{"id":"https://openalex.org/W7141399549","doi":"https://doi.org/10.48550/arxiv.2603.25687","title":"On Neural Scaling Laws for Weather Emulation through Continual Training","display_name":"On Neural Scaling Laws for Weather Emulation through Continual Training","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141399549","doi":"https://doi.org/10.48550/arxiv.2603.25687"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.25687","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25687","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.25687","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130788011","display_name":"Shashank Subramanian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Subramanian, Shashank","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130796790","display_name":"Alexander Kiefer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiefer, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065416310","display_name":"Arnur Nigmetov","orcid":"https://orcid.org/0000-0003-4823-5311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nigmetov, Arnur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130723017","display_name":"Amir Gholami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gholami, Amir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060468015","display_name":"Dmitriy Morozov","orcid":"https://orcid.org/0000-0002-4330-6670"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morozov, Dmitriy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130795961","display_name":"Michael W. Mahoney","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahoney, Michael W.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"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/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.093299999833107,"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":0.093299999833107,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.08969999849796295,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.07199999690055847,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6478999853134155},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6399000287055969},{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.6093000173568726},{"id":"https://openalex.org/keywords/trigonometric-functions","display_name":"Trigonometric functions","score":0.3587000072002411},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3549000024795532},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3456000089645386},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.34529998898506165},{"id":"https://openalex.org/keywords/scaling-law","display_name":"Scaling law","score":0.34139999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7057999968528748},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6478999853134155},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6399000287055969},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.6093000173568726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5382999777793884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4447000026702881},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.34139999747276306},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3353999853134155},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2849000096321106},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.25687","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25687","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":"doi:10.48550/arxiv.2603.25687","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.25687","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"scaling":[1,41,54,100,176],"laws,":[2],"which":[3],"in":[4,31,42,56,94],"some":[5],"domains":[6],"can":[7,112,177],"predict":[8],"the":[9,25],"performance":[10,171],"of":[11,18,27,144],"large":[12],"neural":[13,40,175],"networks":[14],"as":[15,57,61,84,128,130,179],"a":[16,59,65,141],"function":[17],"model,":[19],"data,":[20],"and":[21,35,72,81,102,146,157],"compute":[22,151],"scale,":[23],"are":[24],"cornerstone":[26],"building":[28],"foundation":[29],"models":[30,48,92],"Natural":[32],"Language":[33],"Processing":[34],"Computer":[36],"Vision.":[37],"We":[38,89,137,187],"study":[39],"Scientific":[43],"Machine":[44],"Learning,":[45],"focusing":[46],"on":[47],"for":[49,183,191],"weather":[50],"forecasting.":[51],"To":[52],"analyze":[53],"behavior":[55],"simple":[58],"setting":[60],"possible,":[62],"we":[63,73,158],"adopt":[64],"minimal,":[66],"scalable,":[67],"general-purpose":[68],"Swin":[69],"Transformer":[70],"architecture,":[71],"use":[74],"continual":[75],"training":[76,87,161],"with":[77],"constant":[78],"learning":[79,107],"rates":[80],"periodic":[82],"cooldowns":[83],"an":[85,180],"efficient":[86,184],"strategy.":[88],"show":[90],"that":[91,174],"trained":[93],"this":[95],"minimalist":[96],"way":[97],"follow":[98],"predictable":[99],"trends":[101,165],"even":[103],"outperform":[104],"standard":[105],"cosine":[106],"rate":[108],"schedules.":[109],"Cooldown":[110],"phases":[111],"be":[113],"re-purposed":[114],"to":[115,153,166],"improve":[116],"downstream":[117],"performance,":[118],"e.g.,":[119],"enabling":[120],"accurate":[121],"multi-step":[122],"rollouts":[123],"over":[124],"longer":[125],"forecast":[126],"horizons":[127],"well":[129],"sharper":[131],"predictions":[132],"through":[133],"spectral":[134],"loss":[135],"adjustments.":[136],"also":[138],"systematically":[139],"explore":[140],"wide":[142],"range":[143],"model":[145],"dataset":[147],"sizes":[148],"under":[149],"various":[150],"budgets":[152],"construct":[154],"IsoFLOP":[155],"curves,":[156],"identify":[159],"compute-optimal":[160],"regimes.":[162],"Extrapolating":[163],"these":[164],"larger":[167],"scales":[168],"highlights":[169],"potential":[170],"limits,":[172],"demonstrating":[173],"serve":[178],"important":[181],"diagnostic":[182],"resource":[185],"allocation.":[186],"open-source":[188],"our":[189],"code":[190],"reproducibility.":[192]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-28T00:00:00"}