{"id":"https://openalex.org/W4392586563","doi":"https://doi.org/10.5194/egusphere-egu24-3540","title":"Testing the use of deep learning techniques for emulating regional reanalysis","display_name":"Testing the use of deep learning techniques for emulating regional reanalysis","publication_year":2024,"publication_date":"2024-03-08","ids":{"openalex":"https://openalex.org/W4392586563","doi":"https://doi.org/10.5194/egusphere-egu24-3540"},"language":"en","primary_location":{"id":"doi:10.5194/egusphere-egu24-3540","doi":"https://doi.org/10.5194/egusphere-egu24-3540","is_oa":true,"landing_page_url":"https://doi.org/10.5194/egusphere-egu24-3540","pdf_url":null,"source":{"id":"https://openalex.org/S4306508951","display_name":"EGU General Assembly Conference Abstracts","issn_l":null,"issn":null,"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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"conference-abstract","is_traditional":false,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.5194/egusphere-egu24-3540","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018570274","display_name":"Antonio P\u00e9rez","orcid":"https://orcid.org/0000-0002-0250-1461","observed_orcids":["https://orcid.org/0000-0002-0250-1461"]},"institutions":[{"id":"https://openalex.org/I4405283181","display_name":"Predictia Intelligent Data Solutions SL (Spain)","ror":"https://ror.org/016c5s732","country_code":"ES","type":"company","lineage":["https://openalex.org/I4405283181"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Antonio P\u00e9rez","raw_affiliation_strings":["Predictia Intelligent Data Solutions S.L. (Predictia), Santander, Spain (predictia@predictia.es)"],"raw_orcid":"https://orcid.org/0000-0002-0250-1461","affiliations":[{"raw_affiliation_string":"Predictia Intelligent Data Solutions S.L. (Predictia), Santander, Spain (predictia@predictia.es)","institution_ids":["https://openalex.org/I4405283181"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065126931","display_name":"Mario Santa Cruz","orcid":"https://orcid.org/0000-0003-4446-2648","observed_orcids":["https://orcid.org/0000-0003-4446-2648"]},"institutions":[{"id":"https://openalex.org/I4405283181","display_name":"Predictia Intelligent Data Solutions SL (Spain)","ror":"https://ror.org/016c5s732","country_code":"ES","type":"company","lineage":["https://openalex.org/I4405283181"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Mario Santa Cruz","raw_affiliation_strings":["Predictia Intelligent Data Solutions S.L. (Predictia), Santander, Spain (predictia@predictia.es)"],"raw_orcid":"https://orcid.org/0000-0003-4446-2648","affiliations":[{"raw_affiliation_string":"Predictia Intelligent Data Solutions S.L. (Predictia), Santander, Spain (predictia@predictia.es)","institution_ids":["https://openalex.org/I4405283181"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081643564","display_name":"Javier D\u00edez-Sierra","orcid":"https://orcid.org/0000-0001-9053-2542","observed_orcids":["https://orcid.org/0000-0001-9053-2542"]},"institutions":[{"id":"https://openalex.org/I13134134","display_name":"Universidad de Cantabria","ror":"https://ror.org/046ffzj20","country_code":"ES","type":"education","lineage":["https://openalex.org/I13134134"]},{"id":"https://openalex.org/I4210152024","display_name":"Instituto de F\u00edsica de Cantabria","ror":"https://ror.org/040kx1j83","country_code":"ES","type":"facility","lineage":["https://openalex.org/I13134134","https://openalex.org/I134820265","https://openalex.org/I4210152024"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Javier Diez-Sierra","raw_affiliation_strings":["Instituto de F\u00edsica de Cantabria (IFCA), CSIC-Universidad de Cantabria, Santander, Spain"],"raw_orcid":"https://orcid.org/0000-0001-9053-2542","affiliations":[{"raw_affiliation_string":"Instituto de F\u00edsica de Cantabria (IFCA), CSIC-Universidad de Cantabria, Santander, Spain","institution_ids":["https://openalex.org/I13134134","https://openalex.org/I4210152024"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067735026","display_name":"Matthew