{"id":"https://openalex.org/W4406461324","doi":"https://doi.org/10.1109/bigdata62323.2024.10825990","title":"An Active Learning-Based Streaming Pipeline for Reduced Data Training of Structure Finding Models in Neutron Diffractometry","display_name":"An Active Learning-Based Streaming Pipeline for Reduced Data Training of Structure Finding Models in Neutron Diffractometry","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406461324","doi":"https://doi.org/10.1109/bigdata62323.2024.10825990"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.11100","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101928623","display_name":"Tianle Wang","orcid":"https://orcid.org/0009-0003-7003-0264"},"institutions":[{"id":"https://openalex.org/I200870766","display_name":"Brookhaven National Laboratory","ror":"https://ror.org/02ex6cf31","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I200870766","https://openalex.org/I39565521","https://openalex.org/I4210142672"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianle Wang","raw_affiliation_strings":["Brookhaven National Laboratory,Computational Science Initiative,USA"],"affiliations":[{"raw_affiliation_string":"Brookhaven National Laboratory,Computational Science Initiative,USA","institution_ids":["https://openalex.org/I200870766"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100688216","display_name":"Jorge Ramirez","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":"Jorge Ramirez","raw_affiliation_strings":["Oak Ridge National Laboratory,Computer Science and Mathematics Division,USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,Computer Science and Mathematics Division,USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086975677","display_name":"Cristina Garc\u00eda\u2013Cardona","orcid":"https://orcid.org/0000-0002-5641-3491"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cristina Garcia-Cardona","raw_affiliation_strings":["Los Alamos National Laboratory,Computer, Computational and Statistical Sciences Division,USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory,Computer, Computational and Statistical Sciences Division,USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073026110","display_name":"Thomas Proffen","orcid":"https://orcid.org/0000-0002-1408-6031"},"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"]},{"id":"https://openalex.org/I4390039231","display_name":"Spallation Neutron Source","ror":"https://ror.org/00q6v6102","country_code":null,"type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294","https://openalex.org/I4390039231"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Proffen","raw_affiliation_strings":["Oak Ridge National Laboratory,Spallation Neutron Source,USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,Spallation Neutron Source,USA","institution_ids":["https://openalex.org/I1289243028","https://openalex.org/I4390039231"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038763846","display_name":"Shantenu Jha","orcid":"https://orcid.org/0000-0002-5040-026X"},"institutions":[{"id":"https://openalex.org/I200870766","display_name":"Brookhaven National Laboratory","ror":"https://ror.org/02ex6cf31","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I200870766","https://openalex.org/I39565521","https://openalex.org/I4210142672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shantenu Jha","raw_affiliation_strings":["Brookhaven National Laboratory,Computational Science Initiative,USA"],"affiliations":[{"raw_affiliation_string":"Brookhaven National Laboratory,Computational Science Initiative,USA","institution_ids":["https://openalex.org/I200870766"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039319913","display_name":"Sudip K. Seal","orcid":"https://orcid.org/0000-0003-3233-0656"},"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":"Sudip K. Seal","raw_affiliation_strings":["Oak Ridge National Laboratory,Computer Science and Mathematics Division,USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory,Computer Science and Mathematics Division,USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101928623"],"corresponding_institution_ids":["https://openalex.org/I200870766"],"apc_list":null,"apc_paid":null,"fwci":0.1187,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43921341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1873","last_page":"1882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12613","display_name":"X-ray Diffraction in Crystallography","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11949","display_name":"Nuclear Physics and Applications","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7791851758956909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5889782309532166},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5109397768974304},{"id":"https://openalex.org/keywords/neutron","display_name":"Neutron","score":0.49545466899871826},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45656025409698486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4234652519226074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3361446261405945},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.19912710785865784},{"id":"https://openalex.org/keywords/nuclear-physics","display_name":"Nuclear