{"id":"https://openalex.org/W7224090789","doi":"https://doi.org/10.56831/psen-09-299","title":"LLM-Enhanced Pollution Source Attribution: A Multimodal Framework Integrating Vision Transformers with Semantic Feature Extraction","display_name":"LLM-Enhanced Pollution Source Attribution: A Multimodal Framework Integrating Vision Transformers with Semantic Feature Extraction","publication_year":2026,"publication_date":"2026-10-28","ids":{"openalex":"https://openalex.org/W7224090789","doi":"https://doi.org/10.56831/psen-09-299"},"language":"en","primary_location":{"id":"doi:10.56831/psen-09-299","doi":"https://doi.org/10.56831/psen-09-299","is_oa":true,"landing_page_url":"https://doi.org/10.56831/psen-09-299","pdf_url":"https://doi.org/10.56831/psen-09-299","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PriMera Scientific Engineering","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.56831/psen-09-299","any_repository_has_fulltext":null},"authorships":[],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7390783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12120","display_name":"Air Quality Monitoring and Forecasting","score":0.9916999936103821,"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"}},"topics":[{"id":"https://openalex.org/T12120","display_name":"Air Quality Monitoring and Forecasting","score":0.9916999936103821,"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"}},{"id":"https://openalex.org/T10190","display_name":"Air Quality and Health Impacts","score":0.002400000113993883,"subfield":{"id":"https://openalex.org/subfields/2307","display_name":"Health, Toxicology and Mutagenesis"},"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/T10075","display_name":"Atmospheric chemistry and aerosols","score":0.0006000000284984708,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9589999914169312},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.984000027179718},{"id":"https://openalex.org/keywords/semantic-feature-extraction","display_name":"semantic feature extraction","score":0.9049999713897705},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":0.9629999995231628},{"id":"https://openalex.org/keywords/environmental-policy","display_name":"environmental policy","score":0.8209999799728394}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8008000254631042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131999731063843},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49160000681877136},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4740999937057495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4361000061035156},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3885999917984009},{"id":"https://openalex.org/C539469273","wikidata":"https://www.wikidata.org/wiki/Q1749732","display_name":"Environmental monitoring","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C521259446","wikidata":"https://www.wikidata.org/wiki/Q58734","display_name":"Pollution","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C110893760","wikidata":"https://www.wikidata.org/wiki/Q3115590","display_name":"Named graph","level":5,"score":0.36880001425743103},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.36090001463890076},{"id":"https://openalex.org/C70798638","wikidata":"https://www.wikidata.org/wiki/Q4575211","display_name":"Environmental quality","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C2909468537","wikidata":"https://www.wikidata.org/wiki/Q58734","display_name":"Environmental pollution","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.29589998722076416},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C139458680","wikidata":"https://www.wikidata.org/wiki/Q12184942","display_name":"Interoperation","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2533999979496002},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.56831/psen-09-299","doi":"https://doi.org/10.56831/psen-09-299","is_oa":true,"landing_page_url":"https://doi.org/10.56831/psen-09-299","pdf_url":"https://doi.org/10.56831/psen-09-299","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PriMera Scientific Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.56831/psen-09-299","doi":"https://doi.org/10.56831/psen-09-299","is_oa":true,"landing_page_url":"https://doi.org/10.56831/psen-09-299","pdf_url":"https://doi.org/10.56831/psen-09-299","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PriMera Scientific Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Clean water and sanitation","score":0.6618000268936157,"id":"https://metadata.un.org/sdg/6"},{"display_name":"Climate action","score":0.5351999998092651,"id":"https://metadata.un.org/sdg/13"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224090789.pdf","grobid_xml":"https://content.openalex.org/works/W7224090789.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W2965373594","https://openalex.org/W3111356309","https://openalex.org/W4327810158"],"related_works":["https://openalex.org/W4412391220","https://openalex.org/W2998686570","https://openalex.org/W7215787750","https://openalex.org/W7201913182","https://openalex.org/W4416132502","https://openalex.org/W4410886976","https://openalex.org/W7125016744","https://openalex.org/W7215367958","https://openalex.org/W7166854667","https://openalex.org/W7148559374"],"abstract_inverted_index":{"Traditional":[0],"pollution":[1,42,134],"source":[2,43,135],"attribution":[3],"relies":[4],"on":[5,69],"expensive":[6],"chemical":[7],"speciation":[8],"and":[9,56,127],"handcrafted":[10],"statistical":[11],"models":[12],"that":[13,31,75,96],"cannot":[14],"leverage":[15],"the":[16,119,129],"rich":[17],"semantic":[18,47,98],"information":[19],"embedded":[20],"in":[21,103],"environmental":[22,61,115,125],"monitoring":[23,72,126],"metadata.We":[24],"present":[25],"EnhancedPollutionAttributorWithLLMs,":[26],"a":[27],"novel":[28],"multimodal":[29],"framework":[30],"integrates":[32],"Large":[33],"Language":[34],"Models":[35],"with":[36,59,78],"advanced":[37],"neural":[38],"architectures":[39],"for":[40,114,123,131],"automated":[41],"attribution.Our":[44],"approach":[45],"extracts":[46],"features":[48,80,99],"from":[49],"EPA":[50,71],"Air":[51],"Quality":[52],"System":[53],"site":[54],"descriptions":[55],"combines":[57],"them":[58],"spatiotemporal":[60],"data":[62],"using":[63,109],"rigorous":[64],"geographic":[65],"holdout":[66],"validation.Experimental":[67],"evaluation":[68],"3,899":[70],"records":[73],"demonstrates":[74,128],"Vision":[76],"Transformer":[77],"LLM-enhanced":[79,124],"achieves":[81],"exceptional":[82],"performance":[83],"(R\u00b2":[84],"=":[85,88],"0.9969,":[86],"RMSE":[87],"0.3116),":[89],"significantly":[90],"outperforming":[91],"traditional":[92],"approaches.Ablation":[93],"studies":[94],"reveal":[95],"LLM-derived":[97],"contribute":[100],"1.2%":[101],"improvement":[102],"R\u00b2,":[104],"while":[105],"comprehensive":[106],"interpretability":[107],"analysis":[108],"SHAP":[110],"provides":[111],"actionable":[112],"insights":[113],"policy.This":[116],"work":[117],"establishes":[118],"first":[120],"reproducible":[121],"benchmark":[122],"potential":[130],"automated,":[132],"large-scale":[133],"attribution.":[136]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-29T00:00:00"}