Chantry","orcid":"https://orcid.org/0000-0002-1132-0961","observed_orcids":["https://orcid.org/0000-0002-1132-0961"]},"institutions":[{"id":"https://openalex.org/I154986956","display_name":"European Centre for Medium-Range Weather Forecasts","ror":"https://ror.org/014w0fd65","country_code":"GB","type":"other","lineage":["https://openalex.org/I154986956"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Matthew Chantry","raw_affiliation_strings":["European Centre for Medium-Range Weather Forecasts (ECMWF), Reading, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-1132-0961","affiliations":[{"raw_affiliation_string":"European Centre for Medium-Range Weather Forecasts (ECMWF), Reading, United Kingdom","institution_ids":["https://openalex.org/I154986956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087576182","display_name":"\u00c1ndr\u00e1s Hor\u00e1nyi","orcid":"https://orcid.org/0000-0002-1517-6602","observed_orcids":["https://orcid.org/0000-0002-1517-6602"]},"institutions":[{"id":"https://openalex.org/I154986956","display_name":"European Centre for Medium-Range Weather Forecasts","ror":"https://ror.org/014w0fd65","country_code":"GB","type":"other","lineage":["https://openalex.org/I154986956"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andr\u00e1s Hor\u00e1nyi","raw_affiliation_strings":["European Centre for Medium-Range Weather Forecasts (ECMWF), Reading, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Centre for Medium-Range Weather Forecasts (ECMWF), Reading, United Kingdom","institution_ids":["https://openalex.org/I154986956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035503968","display_name":"Mariana Clare","orcid":"https://orcid.org/0000-0002-5010-0363","observed_orcids":["https://orcid.org/0000-0002-5010-0363"]},"institutions":[{"id":"https://openalex.org/I154986956","display_name":"European Centre for Medium-Range Weather Forecasts","ror":"https://ror.org/014w0fd65","country_code":"GB","type":"other","lineage":["https://openalex.org/I154986956"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mariana Clare","raw_affiliation_strings":["European Centre for Medium-Range Weather Forecasts (ECMWF), Reading, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-5010-0363","affiliations":[{"raw_affiliation_string":"European Centre for Medium-Range Weather Forecasts (ECMWF), Reading, United Kingdom","institution_ids":["https://openalex.org/I154986956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060475316","display_name":"Cornel Soci","orcid":"https://orcid.org/0009-0008-9692-748X","observed_orcids":["https://orcid.org/0009-0008-9692-748X"]},"institutions":[{"id":"https://openalex.org/I154986956","display_name":"European Centre for Medium-Range Weather Forecasts","ror":"https://ror.org/014w0fd65","country_code":"GB","type":"other","lineage":["https://openalex.org/I154986956"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cornel Soci","raw_affiliation_strings":["European Centre for Medium-Range Weather Forecasts (ECMWF), Reading, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Centre for Medium-Range Weather Forecasts (ECMWF), Reading, United Kingdom","institution_ids":["https://openalex.org/I154986956"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018570274","https://openalex.org/A5035503968","https://openalex.org/A5065126931","https://openalex.org/A5067735026","https://openalex.org/A5081643564"],"corresponding_institution_ids":["https://openalex.org/I13134134","https://openalex.org/I154986956","https://openalex.org/I4210152024","https://openalex.org/I4405283181"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.9150000214576721,"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":0.9150000214576721,"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/T10029","display_name":"Climate variability and models","score":0.03020000085234642,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.015599999576807022,"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/era5-reanalysis","display_name":"ERA5 