{"id":"https://openalex.org/W4414943781","doi":"https://doi.org/10.48550/arxiv.2507.10893","title":"Modernizing CNN-based Weather Forecast Model towards Higher Computational Efficiency","display_name":"Modernizing CNN-based Weather Forecast Model towards Higher Computational Efficiency","publication_year":2025,"publication_date":"2025-07-15","ids":{"openalex":"https://openalex.org/W4414943781","doi":"https://doi.org/10.48550/arxiv.2507.10893"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.10893","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10893","pdf_url":"https://arxiv.org/pdf/2507.10893","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.10893","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093931950","display_name":"Minjong Cheon","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cheon, Minjong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119896777","display_name":"Eunhan Goo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goo, Eunhan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101630995","display_name":"SeongHan Shin","orcid":"https://orcid.org/0000-0002-2827-7402"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shin, Su-Hyeon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101596149","display_name":"Muhammad Ahmed","orcid":"https://orcid.org/0000-0001-9026-9502"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed, Muhammad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090355006","display_name":"Hyungjun Kim","orcid":"https://orcid.org/0000-0003-1083-8416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Hyungjun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5093931950"],"corresponding_institution_ids":[],"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.6945000290870667,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.6945000290870667,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/numerical-weather-prediction","display_name":"Numerical weather prediction","score":0.6517999768257141},{"id":"https://openalex.org/keywords/global-forecast-system","display_name":"Global Forecast System","score":0.628000020980835},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6166999936103821},{"id":"https://openalex.org/keywords/tropical-cyclone-forecast-model","display_name":"Tropical cyclone forecast model","score":0.516700029373169},{"id":"https://openalex.org/keywords/milestone","display_name":"Milestone","score":0.5029000043869019},{"id":"https://openalex.org/keywords/weather-prediction","display_name":"Weather prediction","score":0.4846000075340271},{"id":"https://openalex.org/keywords/weather-forecasting","display_name":"Weather forecasting","score":0.42410001158714294},{"id":"https://openalex.org/keywords/extreme-weather","display_name":"Extreme weather","score":0.3971000015735626}],"concepts":[{"id":"https://openalex.org/C147947694","wikidata":"https://www.wikidata.org/wiki/Q837552","display_name":"Numerical weather prediction","level":2,"score":0.6517999768257141},{"id":"https://openalex.org/C163109420","wikidata":"https://www.wikidata.org/wiki/Q287011","display_name":"Global Forecast System","level":3,"score":0.628000020980835},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6166999936103821},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.536300003528595},{"id":"https://openalex.org/C102561126","wikidata":"https://www.wikidata.org/wiki/Q17164865","display_name":"Tropical cyclone forecast model","level":3,"score":0.516700029373169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5037999749183655},{"id":"https://openalex.org/C120060458","wikidata":"https://www.wikidata.org/wiki/Q10145","display_name":"Milestone","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C2987469573","wikidata":"https://www.wikidata.org/wiki/Q182868","display_name":"Weather prediction","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C21001229","wikidata":"https://www.wikidata.org/wiki/Q182868","display_name":"Weather forecasting","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C205537798","wikidata":"https://www.wikidata.org/wiki/Q1277161","display_name":"Extreme weather","level":3,"score":0.3971000015735626},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.3885999917984009},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C118365302","wikidata":"https://www.wikidata.org/wiki/Q4817115","display_name":"Atmospheric model","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C188052254","wikidata":"https://www.wikidata.org/wiki/Q1516983","display_name":"MM5","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C170061395","wikidata":"https://www.wikidata.org/wiki/Q5468164","display_name":"Forecast skill","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C49204034","wikidata":"https://www.wikidata.org/wiki/Q52139","display_name":"Climatology","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C37505551","wikidata":"https://www.wikidata.org/wiki/Q1453537","display_name":"Model output statistics","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.10893","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10893","pdf_url":"https://arxiv.org/pdf/2507.10893","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2507.10893","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.10893","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.10893","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10893","pdf_url":"https://arxiv.org/pdf/2507.10893","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"AI-based":[1],"weather":[2,26,61,155],"forecast":[3],"models":[4,10,152],"have":[5,11],"achieved":[6],"impressive":[7],"advances.":[8],"These":[9],"reached":[12],"accuracy":[13,66],"levels":[14],"comparable":[15],"to":[16,37,45,105],"traditional":[17],"NWP":[18],"systems,":[19],"marking":[20],"a":[21,55,74,94,101,137,159],"significant":[22],"milestone":[23],"in":[24,132,153,181],"data-driven":[25],"prediction.":[27],"However,":[28],"they":[29],"mostly":[30],"leverage":[31],"Transformer-based":[32],"architectures,":[33],"which":[34],"often":[35],"leads":[36],"high":[38],"training":[39,131],"complexity":[40],"and":[41,97,129,171],"resource":[42],"demands":[43],"due":[44],"the":[46,106,114,122,148,167,172],"massive":[47],"parameter":[48],"sizes.":[49],"In":[50],"this":[51],"study,":[52],"we":[53,78],"introduce":[54],"modernized":[56],"CNN-based":[57,90],"model":[58,123],"for":[59],"global":[60],"forecasting":[62],"that":[63,145],"delivers":[64],"competitive":[65],"while":[67,157],"significantly":[68,160],"reducing":[69],"computational":[70],"requirements.":[71],"To":[72],"present":[73],"systematic":[75],"modernization":[76],"roadmap,":[77],"highlight":[79],"key":[80],"architectural":[81],"enhancements":[82],"across":[83],"multiple":[84],"design":[85],"scales":[86],"from":[87],"an":[88],"earlier":[89],"approach.":[91],"KAI-a":[92,146],"incorporates":[93],"scale-invariant":[95],"architecture":[96],"InceptionNeXt-based":[98],"blocks":[99],"within":[100],"geophysically-aware":[102],"design,":[103],"tailored":[104],"structure":[107],"of":[108,150],"Earth":[109],"system":[110],"data.":[111],"Trained":[112],"on":[113,136,166],"ERA5":[115],"daily":[116],"dataset":[117],"with":[118],"67":[119],"atmospheric":[120],"variables,":[121],"contains":[124],"about":[125],"7":[126],"million":[127],"parameters":[128],"completes":[130],"just":[133],"12":[134],"hours":[135],"single":[138],"NVIDIA":[139],"L40s":[140],"GPU.":[141],"Our":[142],"evaluation":[143],"shows":[144],"matches":[147],"performance":[149],"state-of-the-art":[151],"medium-range":[154],"forecasting,":[156],"offering":[158],"lightweight":[161],"design.":[162],"Furthermore,":[163],"case":[164],"studies":[165],"2018":[168],"European":[169],"heatwave":[170],"East":[173],"Asian":[174],"summer":[175],"monsoon":[176],"demonstrate":[177],"KAI-a's":[178],"robust":[179],"skill":[180],"capturing":[182],"extreme":[183],"events,":[184],"reinforcing":[185],"its":[186],"practical":[187],"utility.":[188]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}