","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1982388645","https://openalex.org/W1984845482","https://openalex.org/W1984958640","https://openalex.org/W2025945642","https://openalex.org/W2033468335","https://openalex.org/W2048494347","https://openalex.org/W2052440657","https://openalex.org/W2065360261","https://openalex.org/W2083045868","https://openalex.org/W2142265837","https://openalex.org/W2486202470","https://openalex.org/W2625759119","https://openalex.org/W2793315650","https://openalex.org/W2899601494","https://openalex.org/W2904210572","https://openalex.org/W2912174957","https://openalex.org/W2940637162","https://openalex.org/W2955516565","https://openalex.org/W2969494351","https://openalex.org/W3041193038","https://openalex.org/W3103841771","https://openalex.org/W3126702256","https://openalex.org/W3164444385","https://openalex.org/W3167885647","https://openalex.org/W3174738244","https://openalex.org/W3206053086","https://openalex.org/W4206831315","https://openalex.org/W4220775246","https://openalex.org/W4230804723","https://openalex.org/W4250589301","https://openalex.org/W4283645263","https://openalex.org/W4283777163","https://openalex.org/W4367147520"],"related_works":[],"abstract_inverted_index":{"Data":[0],"compression":[1,32,43,58,69,76,84,127,165],"is":[2,129],"becoming":[3],"critical":[4],"for":[5,25,67,184,194],"storing":[6],"scientific":[7,11,26],"data":[8,19,24,39,68,100,126,136,150],"because":[9],"many":[10],"applications":[12],"need":[13],"to":[14,37,95,108],"store":[15],"large":[16],"amounts":[17],"of":[18,50,124,147,149,169,179],"and":[20,30,82,102,162],"post":[21],"process":[22],"this":[23,72],"discovery.":[27],"Unlike":[28],"image":[29],"video":[31],"algorithms":[33],"that":[34,45,70],"limit":[35],"errors":[36],"primary":[38],"(PD),":[40],"scientists":[41],"require":[42],"techniques":[44,81],"accurately":[46],"preserve":[47,109],"derived":[48],"quantities":[49],"interest":[51],"(QoIs).":[52],"This":[53],"paper":[54],"presents":[55],"a":[56,103,113,139,152,167,176],"physics-informed":[57],"technique":[59,77],"implemented":[60],"as":[61],"an":[62,89,91],"end-to-end,":[63],"scalable,":[64],"GPU-based":[65],"pipeline":[66,128],"addresses":[71],"requirement.":[73],"Our":[74,155],"hybrid":[75],"combines":[78],"machine":[79],"learning":[80],"standard":[83],"methods.":[85],"Specifically,":[86],"we":[87],"combine":[88],"autoencoder,":[90],"error-bounded":[92],"lossy":[93],"compressor":[94],"provide":[96],"guarantees":[97],"on":[98],"raw":[99],"error,":[101],"constraint":[104],"satisfaction":[105],"post-processing":[106],"step":[107],"the":[110,125,159,180,186,189],"QoIs":[111],"within":[112,158],"minimal":[114],"error":[115],"(generally":[116],"less":[117],"than":[118,171],"floating":[119],"point":[120],"error).":[121],"The":[122],"effectiveness":[123],"demonstrated":[130],"by":[131,138,166],"compressing":[132],"nuclear":[133],"fusion":[134,141],"simulation":[135],"generated":[137],"large-scale":[140],"code,":[142],"XGC,":[143],"which":[144],"produces":[145],"hundreds":[146],"terabytes":[148],"in":[151,164],"single":[153],"day.":[154],"approach":[156,191],"works":[157],"ADIOS":[160],"framework":[161],"results":[163],"factor":[168],"more":[170],"150":[172],"while":[173],"requiring":[174],"only":[175],"few":[177],"percent":[178],"computational":[181],"resources":[182],"necessary":[183],"generating":[185],"data,":[187],"making":[188],"overall":[190],"highly":[192],"effective":[193],"practical":[195],"scenarios.":[196]},"counts_by_year":[],"updated_date":"2025-11-20T23:13:51.555489","created_date":"2025-10-29T00:00:00"}