{"id":"https://openalex.org/W7214593386","doi":"https://doi.org/10.26434/chemrxiv.15009531/v1","title":"Active Atom Identification for Information-Dense Training of Machine-Learning Potentials in Catalysis","display_name":"Active Atom Identification for Information-Dense Training of Machine-Learning Potentials in Catalysis","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214593386","doi":"https://doi.org/10.26434/chemrxiv.15009531/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15009531/v1","doi":"https://doi.org/10.26434/chemrxiv.15009531/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009531/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009531/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009531/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101124507","display_name":"Haobo Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobo Zhao","raw_affiliation_strings":["Department of Chemistry","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047146284","display_name":"Xiongwei Tian","orcid":"https://orcid.org/0009-0008-8065-7104","observed_orcids":["https://orcid.org/0009-0008-8065-7104"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongwei Tian","raw_affiliation_strings":["Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Department of Energy and Power Engineering","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Department of Energy and Power Engineering","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153291619","display_name":"Jixuan Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixuan Lin","raw_affiliation_strings":["Department of Chemistry","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153328345","display_name":"Yuqun Zhuo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqun Zhuo","raw_affiliation_strings":["Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Department of Energy and Power Engineering","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Department of Energy and Power Engineering","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120991410","display_name":"Yiming Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]},{"id":"https://openalex.org/I4405286224","display_name":"Advanced Institute for Materials Research, Tohoku University","ror":"https://ror.org/01gpt6p30","country_code":"JP","type":"facility","lineage":["https://openalex.org/I201537933","https://openalex.org/I4405286224"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yiming Lu","raw_affiliation_strings":["Advanced Institute for Materials Research (WPI-AIMR","Tohoku University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Institute for Materials Research (WPI-AIMR","institution_ids":["https://openalex.org/I4405286224"]},{"raw_affiliation_string":"Tohoku University","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153321168","display_name":"Hai Xiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Xiao","raw_affiliation_strings":["Department of Chemistry","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153351270","display_name":"Jun Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]},{"id":"https://openalex.org/I4210098034","display_name":"Key Laboratory of Guangdong Province","ror":"https://ror.org/00swtqp09","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210098034"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["Chinese Academy of Science","Department of Chemistry","Department of Chemistry and Guangdong Provincial Key Laboratory of Catalytic Chemistry","Ganjiang Innovation Academy","Southern University of Science and Technology","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Science","institution_ids":[]},{"raw_affiliation_string":"Department of Chemistry","institution_ids":[]},{"raw_affiliation_string":"Department of Chemistry and Guangdong Provincial Key Laboratory of Catalytic Chemistry","institution_ids":["https://openalex.org/I4210098034"]},{"raw_affiliation_string":"Ganjiang Innovation Academy","institution_ids":[]},{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153315033","display_name":"Zhao Haobo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao Haobo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9990000128746033,"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":0.9990000128746033,"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/T10002","display_name":"Advanced Chemical Physics Studies","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"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/machine-learning-interatomic-potentials","display_name":"machine learning interatomic potentials","score":0.8450000286102295},{"id":"https://openalex.org/keywords/heterogeneous-catalysis","display_name":"heterogeneous catalysis","score":0.8059999942779541},{"id":"https://openalex.org/keywords/active-site-identification","display_name":"active site identification","score":0.47999998927116394},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.574999988079071},{"id":"https://openalex.org/keywords/training-sample-selection","display_name":"training data selection","score":0.6539999842643738},{"id":"https://openalex.org/keywords/co2-adsorption","display_name":"CO2 adsorption","score":0.7419999837875366},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.8519999980926514},{"id":"https://openalex.org/keywords/potential-energy-surface","display_name":"potential