{"id":"https://openalex.org/W2734256217","doi":"https://doi.org/10.1109/tkde.2017.2720168","title":"Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data","display_name":"Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data","publication_year":2017,"publication_date":"2017-06-29","ids":{"openalex":"https://openalex.org/W2734256217","doi":"https://doi.org/10.1109/tkde.2017.2720168","mag":"2734256217"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2017.2720168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2017.2720168","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1612.08544","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081622450","display_name":"Anuj Karpatne","orcid":"https://orcid.org/0000-0003-1647-3534"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anuj Karpatne","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047757229","display_name":"Gowtham Atluri","orcid":"https://orcid.org/0000-0001-5619-6688"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gowtham Atluri","raw_affiliation_strings":["University of Cincinnati, Cincinnati, OH"],"affiliations":[{"raw_affiliation_string":"University of Cincinnati, Cincinnati, OH","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039706852","display_name":"James H. Faghmous","orcid":"https://orcid.org/0000-0001-7317-5707"},"institutions":[{"id":"https://openalex.org/I98704320","display_name":"Icahn School of Medicine at Mount Sinai","ror":"https://ror.org/04a9tmd77","country_code":"US","type":"education","lineage":["https://openalex.org/I1320796813","https://openalex.org/I98704320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James H. Faghmous","raw_affiliation_strings":["Icahn School of Medicine at Mount Sinai, New York, NY"],"affiliations":[{"raw_affiliation_string":"Icahn School of Medicine at Mount Sinai, New York, NY","institution_ids":["https://openalex.org/I98704320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089436894","display_name":"Michael Steinbach","orcid":"https://orcid.org/0000-0002-7309-6395"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Steinbach","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014459472","display_name":"Arindam Banerjee","orcid":"https://orcid.org/0000-0002-7856-5699"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arindam Banerjee","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064658255","display_name":"Auroop R. Ganguly","orcid":"https://orcid.org/0000-0002-4292-4856"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Auroop Ganguly","raw_affiliation_strings":["Northeastern University, Boston, MA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102940260","display_name":"Shashi Shekhar","orcid":"https://orcid.org/0000-0002-3191-3879"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shashi Shekhar","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014949576","display_name":"Nagiza Samatova","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nagiza Samatova","raw_affiliation_strings":["North Carolina State University, Raleigh, NC"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100645812","display_name":"Vipin Kumar","orcid":"https://orcid.org/0000-0002-9040-2665"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vipin Kumar","raw_affiliation_strings":["University of Minnesota, Minneapolis, MN"],"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, MN","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5081622450"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":157.3914,"has_fulltext":false,"cited_by_count":1432,"citation_normalized_percentile":{"value":0.99967023,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"29","issue":"10","first_page":"2318","last_page":"2331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13398","display_name":"Data Analysis with R","score":0.9908000230789185,"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/T11937","display_name":"Research Data Management Practices","score":0.9629999995231628,"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/data-science","display_name":"Data science","score":0.676803469657898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6472725868225098},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6415107250213623},{"id":"https://openalex.org/keywords/scientific-discovery","display_name":"Scientific discovery","score":0.5760732293128967},{"id":"https://openalex.org/keywords/data-discovery","display_name":"Data discovery","score":0.5147119164466858},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46267813444137573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1832091510295868},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.15887340903282166},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14500772953033447},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.09474563598632812}],"concepts":[{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.676803469657898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6472725868225098},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6415107250213623},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.5760732293128967},{"id":"https://openalex.org/C2777516300","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data discovery","level":3,"score":0.5147119164466858},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46267813444137573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1832091510295868},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.15887340903282166},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14500772953033447},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.09474563598632812},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tkde.2017.2720168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2017.2720168","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1612.08544","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.08544","pdf_url":"https://arxiv.org/pdf/1612.08544","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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:1612.08544","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.08544","pdf_url":"https://arxiv.org/pdf/1612.08544","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":[{"score":0.8299999833106995,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G2019237434","display_name":null,"funder_award_id":"#1029711","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":