physics","score":0.16905567049980164},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0828065574169159}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7791851758956909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5889782309532166},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5109397768974304},{"id":"https://openalex.org/C152568617","wikidata":"https://www.wikidata.org/wiki/Q2348","display_name":"Neutron","level":2,"score":0.49545466899871826},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45656025409698486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4234652519226074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3361446261405945},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.19912710785865784},{"id":"https://openalex.org/C185544564","wikidata":"https://www.wikidata.org/wiki/Q81197","display_name":"Nuclear physics","level":1,"score":0.16905567049980164},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0828065574169159},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.11100","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11100","pdf_url":"https://arxiv.org/pdf/2506.11100","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.11100","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11100","pdf_url":"https://arxiv.org/pdf/2506.11100","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"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":33,"referenced_works":["https://openalex.org/W1967485833","https://openalex.org/W2052257784","https://openalex.org/W2285142160","https://openalex.org/W2916386941","https://openalex.org/W2939793355","https://openalex.org/W2951278093","https://openalex.org/W2951911250","https://openalex.org/W2966764197","https://openalex.org/W2981272655","https://openalex.org/W2986050396","https://openalex.org/W3000216503","https://openalex.org/W3008213669","https://openalex.org/W3046195400","https://openalex.org/W3100784768","https://openalex.org/W3121513412","https://openalex.org/W3130134189","https://openalex.org/W3132277775","https://openalex.org/W3139362221","https://openalex.org/W3183645185","https://openalex.org/W3200767119","https://openalex.org/W3203287979","https://openalex.org/W3203718464","https://openalex.org/W4225399934","https://openalex.org/W4280588983","https://openalex.org/W4280589740","https://openalex.org/W4286308244","https://openalex.org/W4286905150","https://openalex.org/W4319792360","https://openalex.org/W4366386839","https://openalex.org/W6695741466","https://openalex.org/W6759450206","https://openalex.org/W6761329413","https://openalex.org/W6764723987"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Structure":[0],"determination":[1],"workloads":[2],"in":[3,120],"neutron":[4,26,38],"diffractometry":[5],"are":[6],"computationally":[7],"expensive":[8],"and":[9,73,151],"routinely":[10],"require":[11],"several":[12],"hours":[13],"to":[14,17,41,58,70,96,160],"many":[15],"days":[16],"determine":[18],"the":[19,52,65,111,122,133,138,169],"structure":[20],"of":[21,54,67,140,181],"a":[22,75,85,102,153,165],"material":[23],"from":[24,101],"its":[25,118],"diffraction":[27],"patterns.":[28],"The":[29],"potential":[30],"for":[31],"machine":[32],"learning":[33,89],"models":[34,61,124],"trained":[35],"on":[36,156],"simulated":[37,55],"scattering":[39],"patterns":[40],"significantly":[42],"speed":[43],"up":[44],"these":[45,60],"tasks":[46],"have":[47],"been":[48],"reported":[49],"recently.":[50],"However,":[51],"amount":[53],"data":[56,99,130],"needed":[57],"train":[59],"grows":[62],"exponentially":[63],"with":[64,125,164],"number":[66],"structural":[68],"parameters":[69],"be":[71],"predicted":[72],"poses":[74],"significant":[76],"computational":[77],"challenge.":[78],"To":[79],"overcome":[80],"this":[81,148],"challenge,":[82],"we":[83],"introduce":[84],"novel":[86],"batch-mode":[87],"active":[88],"(AL)":[90],"policy":[91,150],"that":[92,105,146],"uses":[93,147],"uncertainty":[94],"sampling":[95],"simulate":[97],"training":[98,121,129,144,167,176],"drawn":[100],"probability":[103],"distribution":[104],"prefers":[106],"labelled":[107],"examples":[108],"about":[109],"which":[110],"model":[112],"is":[113],"least":[114],"certain.":[115],"We":[116,135],"confirm":[117],"efficacy":[119],"same":[123],"\u223c":[126,173],"75%":[127],"less":[128],"while":[131],"improving":[132],"accuracy.":[134,182],"then":[136],"discuss":[137],"design":[139],"an":[141],"efficient":[142],"stream-based":[143],"workflow":[145,171],"AL":[149],"present":[152],"performance":[154],"study":[155],"two":[157],"heterogeneous":[158],"platforms":[159],"demonstrate":[161],"that,":[162],"compared":[163],"conventional":[166],"workflow,":[168],"streaming":[170],"delivers":[172],"20%":[174],"shorter":[175],"time":[177],"without":[178],"any":[179],"loss":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}