{"id":"https://openalex.org/W4415330503","doi":"https://doi.org/10.48550/arxiv.2508.13313","title":"Flow Matching for Efficient and Scalable Data Assimilation","display_name":"Flow Matching for Efficient and Scalable Data Assimilation","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4415330503","doi":"https://doi.org/10.48550/arxiv.2508.13313"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.13313","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.13313","pdf_url":"https://arxiv.org/pdf/2508.13313","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.13313","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120055949","display_name":"Taos Transue","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Transue, Taos","raw_affiliation_strings":["The Computing and Mathematical Sciences Department , California Institute of Technology , 1200 E California Blvd , Pasadena , CA 91125 "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Computing and Mathematical Sciences Department , California Institute of Technology , 1200 E California Blvd , Pasadena , CA 91125 ","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Bohan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Bohan","raw_affiliation_strings":["The Computing and Mathematical Sciences Department , California Institute of Technology , 1200 E California Blvd , Pasadena , CA 91125 "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Computing and Mathematical Sciences Department , California Institute of Technology , 1200 E California Blvd , Pasadena , CA 91125 ","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037142295","display_name":"So Takao","orcid":"https://orcid.org/0009-0003-4277-9817","observed_orcids":["https://orcid.org/0009-0003-4277-9817"]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takao, So","raw_affiliation_strings":["The Computing and Mathematical Sciences Department , California Institute of Technology , 1200 E California Blvd , Pasadena , CA 91125 "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Computing and Mathematical Sciences Department , California Institute of Technology , 1200 E California Blvd , Pasadena , CA 91125 ","institution_ids":["https://openalex.org/I122411786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010480505","display_name":"Baoshan Wang","orcid":"https://orcid.org/0000-0001-7203-9703","observed_orcids":["https://orcid.org/0000-0001-7203-9703"]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Bao","raw_affiliation_strings":["The Computing and Mathematical Sciences Department , California Institute of Technology , 1200 E California Blvd , Pasadena , CA 91125 "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Computing and Mathematical Sciences Department , California Institute of Technology , 1200 E California Blvd , Pasadena , CA 91125 ","institution_ids":["https://openalex.org/I122411786"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I122411786"],"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/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.5199999809265137,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.5199999809265137,"subfield":{"id":"https://openalex.org/subfields/1902","display_name":"Atmospheric Science"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.1941000074148178,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.09839999675750732,"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/data-assimilation","display_name":"data assimilation","score":0.9750000238418579},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.9990000128746033},{"id":"https://openalex.org/keywords/bayesian-data-assimilation","display_name":"Bayesian data assimilation","score":0.5770000219345093},{"id":"https://openalex.org/keywords/bootstrap-particle-filter","display_name":"bootstrap particle filter","score":0.6460000276565552},{"id":"https://openalex.org/keywords/ensemble-kalman-filter","display_name":"ensemble Kalman filter","score":0.9990000128746033},{"id":"https://openalex.org/keywords/observation-assimilation","display_name":"observation assimilation","score":0.6159999966621399}],"concepts":[{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.7369999885559082},{"id":"https://openalex.org/C24552861","wikidata":"https://www.wikidata.org/wiki/Q2670177","display_name":"Data assimilation","level":2,"score":0.7350999712944031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.647599995136261},{"id":"https://openalex.org/C79334102","wikidata":"https://www.wikidata.org/wiki/Q3072268","display_name":"Ensemble Kalman filter","level":4,"score":0.621999979019165},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6010000109672546},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5259000062942505},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4832000136375427},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.45570001006126404},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C206833254","wikidata":"https://www.wikidata.org/wiki/Q5421817","display_name":"Extended Kalman filter","level":3,"score":0.3855000138282776},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.37279999256134033},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35749998688697815},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C2985957023","wikidata":"https://www.wikidata.org/wiki/Q17105191","display_name":"Particle flow","level":3,"score":0.32690000534057617},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.27230000495910645},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.13313","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.13313","pdf_url":"https://arxiv.org/pdf/2508.13313","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2508.13313","doi":"https://doi.org/10.48550/arxiv.2508.13313","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.13313","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.13313","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2508.13313","pdf_url":"https://arxiv.org/pdf/2508.13313","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1112615069","display_name":"Collaborative Research: Algorithms, Theory, and Validation of Deep Graph Learning with Limited Supervision: A Continuous Perspective","funder_award_id":"2208361","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5529346708","display_name":"Collaborative Research: MATH-DT: Mathematical Foundations of AI-assisted Digital Twins for High Power Laser Science and Engineering","funder_award_id":"2436344","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8112523353","display_name":null,"funder_award_id":"DE-SC0025801","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8442957167","display_name":"RELIABLE, SCALABLE, AND DATA-EFFICIENT RANDOMIZED GRAPH NEURAL NETWORKS FOR NEURAL COMBINATORIAL OPTIMIZATION WITH SCIENTIFIC APPLICATIONS","funder_award_id":"DESC0023490","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8969488128","display_name":"Collaborative Research: ATD: Fast Algorithms and Novel Continuous-depth Graph Neural Networks for Threat Detection","funder_award_id":"2219956","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"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415330503.pdf","grobid_xml":"https://content.openalex.org/works/W4415330503.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Data":[0],"assimilation":[1],"(DA)":[2],"estimates":[3],"a":[4,37,69],"dynamical":[5],"system's":[6],"state":[7],"from":[8],"noisy":[9],"observations.":[10],"Recent":[11],"generative":[12],"models":[13],"like":[14],"the":[15,32,58,75,85],"ensemble":[16,33,90],"score":[17],"filter":[18,35,88],"(EnSF)":[19],"improve":[20],"DA":[21,77],"in":[22,49],"high-dimensional":[23,95],"nonlinear":[24],"settings":[25],"but":[26],"are":[27],"computationally":[28],"expensive.":[29],"We":[30],"introduce":[31],"flow":[34,39,50,60,71],"(EnFF),":[36],"training-free,":[38],"matching":[40],"(FM)-based":[41],"framework":[42],"that":[43,73],"accelerates":[44],"sampling":[45],"and":[46,67,89,102],"offers":[47],"flexibility":[48],"design.":[51],"EnFF":[52],"uses":[53],"Monte":[54],"Carlo":[55],"estimators":[56],"for":[57,64,107],"marginal":[59],"field,":[61],"localized":[62],"guidance":[63],"observation":[65],"assimilation,":[66],"utilizes":[68],"novel":[70],"path":[72],"exploits":[74],"Bayesian":[76],"formulation.":[78],"It":[79],"generalizes":[80],"classical":[81],"filters":[82],"such":[83],"as":[84],"bootstrap":[86],"particle":[87],"Kalman":[91],"filter.":[92],"Experiments":[93],"on":[94],"benchmarks":[96],"demonstrate":[97],"EnFF's":[98],"improved":[99],"cost-accuracy":[100],"tradeoffs":[101],"scalability,":[103],"highlighting":[104],"FM's":[105],"potential":[106],"efficient,":[108],"scalable":[109],"DA.":[110],"Code":[111],"is":[112],"available":[113],"at":[114],"https://github.com/Utah-Math-Data-Science/Data-Assimilation-Flow-Matching.":[115]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-19T00:00:00"}