{"id":"https://openalex.org/W7140162519","doi":"https://doi.org/10.48550/arxiv.2603.21879","title":"SmaAT-QMix-UNet: A Parameter-Efficient Vector-Quantized UNet for Precipitation Nowcasting","display_name":"SmaAT-QMix-UNet: A Parameter-Efficient Vector-Quantized UNet for Precipitation Nowcasting","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7140162519","doi":"https://doi.org/10.48550/arxiv.2603.21879"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.21879","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21879","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.21879","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Stavrou, Nikolas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stavrou, Nikolas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mehrkanoon, Siamak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehrkanoon, Siamak","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/T10466","display_name":"Meteorological Phenomena and Simulations","score":0.8029999732971191,"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":0.8029999732971191,"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/T11234","display_name":"Precipitation Measurement and Analysis","score":0.1647000014781952,"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/T11490","display_name":"Hydrological Forecasting Using AI","score":0.006500000134110451,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"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/nowcasting","display_name":"Nowcasting","score":0.9469000101089478},{"id":"https://openalex.org/keywords/precipitation","display_name":"Precipitation","score":0.506600022315979},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4722000062465668},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4544999897480011},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4388999938964844},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.42800000309944153},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.388700008392334},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3790999948978424}],"concepts":[{"id":"https://openalex.org/C2781013037","wikidata":"https://www.wikidata.org/wiki/Q1433331","display_name":"Nowcasting","level":2,"score":0.9469000101089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5576000213623047},{"id":"https://openalex.org/C107054158","wikidata":"https://www.wikidata.org/wiki/Q25257","display_name":"Precipitation","level":2,"score":0.506600022315979},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4722000062465668},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.4657000005245209},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36719998717308044},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.35580000281333923},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33980000019073486},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C140178040","wikidata":"https://www.wikidata.org/wiki/Q18402512","display_name":"Quantitative precipitation forecast","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C21001229","wikidata":"https://www.wikidata.org/wiki/Q182868","display_name":"Weather forecasting","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C92237259","wikidata":"https://www.wikidata.org/wiki/Q863343","display_name":"Weather radar","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2531000077724457},{"id":"https://openalex.org/C75398719","wikidata":"https://www.wikidata.org/wiki/Q7268938","display_name":"Quantitative precipitation estimation","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.21879","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21879","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.21879","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.21879","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":"Preprint"},"sustainable_development_goals":[{"score":0.6206769347190857,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Weather":[0,13],"forecasting":[1],"supports":[2],"critical":[3],"socioeconomic":[4],"activities":[5],"and":[6,63,72,82,89,113],"complements":[7],"environmental":[8],"protection,":[9],"yet":[10],"operational":[11],"Numerical":[12],"Prediction":[14],"(NWP)":[15],"systems":[16],"remain":[17],"computationally":[18],"intensive,":[19],"thus":[20],"being":[21],"inefficient":[22],"for":[23,144],"certain":[24],"applications.":[25],"Meanwhile,":[26],"recent":[27],"advances":[28],"in":[29,37],"deep":[30],"data-driven":[31],"models":[32],"have":[33],"demonstrated":[34],"promising":[35],"results":[36],"nowcasting":[38,85],"tasks.":[39],"This":[40],"paper":[41],"presents":[42],"SmaAT-QMix-UNet,":[43],"an":[44],"enhanced":[45],"variant":[46],"of":[47,130],"SmaAT-UNet":[48],"that":[49],"introduces":[50],"two":[51],"key":[52],"innovations:":[53],"a":[54,93,127],"vector":[55],"quantization":[56],"(VQ)":[57],"bottleneck":[58],"at":[59],"the":[60,79,114,121,131,135],"encoder-decoder":[61],"bridge,":[62],"mixed":[64],"kernel":[65],"depth-wise":[66],"convolutions":[67],"(MixConv)":[68],"replacing":[69],"selected":[70],"encoder":[71,139],"decoder":[73],"blocks.":[74],"These":[75],"enhancements":[76],"both":[77],"reduce":[78],"model's":[80],"size":[81],"improve":[83],"its":[84],"performance.":[86],"We":[87],"train":[88],"evaluate":[90],"SmaAT-QMix-UNet":[91,145],"on":[92,149],"Dutch":[94],"radar":[95],"precipitation":[96,100],"dataset":[97],"(2016-2019),":[98],"predicting":[99],"30":[101],"minutes":[102],"ahead.":[103],"Three":[104],"configurations":[105],"are":[106],"benchmarked:":[107],"using":[108],"only":[109,111],"VQ,":[110],"MixConv,":[112],"full":[115],"SmaAT-QMix-UNet.":[116],"Grad-CAM":[117],"saliency":[118],"maps":[119],"highlight":[120],"regions":[122],"influencing":[123],"each":[124],"nowcast,":[125],"while":[126],"UMAP":[128],"embedding":[129],"codewords":[132],"illustrates":[133],"how":[134],"VQ":[136],"layer":[137],"clusters":[138],"outputs.":[140],"The":[141],"source":[142],"code":[143],"is":[146],"publicly":[147],"available":[148],"GitHub:":[150],"https://github.com/nstavr04/MasterThesisSnellius.":[151]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-25T00:00:00"}