{"id":"https://openalex.org/W7163692011","doi":"https://doi.org/10.22541/essoar.15004382/v1","title":"GeoVLM: Geography-Aware Multimodal Visual Reasoning for Earth Science Applications","display_name":"GeoVLM: Geography-Aware Multimodal Visual Reasoning for Earth Science Applications","publication_year":2026,"publication_date":"2026-06-05","ids":{"openalex":"https://openalex.org/W7163692011","doi":"https://doi.org/10.22541/essoar.15004382/v1"},"language":"en","primary_location":{"id":"doi:10.22541/essoar.15004382/v1","doi":"https://doi.org/10.22541/essoar.15004382/v1","is_oa":true,"landing_page_url":"https://doi.org/10.22541/essoar.15004382/v1","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.22541/essoar.15004382/v1","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138013400","display_name":"Narawit Phongphat","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Narawit Phongphat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114453876","display_name":"Apiradee Boonmee","orcid":"https://orcid.org/0009-0002-9005-9681","observed_orcids":["https://orcid.org/0009-0002-9005-9681"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Apiradee Boonmee","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-9005-9681","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137939516","display_name":"Ratchanon Srisuk","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ratchanon Srisuk","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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9028000235557556,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9028000235557556,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07039999961853027,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13890","display_name":"Remote Sensing and Land Use","score":0.0052999998442828655,"subfield":{"id":"https://openalex.org/subfields/3305","display_name":"Geography, Planning and Development"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7429999709129333},{"id":"https://openalex.org/keywords/geosciences","display_name":"earth sciences","score":0.6710000038146973},{"id":"https://openalex.org/keywords/temporal-change-detection","display_name":"temporal change detection","score":0.8259999752044678},{"id":"https://openalex.org/keywords/satellite-imagery","display_name":"satellite imagery","score":0.7110000252723694},{"id":"https://openalex.org/keywords/synthetic-aperture-radar","display_name":"synthetic aperture radar","score":0.8970000147819519},{"id":"https://openalex.org/keywords/cross-modal-fusion","display_name":"cross-modal fusion","score":0.7829999923706055},{"id":"https://openalex.org/keywords/multi-agent-reasoning","display_name":"multi-agent reasoning","score":0.7160000205039978},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.7710000276565552},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.47999998927116394},{"id":"https://openalex.org/keywords/long-context-reasoning","display_name":"long-context reasoning","score":0.48500001430511475},{"id":"https://openalex.org/keywords/climate-change","display_name":"climate change","score":0.3160000145435333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6978999972343445},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.6105999946594238},{"id":"https://openalex.org/C39399123","wikidata":"https://www.wikidata.org/wiki/Q1348989","display_name":"Earth observation","level":3,"score":0.5426999926567078},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4747999906539917},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C87360688","wikidata":"https://www.wikidata.org/wiki/Q740686","display_name":"Synthetic aperture radar","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.29089999198913574},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C120938966","wikidata":"https://www.wikidata.org/wiki/Q5275845","display_name":"Digital Earth","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2778102629","wikidata":"https://www.wikidata.org/wiki/Q725252","display_name":"Satellite imagery","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C119666444","wikidata":"https://www.wikidata.org/wiki/Q5977280","display_name":"Temporal resolution","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.22541/essoar.15004382/v1","doi":"https://doi.org/10.22541/essoar.15004382/v1","is_oa":true,"landing_page_url":"https://doi.org/10.22541/essoar.15004382/v1","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.22541/essoar.15004382/v1","doi":"https://doi.org/10.22541/essoar.15004382/v1","is_oa":true,"landing_page_url":"https://doi.org/10.22541/essoar.15004382/v1","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7163914147","https://openalex.org/W7161935930","https://openalex.org/W7166200214","https://openalex.org/W7170797628","https://openalex.org/W7139964634","https://openalex.org/W4413147540","https://openalex.org/W7164208181","https://openalex.org/W7172100251","https://openalex.org/W7196951165","https://openalex.org/W4415707439"],"abstract_inverted_index":{"The":[0],"integration":[1],"of":[2,16,33,174,203,217],"large":[3],"vision-language":[4],"models":[5],"with":[6,172],"earth":[7,35,53],"science":[8,54],"data":[9,115],"presents":[10],"unique":[11],"challenges":[12],"including":[13,117],"the":[14,20,31,193,200,215],"scarcity":[15],"labeled":[17],"geoscientific":[18],"data,":[19],"need":[21],"for":[22,52,78],"effective":[23],"long-context":[24],"reasoning":[25,48,112,156],"over":[26],"temporal":[27,76,146],"satellite":[28,94],"imagery,":[29,119],"and":[30,75,102,125,144,151,153,159,185,206],"heterogeneity":[32],"multimodal":[34,46],"observation":[36],"sources.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"GeoVLM,":[43],"a":[44,61,82,103],"unified":[45],"visual":[47,90],"framework":[49],"specifically":[50],"designed":[51],"applications.":[55],"GeoVLM":[56,130,165],"introduces":[57],"three":[58,136],"key":[59],"innovations:":[60],"Geography-Aware":[62],"Visual":[63],"In-Context":[64],"Learning":[65],"module":[66],"that":[67,87,109,164],"selects":[68],"demonstration":[69],"examples":[70],"based":[71],"on":[72,131,142,149,157,178,183,189],"spatial,":[73],"spectral,":[74],"similarity":[77],"few-shot":[79,139],"geospatial":[80,140],"interpretation;":[81],"Temporal":[83],"Redundancy-Aware":[84],"Attention":[85],"mechanism":[86],"adaptively":[88],"suppresses":[89],"redundancy":[91],"in":[92],"long":[93],"image":[95],"sequences":[96],"while":[97],"preserving":[98],"critical":[99],"change":[100,147],"information;":[101],"Modular":[104],"Multi-Agent":[105],"Cross-Modal":[106],"Fusion":[107],"architecture":[108],"enables":[110],"collaborative":[111],"across":[113,169],"heterogeneous":[114],"sources":[116],"optical":[118],"synthetic":[120],"aperture":[121],"radar,":[122],"meteorological":[123],"measurements,":[124],"geological":[126],"surveys.":[127],"We":[128],"evaluate":[129],"six":[132],"benchmark":[133],"datasets":[134],"spanning":[135],"core":[137],"tasks:":[138],"interpretation":[141],"DFC15":[143],"Potsdam,":[145],"detection":[148],"LEVIR-CD":[150],"WHU-CD,":[152],"extreme":[154],"event":[155],"ClimateBench":[158,190],"MultiEarth.":[160],"Experimental":[161],"results":[162],"demonstrate":[163],"achieves":[166],"state-of-the-art":[167],"performance":[168],"all":[170],"tasks,":[171],"improvements":[173],"3.5":[175],"percent":[176,181],"mIoU":[177],"DFC15,":[179],"2.7":[180],"F1":[182],"LEVIR-CD,":[184],"0.47":[186],"RMSE":[187],"reduction":[188],"compared":[191],"to":[192],"best":[194],"existing":[195],"methods.":[196],"Ablation":[197],"studies":[198],"confirm":[199],"complementary":[201],"contributions":[202],"each":[204],"module,":[205],"human":[207],"evaluation":[208],"by":[209],"remote":[210],"sensing":[211],"experts":[212],"further":[213],"validates":[214],"quality":[216],"our":[218],"predictions.":[219]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-06-06T00:00:00"}