{"id":"https://openalex.org/W4415707439","doi":"https://doi.org/10.1109/tgrs.2025.3626941","title":"EarthGPT-X: A Spatial MLLM for Multilevel Multisource Remote Sensing Imagery Understanding With Visual Prompting","display_name":"EarthGPT-X: A Spatial MLLM for Multilevel Multisource Remote Sensing Imagery Understanding With Visual Prompting","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415707439","doi":"https://doi.org/10.1109/tgrs.2025.3626941"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2025.3626941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3626941","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092401779","display_name":"Wei Zhang","orcid":"https://orcid.org/0009-0003-7332-126X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["School of Interdisciplinary Science, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-7332-126X","affiliations":[{"raw_affiliation_string":"School of Interdisciplinary Science, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102999194","display_name":"Miaoxin Cai","orcid":"https://orcid.org/0009-0007-2584-5949"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaoxin Cai","raw_affiliation_strings":["National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2584-5949","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064618700","display_name":"Yaqian Ning","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqian Ning","raw_affiliation_strings":["School of Optics and Photonics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Optics and Photonics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100688517","display_name":"Tong Zhang","orcid":"https://orcid.org/0000-0002-1769-9829"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Zhang","raw_affiliation_strings":["National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1769-9829","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023179941","display_name":"Yin Zhuang","orcid":"https://orcid.org/0000-0002-0443-1081"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Zhuang","raw_affiliation_strings":["National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0443-1081","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023507910","display_name":"Shijian Lu","orcid":"https://orcid.org/0000-0002-6766-2506"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shijian Lu","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","College of Computing and Data Science, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6766-2506","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327685","display_name":"He Chen","orcid":"https://orcid.org/0000-0003-4182-6493"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Chen","raw_affiliation_strings":["National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4182-6493","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362041","display_name":"Jun Li","orcid":"https://orcid.org/0000-0003-1613-9448"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["School of Computer Science and Hubei Key Laboratory of Intelligent Geo-Information Processing, China University of Geosciences, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-1613-9448","affiliations":[{"raw_affiliation_string":"School of Computer Science and Hubei Key Laboratory of Intelligent Geo-Information Processing, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001776125","display_name":"Xuerui Mao","orcid":"https://orcid.org/0000-0002-8452-5773"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I4210165204","display_name":"Zhuhai Institute of Advanced Technology","ror":"https://ror.org/05r1mzq61","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761","https://openalex.org/I4210165204"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuerui Mao","raw_affiliation_strings":["Beijing Institute of Technology (Zhuhai), Zhuhai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology (Zhuhai), Zhuhai, China","institution_ids":["https://openalex.org/I125839683","https://openalex.org/I4210165204"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5295,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.687037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.928600013256073,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.928600013256073,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.026499999687075615,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0044999998062849045,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5095999836921692},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4717999994754791},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4456000030040741},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4401000142097473},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4205999970436096},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.39800000190734863},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.3596000075340271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8216000199317932},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4918000102043152},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4401000142097473},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3458999991416931},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.3140000104904175},