reanalysis","score":0.652999997138977},{"id":"https://openalex.org/keywords/2-m-air-temperature","display_name":"2 m air temperature","score":0.781000018119812},{"id":"https://openalex.org/keywords/spatial-downscaling","display_name":"spatial downscaling","score":0.6850000023841858},{"id":"https://openalex.org/keywords/super-resolution-reconstruction","display_name":"super-resolution reconstruction","score":0.4390000104904175},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.699999988079071},{"id":"https://openalex.org/keywords/iberian-peninsula","display_name":"Iberian Peninsula","score":0.8640000224113464},{"id":"https://openalex.org/keywords/bicubic-interpolation-comparison","display_name":"bicubic interpolation comparison","score":0.7699999809265137}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5128410458564758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4999523162841797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4761916697025299}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5194/egusphere-egu24-3540","doi":"https://doi.org/10.5194/egusphere-egu24-3540","is_oa":true,"landing_page_url":"https://doi.org/10.5194/egusphere-egu24-3540","pdf_url":null,"source":{"id":"https://openalex.org/S4306508951","display_name":"EGU General Assembly Conference Abstracts","issn_l":null,"issn":null,"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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.5194/egusphere-egu24-3540","doi":"https://doi.org/10.5194/egusphere-egu24-3540","is_oa":true,"landing_page_url":"https://doi.org/10.5194/egusphere-egu24-3540","pdf_url":null,"source":{"id":"https://openalex.org/S4306508951","display_name":"EGU General Assembly Conference Abstracts","issn_l":null,"issn":null,"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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.685699999332428}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7027668299","https://openalex.org/W7135233927","https://openalex.org/W7135167469","https://openalex.org/W4402782550","https://openalex.org/W4392615972","https://openalex.org/W7162446613","https://openalex.org/W7204630846","https://openalex.org/W4410331688","https://openalex.org/W4409919993","https://openalex.org/W7135419844"],"abstract_inverted_index":{"Reanalysis":[0],"datasets":[1],"serve":[2],"as":[3,74,141,165,369,399],"essential":[4],"components":[5],"for":[6,23,41,65,88,479],"contemporary":[7],"climate":[8,20,33],"monitoring,":[9],"integrating":[10,286],"historical":[11],"weather":[12],"observations":[13,469],"with":[14,200,274,438],"predictive":[15],"models":[16],"to":[17,114,118,133,146,170,185,211,227,290,303,316,349,385,459,472],"create":[18,112],"extensive":[19],"data":[21,110,437],"records":[22],"the":[24,38,47,91,104,148,166,174,183,187,201,206,223,228,239,245,250,270,311,322,350,370,379,408,429,460,481],"last":[25],"decades.":[26],"The":[27,233,255],"fifth":[28],"generation":[29],"ECMWF":[30],"atmospheric":[31],"global":[32],"reanalysis":[34,436],"(ERA5)":[35,210],"dataset":[36,313],"from":[37,208,301,383],"European":[39,93,252],"Centre":[40],"Medium-Range":[42],"Weather":[43],"Forecasts":[44],"(ECMWF)":[45],"represents":[46],"latest":[48],"update,":[49],"providing":[50],"a":[51,126,192,217,275,283,287,325,337,375],"broad":[52],"temporal":[53],"scope":[54],"and":[55,77,103,154,305,336,403,446,470,475,484],"improved":[56],"spatial":[57],"granularity.":[58],"However,":[59],"its":[60,99,159,306,420],"resolution":[61,188],"may":[62],"fall":[63],"short":[64],"detailed":[66,85],"local-scale":[67],"analysis":[68],"required":[69],"in":[70,331,341,356,361,378,395,412,422,434,442],"critical":[71],"sectors":[72],"such":[73,368,398],"agriculture,":[75],"energy,":[76],"disaster":[78],"response,":[79],"among":[80],"others.":[81],"Even":[82],"though":[83],"more":[84],"regional":[86],"information":[87],"Europe":[89],"like":[90],"Copernicus":[92],"Regional":[94],"ReAnalysis":[95],"(CERRA)":[96],"do":[97],"exist,":[98],"high":[100],"computational":[101,444],"costs":[102],"lack":[105],"of":[106,123