104,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1447128777","https://openalex.org/W1480376833","https://openalex.org/W1485293642","https://openalex.org/W1494137514","https://openalex.org/W1497745584","https://openalex.org/W1498183065","https://openalex.org/W1516407653","https://openalex.org/W1522319528","https://openalex.org/W1528439235","https://openalex.org/W1800731030","https://openalex.org/W1901616594","https://openalex.org/W1941098055","https://openalex.org/W1970554427","https://openalex.org/W1971782730","https://openalex.org/W1978559313","https://openalex.org/W1980640510","https://openalex.org/W1982598895","https://openalex.org/W1987371344","https://openalex.org/W1990633230","https://openalex.org/W1990797806","https://openalex.org/W2000009216","https://openalex.org/W2010189695","https://openalex.org/W2019440647","https://openalex.org/W2021972235","https://openalex.org/W2026480276","https://openalex.org/W2030976617","https://openalex.org/W2032417721","https://openalex.org/W2044306058","https://openalex.org/W2045272935","https://openalex.org/W2058349530","https://openalex.org/W2068181924","https://openalex.org/W2078178396","https://openalex.org/W2086601127","https://openalex.org/W2097487180","https://openalex.org/W2103018059","https://openalex.org/W2108738385","https://openalex.org/W2110418811","https://openalex.org/W2112420033","https://openalex.org/W2113328646","https://openalex.org/W2114660177","https://openalex.org/W2115570304","https://openalex.org/W2117239687","https://openalex.org/W2117380102","https://openalex.org/W2123306226","https://openalex.org/W2123615155","https://openalex.org/W2124098688","https://openalex.org/W2124220537","https://openalex.org/W2124738823","https://openalex.org/W2126681669","https://openalex.org/W2130694448","https://openalex.org/W2132555912","https://openalex.org/W2138019504","https://openalex.org/W2138914055","https://openalex.org/W2139433170","https://openalex.org/W2148603752","https://openalex.org/W2159287270","https://openalex.org/W2162584119","https://openalex.org/W2163605009","https://openalex.org/W2165960883","https://openalex.org/W2182802049","https://openalex.org/W2195080394","https://openalex.org/W2245998324","https://openalex.org/W2293634267","https://openalex.org/W2395060098","https://openalex.org/W2398062891","https://openalex.org/W2400197280","https://openalex.org/W2410883106","https://openalex.org/W2418421170","https://openalex.org/W2428977877","https://openalex.org/W2462395039","https://openalex.org/W2466424288","https://openalex.org/W2469732900","https://openalex.org/W2482589566","https://openalex.org/W2498607333","https://openalex.org/W2538573120","https://openalex.org/W2594632285","https://openalex.org/W2614083378","https://openalex.org/W2620485168","https://openalex.org/W2622626827","https://openalex.org/W2722058651","https://openalex.org/W2950547155","https://openalex.org/W2962757926","https://openalex.org/W2963071675","https://openalex.org/W3105469151","https://openalex.org/W3202333041","https://openalex.org/W3203998685","https://openalex.org/W4231204432","https://openalex.org/W4238444188","https://openalex.org/W4245033352","https://openalex.org/W4413288418","https://openalex.org/W6607333740","https://openalex.org/W6629935912","https://openalex.org/W6655719384","https://openalex.org/W6674560329","https://openalex.org/W6676077707","https://openalex.org/W6680896613","https://openalex.org/W6683362450","https://openalex.org/W6684191040","https://openalex.org/W6691136659","https://openalex.org/W6696934422","https://openalex.org/W6737804099","https://openalex.org/W6801708263","https://openalex.org/W6824129819"],"related_works":["https://openalex.org/W2126681669","https://openalex.org/W988580544","https://openalex.org/W2148010638","https://openalex.org/W2218434502","https://openalex.org/W3202643159","https://openalex.org/W2413102523","https://openalex.org/W2399037375","https://openalex.org/W1539622965","https://openalex.org/W2210409742","https://openalex.org/W4231842067"],"abstract_inverted_index":{"Data":[0],"science":[1,24,45],"models,":[2,74],"although":[3],"successful":[4],"in":[5,15,47,97,136,146],"a":[6,98,131],"number":[7,99],"of":[8,36,43,54,90,100,127,133,160,164,172],"commercial":[9],"domains,":[10],"have":[11],"had":[12],"limited":[13],"applicability":[14],"scientific":[16,37,49,59,80,101],"problems":[17],"involving":[18],"complex":[19],"physical":[20],"phenomena.":[21],"Theory-guided":[22],"data":[23,44,174],"(TGDS)":[25],"is":[26,56],"an":[27,62],"emerging":[28],"paradigm":[29,89,126],"that":[30],"aims":[31,76],"to":[32,57,77,94],"leverage":[33],"the":[34,41,88,125,161,169],"wealth":[35],"knowledge":[38,145],"for":[39,65,142,167],"improving":[40],"effectiveness":[42],"models":[46],"enabling":[48],"discovery.":[50],"The":[51],"overarching":[52],"vision":[53],"TGDS":[55,75,91,128],"introduce":[58],"consistency":[60],"as":[61,104],"essential":[63],"component":[64],"learning":[66],"generalizable":[67],"models.":[68],"Further,":[69],"by":[70,82],"producing":[71],"scientifically":[72],"interpretable":[73],"advance":[78],"our":[79],"understanding":[81],"discovering":[83],"novel":[84,165],"domain":[85,144],"insights.":[86],"Indeed,":[87],"has":[92],"started":[93],"gain":[95],"prominence":[96],"disciplines":[102],"such":[103],"turbulence":[105],"modeling,":[106],"material":[107],"discovery,":[108,114],"quantum":[109],"chemistry,":[110],"bio-medical":[111],"science,":[112,116],"bio-marker":[113],"climate":[115],"and":[117,129],"hydrology.":[118],"In":[119],"this":[120],"paper,":[121],"we":[122],"formally":[123],"conceptualize":[124],"present":[130],"taxonomy":[132],"research":[134,148,166],"themes":[135,149],"TGDS.":[137],"We":[138,156],"describe":[139],"several":[140],"approaches":[141],"integrating":[143],"different":[147,154],"using":[150],"illustrative":[151],"examples":[152],"from":[153],"disciplines.":[155],"also":[157],"highlight":[158],"some":[159],"promising":[162],"avenues":[163],"realizing":[168],"full":[170],"potential":[171],"theory-guided":[173],"science.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":112},{"year":2025,"cited_by_count":230},{"year":2024,"cited_by_count":224},{"year":2023,"cited_by_count":208},{"year":2022,"cited_by_count":209},{"year":2021,"cited_by_count":220},{"year":2020,"cited_by_count":138},{"year":2019,"cited_by_count":60},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":7}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}