{"id":"https://openalex.org/W7220676676","doi":"https://doi.org/10.48550/arxiv.2610.03736","title":"Efficient Analog-Initialized Latent Transport for Spatially Coherent Probabilistic Downscaling from Global to Kilometer Scales","display_name":"Efficient Analog-Initialized Latent Transport for Spatially Coherent Probabilistic Downscaling from Global to Kilometer Scales","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7220676676","doi":"https://doi.org/10.48550/arxiv.2610.03736"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.03736","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03736","pdf_url":"https://arxiv.org/pdf/2610.03736","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.03736","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028880466","display_name":"Oph\u00e9lia Miralles","orcid":"https://orcid.org/0000-0002-1142-8972","observed_orcids":["https://orcid.org/0000-0002-1142-8972"]},"institutions":[{"id":"https://openalex.org/I1314042554","display_name":"Norwegian Meteorological Institute","ror":"https://ror.org/001n36p86","country_code":"NO","type":"government","lineage":["https://openalex.org/I1314042554"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Miralles, Oph\u00e9lia","raw_affiliation_strings":["Norwegian Meteorological Institute , Oslo , Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian Meteorological Institute , Oslo , Norway","institution_ids":["https://openalex.org/I1314042554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5028880466"],"corresponding_institution_ids":["https://openalex.org/I1314042554"],"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":0.9970999956130981,"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":0.9970999956130981,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.0005000000237487257,"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"}},{"id":"https://openalex.org/T10029","display_name":"Climate variability and models","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.7570000290870667},{"id":"https://openalex.org/keywords/graph-neural-networks","display_name":"graph neural networks","score":0.7080000042915344},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"ensemble forecasting","score":0.4970000088214874},{"id":"https://openalex.org/keywords/integrated-forecasting-system","display_name":"Integrated Forecasting System","score":0.8339999914169312},{"id":"https://openalex.org/keywords/precipitation","display_name":"precipitation","score":0.3630000054836273},{"id":"https://openalex.org/keywords/covariance-matching","display_name":"covariance matching","score":0.503000020980835}],"concepts":[{"id":"https://openalex.org/C41156917","wikidata":"https://www.wikidata.org/wiki/Q682831","display_name":"Downscaling","level":3,"score":0.7771999835968018},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7537999749183655},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.569100022315979},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4494999945163727},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3824999928474426},{"id":"https://openalex.org/C150060386","wikidata":"https://www.wikidata.org/wiki/Q7574054","display_name":"Spatial correlation","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3675000071525574},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C168754636","wikidata":"https://www.wikidata.org/wiki/Q620920","display_name":"Climate model","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C123046963","wikidata":"https://www.wikidata.org/wiki/Q22664","display_name":"Geographic coordinate system","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C118365302","wikidata":"https://www.wikidata.org/wiki/Q4817115","display_name":"Atmospheric model","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.03736","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03736","pdf_url":"https://arxiv.org/pdf/2610.03736","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.2610.03736","doi":"https://doi.org/10.48550/arxiv.2610.03736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.03736","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.03736","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03736","pdf_url":"https://arxiv.org/pdf/2610.03736","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":[{"score":0.5351999998092651,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220676676.pdf","grobid_xml":"https://content.openalex.org/works/W7220676676.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2138985740","https://openalex.org/W3026449040","https://openalex.org/W4302424651","https://openalex.org/W4388654737","https://openalex.org/W4399048885","https://openalex.org/W4399401448","https://openalex.org/W4416121871","https://openalex.org/W7108219424","https://openalex.org/W7127046044","https://openalex.org/W7151247253","https://openalex.org/W7165135681","https://openalex.org/W7202124706"],"related_works":["https://openalex.org/W2613116732","https://openalex.org/W6922589923","https://openalex.org/W2101036997","https://openalex.org/W3108698805","https://openalex.org/W2074265780","https://openalex.org/W7151247253","https://openalex.org/W7009113580","https://openalex.org/W4300547559","https://openalex.org/W2118128482","https://openalex.org/W7172261914"],"abstract_inverted_index":{"Probabilistic":[0],"downscaling":[1,149],"must":[2],"represent":[3],"kilometer-scale":[4],"structure":[5],"left":[6],"unresolved":[7],"by":[8],"a":[9,26,69,77,90,130,181],"deterministic":[10,38,100],"regional":[11,23,198],"prediction.":[12],"We":[13],"introduce":[14],"an":[15],"analog-initialized":[16],"latent":[17,74,193],"transport":[18,194],"method":[19,187],"that":[20],"uses":[21],"historical":[22],"residuals":[24,49],"as":[25],"meteorologically":[27],"informed":[28],"empirical":[29,189],"source.":[30],"A":[31,61],"frozen":[32,167],"graph":[33],"neural":[34],"network":[35],"predicts":[36],"the":[37,41,59,141,148],"state":[39],"from":[40,50],"Integrated":[42],"Forecasting":[43],"System":[44],"(IFS).":[45],"For":[46],"each":[47],"input,":[48],"20":[51],"training":[52,146],"dates":[53],"with":[54,123,127,176,191],"similar":[55],"IFS":[56],"conditions":[57],"initialize":[58],"ensemble.":[60],"conditional":[62],"flow-matching":[63],"model":[64,133,150],"transports":[65],"these":[66],"fields":[67,171],"in":[68],"carefully":[70],"designed":[71],"65-factor,":[72],"100,000-node":[73],"space,":[75],"and":[76,92,112,118,134,158,180],"grid":[78,136],"decoder":[79],"reconstructs":[80],"81":[81,106],"atmospheric":[82],"channels":[83],"including":[84],"precipitation":[85],"at":[86],"2.5km":[87],"spacing.":[88],"On":[89],"season-":[91],"cycle-balanced":[93],"2025":[94],"test,":[95],"ensemble":[96],"CRPS":[97],"improves":[98],"over":[99,115,172],"mean":[101],"absolute":[102],"error":[103,121],"for":[104,195],"all":[105],"variables.":[107],"Matched":[108],"analogs":[109],"improve":[110],"point":[111],"spatial":[113],"errors":[114],"Gaussian":[116],"initialization":[117,190],"reduce":[119],"spectral":[120],"compared":[122],"covariance":[124],"matching.":[125],"Comparisons":[126],"released":[128],"CorrDiff,":[129],"local":[131,177],"CorrDiff-mini":[132],"full":[135],"EDM":[137],"provide":[138],"context":[139],"on":[140,154],"2023":[142],"validation":[143],"sample.":[144],"Total":[145],"of":[147],"takes":[151,160],"approximately":[152],"12h":[153],"one":[155],"NVIDIA":[156],"H200,":[157],"inference":[159],"about":[161],"12s":[162],"per":[163],"81-field":[164],"member.":[165],"The":[166,186],"networks":[168],"also":[169],"generate":[170],"France":[173],"when":[174],"supplied":[175],"static":[178],"data":[179],"high-resolution":[182],"IFS-derived":[183],"analog":[184],"bank.":[185],"combines":[188],"whole-domain":[192],"computationally":[196],"practical":[197],"ensembles.":[199]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-07T00:00:00"}