{"id":"https://openalex.org/W7128529291","doi":"https://doi.org/10.48550/arxiv.2602.07463","title":"GlobalWasteData: A Large-Scale, Integrated Dataset for Robust Waste Classification and Environmental Monitoring","display_name":"GlobalWasteData: A Large-Scale, Integrated Dataset for Robust Waste Classification and Environmental Monitoring","publication_year":2026,"publication_date":"2026-02-07","ids":{"openalex":"https://openalex.org/W7128529291","doi":"https://doi.org/10.48550/arxiv.2602.07463"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.07463","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.07463","pdf_url":"https://arxiv.org/pdf/2602.07463","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.07463","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125511957","display_name":"Misbah Ijaz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99165933","display_name":"University of Gujrat","ror":"https://ror.org/01xe5fb92","country_code":"PK","type":"education","lineage":["https://openalex.org/I99165933"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ijaz, Misbah","raw_affiliation_strings":["Department of Computer Science , University of Gujrat , Gujrat , 51700 , Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Gujrat , Gujrat , 51700 , Pakistan","institution_ids":["https://openalex.org/I99165933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125564544","display_name":"Saif Ur Rehman Khan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Saif Ur Rehman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128915834","display_name":"Abd Ur Rehman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99165933","display_name":"University of Gujrat","ror":"https://ror.org/01xe5fb92","country_code":"PK","type":"education","lineage":["https://openalex.org/I99165933"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Rehman, Abd Ur","raw_affiliation_strings":["Department of Computer Science , University of Gujrat , Gujrat , 51700 , Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Gujrat , Gujrat , 51700 , Pakistan","institution_ids":["https://openalex.org/I99165933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025710692","display_name":"Tayyaba Asif","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I153267046","display_name":"University of Kaiserslautern","ror":"https://ror.org/04zrf7b53","country_code":"DE","type":"education","lineage":["https://openalex.org/I153267046","https://openalex.org/I4387152675"]},{"id":"https://openalex.org/I4387152675","display_name":"Rheinland-Pf\u00e4lzische Technische Universit\u00e4t Kaiserslautern-Landau","ror":"https://ror.org/01qrts582","country_code":"DE","type":"education","lineage":["https://openalex.org/I4387152675"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Asif, Tayyaba","raw_affiliation_strings":["Department of Computer Science , Rhineland-Palatinate Technical University of Kaiserslautern-Landau , orgaddressKaiserslautern , 67663 , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Rhineland-Palatinate Technical University of Kaiserslautern-Landau , orgaddressKaiserslautern , 67663 , Germany","institution_ids":["https://openalex.org/I153267046","https://openalex.org/I4387152675"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128920312","display_name":"Sebastian Vollmer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vollmer, Sebastian","raw_affiliation_strings":["German Research Center for Artificial Intelligence , Kaiserslautern , 67663 , Germany","Intelligentx GmbH (intelligentx.com) , Kaiserslautern , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence , Kaiserslautern , 67663 , Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Intelligentx GmbH (intelligentx.com) , Kaiserslautern , Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146809033","display_name":"Andreas Dengel","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dengel, Andreas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068324429","display_name":"Muhammad Nabeel Asim","orcid":"https://orcid.org/0000-0001-5507-198X","observed_orcids":["https://orcid.org/0000-0001-5507-198X"]},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Asim, Muhammad Nabeel","raw_affiliation_strings":["German Research Center for Artificial Intelligence , Kaiserslautern , 67663 , Germany","Intelligentx GmbH (intelligentx.com) , Kaiserslautern , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence , Kaiserslautern , 67663 , Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Intelligentx GmbH (intelligentx.com) , Kaiserslautern , Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6967999935150146,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6967999935150146,"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/T11108","display_name":"Municipal Solid Waste Management","score":0.15060000121593475,"subfield":{"id":"https://openalex.org/subfields/2311","display_name":"Waste Management and Disposal"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14179","display_name":"Waste Management and Recycling","score":0.09440000355243683,"subfield":{"id":"https://openalex.org/subfields/2311","display_name":"Waste Management and Disposal"},"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/waste-classification","display_name":"waste