{"id":"https://openalex.org/W7163997467","doi":"https://doi.org/10.48550/arxiv.2606.07694","title":"Vessel Traffic Flow Prediction on Sparse Data via Spatio-Temporal Graph Neural Networks with a Learnable Tweedie Head","display_name":"Vessel Traffic Flow Prediction on Sparse Data via Spatio-Temporal Graph Neural Networks with a Learnable Tweedie Head","publication_year":2026,"publication_date":"2026-06-05","ids":{"openalex":"https://openalex.org/W7163997467","doi":"https://doi.org/10.48550/arxiv.2606.07694"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.07694","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07694","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.07694","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101460125","display_name":"Kyeongjun Lee","orcid":"https://orcid.org/0000-0002-0754-5172"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Kyeongjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100716622","display_name":"Heeyoung Kim","orcid":"https://orcid.org/0000-0001-6415-9887"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Heeyoung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.6424000263214111,"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":0.6424000263214111,"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"}},{"id":"https://openalex.org/T11622","display_name":"Maritime Navigation and Safety","score":0.1826000064611435,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14413","display_name":"Advanced Technologies in Various Fields","score":0.014100000262260437,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.5580999851226807},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4287000000476837},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.3977000117301941},{"id":"https://openalex.org/keywords/traffic-flow","display_name":"Traffic flow (computer networking)","score":0.3804999887943268},{"id":"https://openalex.org/keywords/port","display_name":"Port (circuit theory)","score":0.34630000591278076},{"id":"https://openalex.org/keywords/deviance","display_name":"Deviance (statistics)","score":0.34119999408721924},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.30059999227523804},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.29440000653266907}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6187000274658203},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5580999851226807},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C207512268","wikidata":"https://www.wikidata.org/wiki/Q3074551","display_name":"Traffic flow (computer networking)","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3675000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C32802771","wikidata":"https://www.wikidata.org/wiki/Q2443617","display_name":"Port (circuit theory)","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C177599991","wikidata":"https://www.wikidata.org/wiki/Q3706279","display_name":"Deviance (statistics)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32420000433921814},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C114809511","wikidata":"https://www.wikidata.org/wiki/Q1412924","display_name":"Flow network","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.07694","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07694","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.07694","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07694","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Accurate":[0],"vessel":[1],"traffic":[2,16,137,177],"flow":[3,17],"prediction":[4],"is":[5],"crucial":[6],"for":[7,117,174],"smart":[8],"port":[9,131],"operations":[10],"and":[11,45,113,150],"navigational":[12],"safety.":[13],"However,":[14],"maritime":[15,136,176],"data":[18,143],"are":[19],"often":[20],"highly":[21],"sparse":[22],"with":[23],"intermittent":[24],"bursts,":[25],"making":[26],"robust":[27],"forecasting":[28,119],"challenging.":[29],"Under":[30],"such":[31],"conditions,":[32],"conventional":[33],"spatio-temporal":[34],"graph":[35,138],"neural":[36],"networks":[37],"(ST-GNNs)":[38],"can":[39,64,83],"degrade":[40],"toward":[41],"conservative":[42,67],"near-zero":[43],"predictions":[44],"fail":[46],"to":[47,91,126,170],"capture":[48,127],"non-zero":[49,167],"activity.":[50],"Although":[51],"zero-inflated":[52],"negative":[53],"binomial":[54],"(ZINB)":[55],"models":[56],"partially":[57],"address":[58,72],"excess":[59],"zeros,":[60],"their":[61],"two-part":[62],"formulation":[63],"still":[65],"remain":[66],"around":[68],"abrupt":[69],"transitions.":[70],"To":[71],"these":[73],"issues,":[74],"we":[75],"propose":[76],"a":[77,87,122,135],"model-agnostic":[78],"learnable":[79],"Tweedie":[80,98,110],"head":[81,157],"that":[82,154],"be":[84],"attached":[85],"as":[86],"plug-and-play":[88],"output":[89],"module":[90],"arbitrary":[92],"ST-GNN":[93,163],"backbones.":[94],"Instead":[95],"of":[96,147],"likelihood-based":[97],"training,":[99],"which":[100],"typically":[101],"requires":[102],"surrogate":[103],"objectives,":[104],"our":[105],"approach":[106],"optimizes":[107],"the":[108,115,145,155],"closed-form":[109],"unit":[111],"deviance":[112],"predicts":[114],"mean":[116],"point":[118],"while":[120],"learning":[121],"node-level":[123],"variance":[124],"power":[125],"heterogeneous":[128],"variability":[129],"across":[130,161],"areas.":[132],"Experiments":[133],"on":[134,166],"constructed":[139],"from":[140],"real-world":[141],"AIS":[142],"in":[144],"Port":[146],"Los":[148],"Angeles":[149],"Long":[151],"Beach":[152],"show":[153],"proposed":[156],"consistently":[158],"improves":[159],"RMSE":[160],"multiple":[162],"backbones,":[164],"especially":[165],"events,":[168],"leading":[169],"more":[171],"reliable":[172],"forecasts":[173],"practical":[175],"control.":[178]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}