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2761000096797943},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26499998569488525}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tgrs.2025.3626941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3626941","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/217775","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/217775","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4914362321","display_name":null,"funder_award_id":"92152109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6716103886","display_name":null,"funder_award_id":"T2225019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W1958291604","https://openalex.org/W1980038761","https://openalex.org/W2101105183","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2510520237","https://openalex.org/W2515866431","https://openalex.org/W2779054585","https://openalex.org/W2911584214","https://openalex.org/W2920981979","https://openalex.org/W2928007866","https://openalex.org/W2947312908","https://openalex.org/W2962766617","https://openalex.org/W2963115613","https://openalex.org/W2963250244","https://openalex.org/W2964194231","https://openalex.org/W2997464028","https://openalex.org/W3098267758","https://openalex.org/W3198377975","https://openalex.org/W3200733355","https://openalex.org/W3202187941","https://openalex.org/W3207919963","https://openalex.org/W4288083516","https://openalex.org/W4292968451","https://openalex.org/W4312605942","https://openalex.org/W4312651322","https://openalex.org/W4312915946","https://openalex.org/W4322707256","https://openalex.org/W4366598917","https://openalex.org/W4387886005","https://openalex.org/W4390874575","https://openalex.org/W4391021462","https://openalex.org/W4391032437","https://openalex.org/W4391451889","https://openalex.org/W4392007279","https://openalex.org/W4395041667","https://openalex.org/W4399399400","https://openalex.org/W4399449337","https://openalex.org/W4400314890","https://openalex.org/W4402703108","https://openalex.org/W4402716166","https://openalex.org/W4402727018","https://openalex.org/W4402734376","https://openalex.org/W4402776460","https://openalex.org/W4403906565","https://openalex.org/W4403919659","https://openalex.org/W4404177154","https://openalex.org/W4404536218","https://openalex.org/W4405895891","https://openalex.org/W4407152340","https://openalex.org/W4409367667","https://openalex.org/W4409383105","https://openalex.org/W4410226751","https://openalex.org/W4410706693","https://openalex.org/W4410808562","https://openalex.org/W4412888596","https://openalex.org/W4413147540"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1,131],"in":[2,87,119,193],"natural-domain":[3],"multi-modal":[4],"large":[5],"language":[6,50],"models":[7],"(MLLMs)":[8],"have":[9],"demonstrated":[10],"effective":[11],"spatial":[12,37,67,139],"reasoning":[13],"through":[14],"visual":[15,81,85,106,191],"and":[16,35,48,54,75,79,111,144,148,160,165,176,187,198],"textual":[17],"prompting.":[18],"However,":[19],"their":[20],"direct":[21],"transfer":[22],"to":[23,45,113,136],"remote":[24],"sensing":[25,31],"(RS)":[26],"is":[27,62],"hindered":[28],"by":[29],"heterogeneous":[30],"physics,":[32],"diverse":[33,84],"modalities,":[34],"unique":[36],"scales.":[38],"Existing":[39],"RS":[40,72,177,194],"MLLMs":[41],"are":[42,200],"mainly":[43],"limited":[44],"optical":[46],"imagery":[47,73],"plain":[49],"interaction,":[51],"preventing":[52],"flexible":[53,66],"scalable":[55],"real-world":[56],"applications.":[57],"In":[58],"this":[59],"article,":[60],"EarthGPT-X":[61,95,171],"proposed,":[63],"the":[64,115,129,180],"first":[65,181],"MLLM":[68],"that":[69,170],"unifies":[70],"multi-source":[71,125],"comprehension":[74],"accomplishes":[76],"both":[77],"coarse-grained":[78],"fine-grained":[80,145],"tasks":[82],"under":[83],"prompts":[86,107],"a":[88,98,123,152],"single":[89],"framework.":[90],"Distinct":[91],"from":[92],"prior":[93,174],"models,":[94],"introduces:":[96],"1)":[97],"dual-prompt":[99],"mechanism":[100],"combining":[101],"text":[102],"instructions":[103],"with":[104],"various":[105],"(i.e.,":[108],"point,":[109],"box,":[110],"free-form)":[112],"mimic":[114],"versatility":[116],"of":[117,184],"referring":[118],"human":[120],"life;":[121],"2)":[122],"comprehensive":[124],"multi-level":[126,188],"prompting":[127,192],"dataset,":[128],"model":[130],"beyond":[132],"holistic":[133],"image":[134],"understanding":[135,143],"support":[137],"hierarchical":[138],"reasoning,":[140],"including":[141],"scene-level":[142],"object":[146],"attributes":[147],"relational":[149],"analysis;":[150],"3)":[151],"cross-domain":[153],"one-stage":[154],"fusion":[155],"training":[156],"strategy,":[157],"enabling":[158],"efficient":[159],"consistent":[161],"alignment":[162],"across":[163],"modalities":[164],"tasks.":[166],"Extensive":[167],"experiments":[168],"demonstrate":[169],"substantially":[172],"outperforms":[173],"natural":[175],"MLLMs,":[178],"establishing":[179],"framework":[182],"capable":[183],"multi-source,":[185],"multi-task,":[186],"interpretation":[189],"using":[190],"scenarios.":[195],"The":[196],"code":[197],"dataset":[199],"available":[201],"athttps://github.com/wivizhang/EarthGPT-X.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-30T00:00:00"}