{"id":"https://openalex.org/W4412876817","doi":"https://doi.org/10.1145/3711896.3737178","title":"Utilizing Strategic Pre-training to Reduce Overfitting: Baguan - A Pre-trained Weather Forecasting Model","display_name":"Utilizing Strategic Pre-training to Reduce Overfitting: Baguan - A Pre-trained Weather Forecasting Model","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412876817","doi":"https://doi.org/10.1145/3711896.3737178"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737178","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737178","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737178","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737178","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069211368","display_name":"Peisong Niu","orcid":"https://orcid.org/0009-0007-7023-0900"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peisong Niu","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-7023-0900","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035357260","display_name":"Ziqing Ma","orcid":"https://orcid.org/0000-0003-1567-5054"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqing Ma","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1567-5054","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101890076","display_name":"Tian Zhou","orcid":"https://orcid.org/0000-0003-1789-5413"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","KY"],"is_corresponding":false,"raw_author_name":"Tian Zhou","raw_affiliation_strings":["DAMO Academy, Alibaba Group, hang zhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1789-5413","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, hang zhou, China","institution_ids":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100646104","display_name":"Weiqi Chen","orcid":"https://orcid.org/0009-0007-9246-9402"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqi Chen","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-9246-9402","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101363686","display_name":"Lefei Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lefei Shen","raw_affiliation_strings":["Computer Science and Technology, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-9203-9086","affiliations":[{"raw_affiliation_string":"Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069394608","display_name":"Rong Jin","orcid":"https://orcid.org/0000-0002-8797-4646"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","KY"],"is_corresponding":false,"raw_author_name":"Rong Jin","raw_affiliation_strings":["DAMO Academy, Alibaba Group, HangZhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8797-4646","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, HangZhou, China","institution_ids":["https://openalex.org/I45928872","https://openalex.org/I4210086143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054846625","display_name":"Liang Sun","orcid":"https://orcid.org/0009-0002-5835-7259"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Sun","raw_affiliation_strings":["DAMO Academy, Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-5835-7259","affiliations":[{"raw_affiliation_string":"DAMO Academy, Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15782506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2186","last_page":"2197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10029","display_name":"Climate variability and models","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10029","display_name":"Climate variability and models","score":0.9997000098228455,"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/T11186","display_name":"Hydrology and Drought Analysis","score":0.9979000091552734,"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/T10930","display_name":"Flood Risk Assessment and Management","score":0.9932000041007996,"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/overfitting","display_name":"Overfitting","score":0.9546090364456177},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.8096024990081787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6575030088424683},{"id":"https://openalex.org/keywords/weather-forecasting","display_name":"Weather forecasting","score":0.6563498973846436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5560243129730225},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4869774281978607},{"id":"https://openalex.org/keywords/meteorology","display_name":"Meteorology","score":0.21652832627296448},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16483089327812195},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05830523371696472}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9546090364456177},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.8096024990081787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6575030088424683},{"id":"https://openalex.org/C21001229","wikidata":"https://www.wikidata.org/wiki/Q182868","display_name":"Weather forecasting","level":2,"score":0.6563498973846436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5560243129730225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4869774281978607},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.21652832627296448},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16483089327812195},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05830523371696472}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737178","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737178","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737178","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737178","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737178","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737178","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.8600000143051147}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412876817.pdf","grobid_xml":"https://content.openalex.org/works/W4412876817.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2806365088","https://openalex.org/W3025949386","https://openalex.org/W4214550829","https://openalex.org/W4313156423","https://openalex.org/W4378509424","https://openalex.org/W4382048606","https://openalex.org/W4387156810","https://openalex.org/W4388654737","https://openalex.org/W4388728292","https://openalex.org/W4389500830","https://openalex.org/W4403621800","https://openalex.org/W6600574797","https://openalex.org/W6606298547","https://openalex.org/W6852918553"],"related_works":["https://openalex.org/W4410497501","https://openalex.org/W2989932438","https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W2186333919","https://openalex.org/W4387297750","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264"],"abstract_inverted_index":{"Weather":[0],"forecasting":[1,24,61],"has":[2],"long":[3],"posed":[4],"a":[5,28,42,102,112,117],"significant":[6],"challenge":[7,68],"for":[8,79,106,122],"humanity.":[9],"While":[10],"recent":[11],"AI-based":[12],"models":[13],"have":[14],"surpassed":[15],"traditional":[16,132],"numerical":[17],"weather":[18,38,60,80,108],"prediction":[19],"(NWP)":[20],"methods":[21,78],"in":[22,116,148],"global":[23],"tasks,":[25,150],"overfitting":[26,95,144],"remains":[27],"critical":[29],"issue":[30],"due":[31],"to":[32,65],"the":[33,139],"limited":[34],"availability":[35],"of":[36],"real-world":[37],"data":[39,55],"spanning":[40],"only":[41],"few":[43],"decades.":[44],"Unlike":[45],"fields":[46],"like":[47],"computer":[48],"vision":[49],"or":[50],"natural":[51],"language":[52],"processing,":[53],"where":[54],"abundance":[56],"can":[57],"mitigate":[58],"overfitting,":[59],"demands":[62],"innovative":[63],"strategies":[64],"address":[66],"this":[67,73],"with":[69],"existing":[70],"data.":[71],"In":[72],"paper,":[74],"we":[75],"explore":[76],"pre-training":[77,88],"forecasting,":[81,109,158],"finding":[82],"that":[83,129],"selecting":[84],"an":[85],"appropriately":[86],"challenging":[87],"task":[89],"introduces":[90],"locality":[91],"bias,":[92],"effectively":[93],"mitigating":[94],"and":[96,120,146,156],"enhancing":[97],"performance.":[98],"We":[99],"introduce":[100],"Baguan,":[101],"novel":[103],"data-driven":[104],"model":[105],"medium-range":[107],"built":[110],"on":[111],"Siamese":[113],"Autoencoder":[114],"pre-trained":[115,140],"self-supervised":[118],"manner":[119],"fine-tuned":[121],"different":[123],"lead":[124],"times.":[125],"Experimental":[126],"results":[127],"show":[128],"Baguan":[130,141],"outperforms":[131],"methods,":[133],"delivering":[134],"more":[135],"accurate":[136],"forecasts.":[137],"Additionally,":[138],"demonstrates":[142],"robust":[143],"control":[145],"excels":[147],"downstream":[149],"such":[151],"as":[152],"subseasonal-to-seasonal":[153],"(S2S)":[154],"modeling":[155],"regional":[157],"after":[159],"fine-tuning.":[160]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}