,150,189,194,204,242,244,249,278,298,314,321],"very":[107],"near":[108,447],"real-time":[109,448],"updates":[111],"limitations":[113],"conducting":[115],"analyses":[116],"close":[117],"real":[119],"time.To":[120],"solve":[121],"some":[122],"these":[124],"limitations,":[125],"deep":[127],"learning":[128,276],"model":[129,172,234,323],"has":[130,180],"been":[131,393],"developed":[132],"mirror":[134],"CERRA's":[135],"2m":[136],"temperature":[137],"field":[138],"utilising":[139],"ERA5":[140],"input.":[142],"This":[143,196,354],"approach":[144],"aims":[145],"replicate":[147],"details":[149],"CERRA,":[151],"ensuring":[152],"rapid":[153],"efficient":[155],"emulation":[156],"without":[157],"surpassing":[158],"original":[160],"quality,":[161],"i.e.":[162],"treating":[163],"CERRA":[164,253,466],"ground":[167],"truth.":[168],"Central":[169],"this":[171],"is":[173,236,308,358],"Swin2SRModel":[175],"component":[176],"(Swin":[177],"v2),":[178],"which":[179],"effectively":[181],"demonstrated":[182,374],"ability":[184,421],"downscale":[186],"inputs":[190],"by":[191],"factor":[193],"8.":[195],"capability":[197],"aligns":[198],"well":[199],"intended":[202],"task":[203],"downscaling":[205],"grid":[207],"0.25\u00ba":[209],"0.05\u00ba":[212],"(CERRA).":[213],"To":[214],"achieve":[215],"this,":[216],"Convolutional":[218],"Neural":[219],"Network":[220],"(CNN)":[221],"pre-processes":[222],"data,":[224,299],"reshaping":[225],"it":[226],"necessary":[229],"feature":[230],"map":[231],"size.":[232],"training":[235,292],"focused":[237],"on":[238,365],"specific":[240,366],"region":[241],"interest":[243],"Iberian":[246],"Peninsula,":[247],"instead":[248],"entire":[251],"domain.":[254],"training,":[256],"lasting":[257],"100":[258],"epochs,":[259],"takes":[260],"approximately":[261],"3.6":[262],"days":[263],"using":[264,467],"small":[265],"batch":[266],"processing.":[267],"It":[268,294],"employs":[269],"Adam":[271],"optimizer,":[272],"starting":[273],"rate":[277],"0.0001":[279],"that":[280,424],"decreases":[281],"following":[282],"cosine":[284],"curve,":[285],"warm-up":[288],"phase":[289],"mitigate":[291],"instability.":[293],"utilises":[295],"32":[296],"years":[297],"spanning":[300],"1985":[302],"2016,":[304],"performance":[307,411],"validated":[309],"against":[310,465],"independent":[312,468],"2017":[315],"2021.A":[317],"comprehensive":[318,463],"post-training":[319],"evaluation":[320],"shows":[324,431],"marked":[326],"improvement":[327],"\u2013":[328,347,387],"35%":[329],"reduction":[330],"Mean":[332,343],"Absolute":[333],"Error":[334,345],"(MAE)":[335],"nearly":[338],"30%":[339],"enhancement":[340],"Root":[342],"Square":[344],"(RMSE)":[346],"compared":[348,458],"bicubic":[351,461],"interpolation":[352],"method.":[353],"leap":[355],"accuracy":[357],"especially":[359],"notable":[360],"complex":[362],"landscapes.":[363],"Validation":[364],"locations,":[367],"Aneto":[371],"mountain,":[372],"have":[373,392],"dramatic":[376],"refinement":[377],"mean":[380],"error,":[381],"dropping":[382],"-6.3\u00b0C":[384],"0.06\u00b0C":[386],"99%":[388],"improvement.":[389],"Similar":[390],"improvements":[391],"observed":[394],"Cantabrian":[396],"Mountains":[397],"Pe\u00f1a":[400,404],"Vieja":[401],"(94%)":[402],"Labra":[405],"(88%),":[406],"illustrating":[407],"model's":[409],"superior":[410],"areas":[413,423],"where":[414],"previous":[415],"errors":[416,457],"were":[417],"substantial,":[418],"highlighting":[419],"most":[425],"require":[426],"it.In":[427],"conclusion,":[428],"project":[430],"promising":[432],"results":[433,452],"enhancing":[435],"AI,":[439],"demonstrating":[440],"potential":[441],"both":[443],"efficiency":[445],"application.":[449],"While":[450],"initial":[451],"are":[453],"encouraging,":[454],"indicating":[455],"reduced":[456],"interpolation,":[462],"validation":[464],"expansion":[471],"broader":[473],"domains":[474],"variables":[476],"remain":[477],"crucial":[478],"confirming":[480],"method's":[482],"effectiveness":[483],"reliability.":[485]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2024-03-09T00:00:00"}