energy surface","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.626800000667572},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5223000049591064},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C58312451","wikidata":"https://www.wikidata.org/wiki/Q4817200","display_name":"Atom (system on chip)","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.39010000228881836},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.38600000739097595},{"id":"https://openalex.org/C152365726","wikidata":"https://www.wikidata.org/wiki/Q1048589","display_name":"Density functional theory","level":2,"score":0.3628000020980835},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C159467904","wikidata":"https://www.wikidata.org/wiki/Q2001702","display_name":"Chemical physics","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C41183919","wikidata":"https://www.wikidata.org/wiki/Q423026","display_name":"Active site","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3109000027179718},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3037000000476837},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15009531/v1","doi":"https://doi.org/10.26434/chemrxiv.15009531/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009531/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009531/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15009531/v1","doi":"https://doi.org/10.26434/chemrxiv.15009531/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009531/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009531/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G137275667","display_name":null,"funder_award_id":"22525302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5085971758","display_name":null,"funder_award_id":"22388102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8661098714","display_name":null,"funder_award_id":"2022YFA1503000","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214593386.pdf","grobid_xml":"https://content.openalex.org/works/W7214593386.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4417114399","https://openalex.org/W7162567796"],"related_works":["https://openalex.org/W4402438846","https://openalex.org/W4408690571","https://openalex.org/W4313652679","https://openalex.org/W4384079969","https://openalex.org/W7128532453","https://openalex.org/W7216038633","https://openalex.org/W4413942145","https://openalex.org/W7162022550","https://openalex.org/W7202186124","https://openalex.org/W7118885072"],"abstract_inverted_index":{"Machine-learning":[0],"potentials":[1],"(MLPs)":[2],"extend":[3],"atomistic":[4,197],"simulations":[5],"beyond":[6],"the":[7,30,142,146,149],"size":[8],"and":[9,87,107,116,169,176],"time":[10],"scales":[11],"accessible":[12],"to":[13,94],"density":[14],"functional":[15],"theory":[16],"while":[17],"retaining":[18],"near-first-principles":[19],"accuracy.":[20],"However,":[21],"their":[22,177],"reliability":[23],"depends":[24],"on":[25,98,135],"training":[26],"data":[27,112],"that":[28,82,91],"cover":[29],"relevant":[31,68],"potential-energy":[32],"surface":[33],"(PES).":[34],"In":[35],"heterogeneous":[36],"catalysis,":[37],"local":[38,84,183],"changes":[39],"at":[40,129],"active":[41,89],"sites":[42],"may":[43],"be":[44],"obscured":[45],"by":[46],"redundant":[47],"nonactive":[48],"atoms":[49,90],"when":[50],"configurations":[51],"are":[52],"selected":[53],"using":[54],"global":[55],"metrics.":[56],"This":[57],"limitation":[58],"calls":[59],"for":[60,64,123,166,190],"an":[61,80,136,187],"atom-resolved":[62,100],"criterion":[63,189],"identifying":[65],"where":[66],"chemically":[67],"configurational":[69,95],"information":[70],"is":[71,157],"concentrated.":[72],"Here":[73],"we":[74,102],"introduce":[75],"Active":[76],"Atom":[77],"Identification":[78],"(AAI),":[79],"algorithm":[81],"measures":[83],"structural":[85,184],"evolution":[86,185],"identifies":[88],"contribute":[92],"most":[93],"diversity.":[96],"Building":[97],"this":[99],"information,":[101],"develop":[103],"IDEAL":[104,156],"(Information-Dense":[105],"Extraction":[106],"Adaptive":[108],"Learning),":[109],"which":[110],"integrates":[111],"generation,":[113],"active-learning":[114],"selection":[115],"dataset":[117],"refinement":[118,165],"into":[119],"a":[120,132],"unified":[121],"workflow":[122],"MLP":[124,193],"construction.":[125],"For":[126],"CO2":[127],"adsorption":[128],"Ag/H2O":[130],"interfaces,":[131],"model":[133],"trained":[134],"IDEAL-selected":[137],"subset":[138],"comprising":[139],"44%":[140],"of":[141,148,155],"original":[143],"dataset,":[144],"reaches":[145],"accuracy":[147],"full-dataset":[150],"model.":[151],"The":[152],"broad":[153],"applicability":[154],"further":[158],"demonstrated":[159],"in":[160,195],"two":[161],"additional":[162],"applications:":[163],"database":[164],"solid-state":[167],"electrolytes":[168],"transfer":[170],"learning":[171],"between":[172],"zeolite-supported":[173],"Rh":[174],"clusters":[175],"hydroxylated":[178],"analogues.":[179],"These":[180],"results":[181],"validate":[182],"as":[186],"effective":[188],"constructing":[191],"information-dense":[192],"datasets":[194],"complex":[196],"systems.":[198]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-29T00:00:00"}