classification","score":0.9810000061988831},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.7070000171661377},{"id":"https://openalex.org/keywords/data-merging","display_name":"data merging","score":0.6200000047683716},{"id":"https://openalex.org/keywords/waste-sorting","display_name":"waste sorting","score":0.5429999828338623},{"id":"https://openalex.org/keywords/recycling-automation","display_name":"recycling automation","score":0.9079999923706055},{"id":"https://openalex.org/keywords/environmental-monitoring","display_name":"environmental monitoring","score":0.9620000123977661},{"id":"https://openalex.org/keywords/image-annotation","display_name":"image annotation","score":0.6660000085830688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7037000060081482},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5418000221252441},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4514000117778778},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4203999936580658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4108999967575073},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C512654426","wikidata":"https://www.wikidata.org/wiki/Q19652","display_name":"Public domain","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C539469273","wikidata":"https://www.wikidata.org/wiki/Q1749732","display_name":"Environmental monitoring","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.07463","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.07463","pdf_url":"https://arxiv.org/pdf/2602.07463","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.07463","doi":"https://doi.org/10.48550/arxiv.2602.07463","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.07463","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.07463","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.07463","pdf_url":"https://arxiv.org/pdf/2602.07463","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":1.0,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128529291.pdf","grobid_xml":"https://content.openalex.org/works/W7128529291.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1965923970","https://openalex.org/W3011137323","https://openalex.org/W4313307742","https://openalex.org/W4317515534","https://openalex.org/W4395089150"],"related_works":["https://openalex.org/W7128745771","https://openalex.org/W7203725227","https://openalex.org/W4409361486","https://openalex.org/W4415974628","https://openalex.org/W7138460419","https://openalex.org/W4407028140","https://openalex.org/W4400076965","https://openalex.org/W4413737633","https://openalex.org/W4411143229","https://openalex.org/W4405847713"],"abstract_inverted_index":{"The":[0,31],"growing":[1],"amount":[2],"of":[3,19,33,45,117,164],"waste":[4,23,62,168,205],"is":[5,26,208],"a":[6,113,143,191],"problem":[7],"for":[8,16,28,53,194],"the":[9,41,51,109,162],"environment":[10],"that":[11,96],"requires":[12],"efficient":[13],"sorting":[14],"techniques":[15],"various":[17],"kinds":[18],"waste.":[20],"An":[21],"automated":[22],"classification":[24,57,63],"system":[25],"used":[27],"this":[29,131,188],"purpose.":[30],"effectiveness":[32],"these":[34,91,105],"Artificial":[35],"Intelligence":[36],"(AI)":[37],"models":[38,95],"depends":[39],"on":[40],"quality":[42,176],"and":[43,55,70,83,156,166,180,204,207,215],"accessibility":[44],"publicly":[46,139,209],"available":[47,140,210],"datasets,":[48],"which":[49],"provide":[50],"basis":[52],"training":[54],"analyzing":[56],"algorithms.":[58],"Although":[59],"several":[60],"public":[61],"datasets":[64,92,141],"exist,":[65],"they":[66],"remain":[67],"fragmented,":[68],"inconsistent,":[69],"biased":[71],"toward":[72],"specific":[73],"environments.":[74],"Differences":[75],"in":[76,199],"class":[77,84,159],"names,":[78],"annotation":[79],"formats,":[80],"image":[81],"conditions,":[82],"distributions":[85],"make":[86],"it":[87],"difficult":[88],"to":[89,99,211],"combine":[90],"or":[93],"train":[94],"generalize":[97],"well":[98],"real":[100],"world":[101],"scenarios.":[102],"To":[103],"address":[104],"issues,":[106],"we":[107],"introduce":[108],"GlobalWasteData":[110],"(GWD)":[111],"archive,":[112],"large":[114],"scale":[115],"dataset":[116,185,189],"89,807":[118],"images":[119],"across":[120],"14":[121],"main":[122],"categories,":[123],"annotated":[124],"with":[125],"68":[126],"distinct":[127],"subclasses.":[128],"We":[129],"compile":[130],"novel":[132],"integrated":[133],"GWD":[134,148],"archive":[135,149],"by":[136],"merging":[137],"multiple":[138],"into":[142],"single,":[144],"unified":[145],"resource.":[146],"This":[147],"offers":[150,190],"consistent":[151],"labeling,":[152],"improved":[153],"domain":[154],"diversity,":[155],"more":[157],"balanced":[158],"representation,":[160],"enabling":[161],"development":[163],"robust":[165],"generalizable":[167],"recognition":[169],"models.":[170],"Additional":[171],"preprocessing":[172],"steps":[173],"such":[174],"as":[175],"filtering,":[177],"duplicate":[178],"removal,":[179],"metadata":[181],"generation":[182],"further":[183],"improve":[184],"reliability.":[186],"Overall,":[187],"strong":[192],"foundation":[193],"Machine":[195],"Learning":[196],"(ML)":[197],"applications":[198],"environmental":[200],"monitoring,":[201],"recycling":[202],"automation,":[203],"identification,":[206],"promote":[212],"future":[213],"research":[214],"reproducibility.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-11T00:00:00"}