{"id":"https://openalex.org/W7162801820","doi":"https://doi.org/10.48550/arxiv.2605.29952","title":"From Short Histories to Long Futures: Horizon-Aware Graph Neural Networks for Long Horizon Forecasting","display_name":"From Short Histories to Long Futures: Horizon-Aware Graph Neural Networks for Long Horizon Forecasting","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162801820","doi":"https://doi.org/10.48550/arxiv.2605.29952"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29952","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29952","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.2605.29952","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084078740","display_name":"Zesheng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zesheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010792548","display_name":"Maryam Rahnemoonfar","orcid":"https://orcid.org/0000-0001-9358-2836"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahnemoonfar, Maryam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"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/T10644","display_name":"Cryospheric studies and observations","score":0.37139999866485596,"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/T10644","display_name":"Cryospheric studies and observations","score":0.37139999866485596,"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/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.1891999989748001,"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/T11459","display_name":"Arctic and Antarctic ice dynamics","score":0.0803999975323677,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7067000269889832},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5914999842643738},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5763000249862671},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5623999834060669},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.444599986076355},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.42969998717308044},{"id":"https://openalex.org/keywords/current","display_name":"Current (fluid)","score":0.41690000891685486},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3474000096321106}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7067000269889832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6057999730110168},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5914999842643738},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5763000249862671},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5623999834060669},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.444599986076355},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38589999079704285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3806999921798706},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3122999966144562},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3003000020980835},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C172025690","wikidata":"https://www.wikidata.org/wiki/Q5332763","display_name":"Echo state network","level":4,"score":0.28380000591278076},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C135796866","wikidata":"https://www.wikidata.org/wiki/Q7315328","display_name":"Reservoir computing","level":4,"score":0.26010000705718994},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29952","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29952","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.2605.29952","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29952","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":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.6576805114746094}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"long-range":[1,217],"prediction":[2,50],"of":[3,17,123],"geophysical":[4,104],"systems":[5],"is":[6,91],"difficult":[7],"due":[8],"to":[9,79,99,156,165,197],"strongly":[10],"nonlinear":[11],"dynamics,":[12],"the":[13,21,58,113,117,120,150,157,235],"high":[14],"computational":[15],"cost":[16],"full-physics":[18],"simulations,":[19],"and":[20,51,106,128,180,191,200,219,238,253],"error":[22],"accumulation":[23],"that":[24,70,186,212,228],"arise":[25],"when":[26],"one-step":[27],"autoregressive":[28,243],"surrogates":[29],"are":[30,45,161],"rolled":[31],"out":[32],"over":[33],"decades.":[34],"Deep":[35],"neural":[36,67],"network":[37,68,151],"can":[38],"serve":[39],"as":[40,57,93],"efficient":[41],"emulators,":[42],"but":[43],"most":[44],"trained":[46],"only":[47],"for":[48,143,250],"next-step":[49],"often":[52],"drift":[53,199],"or":[54],"become":[55],"unstable":[56],"forecast":[59],"horizon":[60],"grows.":[61],"We":[62],"propose":[63],"a":[64,75,94,135,176,183,240,246],"multi-horizon":[65],"graph":[66,115,137],"emulator":[69,249],"learns":[71],"state-to-state":[72],"transitions":[73],"from":[74,234],"single":[76],"current":[77,114,158],"time":[78,232],"multiple":[80],"future":[81,121,167,231],"lead":[82,173],"times":[83,174],"within":[84],"one":[85],"unified":[86,177],"model.":[87],"The":[88],"physical":[89],"domain":[90],"represented":[92],"graph,":[95],"where":[96],"nodes":[97],"correspond":[98],"spatial":[100,110],"locations":[101],"with":[102,139,175,188,194],"time-varying":[103],"attributes":[105],"edges":[107],"encode":[108],"local":[109],"interactions.":[111],"Given":[112],"state,":[116,159],"model":[118],"predicts":[119,152,229],"evolution":[122],"key":[124],"fields,":[125],"ice":[126,129],"thickness":[127],"velocities":[130],"at":[131],"all":[132,172],"nodes,":[133],"using":[134],"shared":[136],"backbone":[138],"separate":[140],"output":[141],"branches":[142],"each":[144,230],"target":[145],"variable.":[146],"To":[147],"improve":[148],"stability,":[149],"state":[153,237],"increments":[154],"relative":[155],"which":[160],"then":[162],"added":[163],"back":[164],"reconstruct":[166],"states.":[168],"Training":[169],"jointly":[170],"optimizes":[171],"regression":[178],"objective,":[179],"inference":[181],"uses":[182],"coarse-to-fine":[184],"rollout":[185],"advances":[187],"larger":[189],"jumps":[190,196],"selectively":[192],"refines":[193],"shorter":[195],"reduce":[198],"avoid":[201],"redundant":[202],"computation.":[203],"Experiments":[204],"on":[205],"multi-decadal":[206],"Pine":[207],"Island":[208],"Glacier":[209],"simulations":[210],"show":[211],"our":[213],"approach":[214],"achieves":[215],"higher":[216],"accuracy":[218],"improved":[220],"stability":[221],"than":[222],"both":[223],"(i)":[224],"an":[225],"initial-state":[226],"baseline":[227],"directly":[233],"starting":[236],"(ii)":[239],"standard":[241],"single-step":[242],"rollout,":[244],"producing":[245],"more":[247],"reliable":[248],"downstream":[251],"climate":[252],"sea-level":[254],"studies.":[255]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-30T00:00:00"}