{"id":"https://openalex.org/W7202042467","doi":"https://doi.org/10.2118/234916-ms","title":"A Hybrid CNN\u2013Vision Language Model Framework for Visual Fire Detection and Context-Aware Decision Support in Oil and Gas Facilities","display_name":"A Hybrid CNN\u2013Vision Language Model Framework for Visual Fire Detection and Context-Aware Decision Support in Oil and Gas Facilities","alternate_titles":[],"publication_year":2026,"publication_date":"2026-08-10","ids":{"openalex":"https://openalex.org/W7202042467","doi":"https://doi.org/10.2118/234916-ms"},"language":"en","primary_location":{"id":"doi:10.2118/234916-ms","doi":"https://doi.org/10.2118/234916-ms","is_oa":false,"landing_page_url":"https://doi.org/10.2118/234916-ms","pdf_url":null,"source":{"id":"https://openalex.org/S4306530696","display_name":"SPE Nigeria Annual International Conference and Exhibition","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4322614974","host_organization_name":"Society of Petroleum Engineers","host_organization_lineage":["https://openalex.org/P4322614974"],"host_organization_lineage_names":["Society of Petroleum Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPE Nigeria Annual International Conference and Exhibition","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W7202042467"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5146208043","display_name":"E. C. Ashinze","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197610006","display_name":"University of Lagos","ror":"https://ror.org/05rk03822","country_code":"NG","type":"education","lineage":["https://openalex.org/I197610006"]}],"countries":["NG"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"E. C. Ashinze","raw_affiliation_strings":["Department of Chemical Engineering, University of Lagos, Lagos, Nigeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, University of Lagos, Lagos, Nigeria","institution_ids":["https://openalex.org/I197610006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5146215810","display_name":"E. P. Okoneyo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197610006","display_name":"University of Lagos","ror":"https://ror.org/05rk03822","country_code":"NG","type":"education","lineage":["https://openalex.org/I197610006"]}],"countries":["NG"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"E. P. Okoneyo","raw_affiliation_strings":["Department of Chemical Engineering, University of Lagos, Lagos, Nigeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, University of Lagos, Lagos, Nigeria","institution_ids":["https://openalex.org/I197610006"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197610006"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"reviewed_by_count":0,"citation_normalized_percentile":{"value":0.0,"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_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12597","display_name":"Fire Detection and Safety Systems","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12597","display_name":"Fire Detection and Safety Systems","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0008999999845400453,"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/T11317","display_name":"Fire dynamics and safety research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fire-detection","display_name":"fire detection","score":0.8799999952316284},{"id":"https://openalex.org/keywords/smoke-detection","display_name":"smoke detection","score":0.9829999804496765},{"id":"https://openalex.org/keywords/oil-and-gas-facilities","display_name":"oil and gas facilities","score":0.9739999771118164},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7919999957084656},{"id":"https://openalex.org/keywords/yolo26","display_name":"YOLO26","score":0.8190000057220459},{"id":"https://openalex.org/keywords/emergency-decision-support","display_name":"emergency decision support","score":0.6669999957084656},{"id":"https://openalex.org/keywords/real-time-video-surveillance","display_name":"real-time video surveillance","score":0.8190000057220459},{"id":"https://openalex.org/keywords/fire-and-explosion-prevention","display_name":"fire and explosion prevention","score":0.5019999742507935},{"id":"https://openalex.org/keywords/pipeline-vandalism","display_name":"pipeline vandalism","score":0.36800000071525574},{"id":"https://openalex.org/keywords/flare-detection","display_name":"flare detection","score":0.32100000977516174},{"id":"https://openalex.org/keywords/false-alarm-reduction","display_name":"false alarm reduction","score":0.5659999847412109}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5920000076293945},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5687999725341797},{"id":"https://openalex.org/C2780836893","wikidata":"https://www.wikidata.org/wiki/Q19922674","display_name":"Fire detection","level":2,"score":0.5620999932289124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5371000170707703},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42820000648498535},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C58874564","wikidata":"https://www.wikidata.org/wiki/Q130768","display_name":"Smoke","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3398999869823456},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C66862320","wikidata":"https://www.wikidata.org/wiki/Q842017","display_name":"Building information modeling","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2590000033378601},{"id":"https://openalex.org/C149271511","wikidata":"https://www.wikidata.org/wiki/Q1417149","display_name":"Rule-based system","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2982912361","wikidata":"https://www.wikidata.org/wiki/Q1851867","display_name":"Mental model","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2118/234916-ms","doi":"https://doi.org/10.2118/234916-ms","is_oa":false,"landing_page_url":"https://doi.org/10.2118/234916-ms","pdf_url":null,"source":{"id":"https://openalex.org/S4306530696","display_name":"SPE Nigeria Annual International Conference and Exhibition","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4322614974","host_organization_name":"Society of Petroleum Engineers","host_organization_lineage":["https://openalex.org/P4322614974"],"host_organization_lineage_names":["Society of Petroleum Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SPE Nigeria Annual International Conference and Exhibition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W3185987447","https://openalex.org/W4385342336","https://openalex.org/W4394748062","https://openalex.org/W4399361386","https://openalex.org/W4401349720","https://openalex.org/W4404303854","https://openalex.org/W4404734233","https://openalex.org/W4406127891","https://openalex.org/W4406324697","https://openalex.org/W4406964611","https://openalex.org/W4408481045","https://openalex.org/W4413381334","https://openalex.org/W4414037437","https://openalex.org/W4414392371","https://openalex.org/W4415154570","https://openalex.org/W6967723214"],"related_works":["https://openalex.org/W4408112786","https://openalex.org/W7134174755","https://openalex.org/W4309684427","https://openalex.org/W4404772570","https://openalex.org/W4412752957","https://openalex.org/W4399179308","https://openalex.org/W3134378827","https://openalex.org/W4285334023","https://openalex.org/W4388538758"],"abstract_inverted_index":{"In":[0,75,126],"Nigeria's":[1],"oil":[2,156,415],"and":[3,7,30,68,89,107,143,157,181,192,197,232,238,283,290,293,309,324,341,344,356,372,379,391,416,439],"gas":[4,158,417],"industry,":[5,363],"fire":[6,67,142,204,236,278,354,371,389,419],"explosion":[8],"incidents":[9],"have":[10,48],"claimed":[11],"more":[12],"than":[13],"3,400":[14],"lives":[15],"over":[16],"the":[17,63,66,69,76,78,93,96,153,167,179,190,198,255,306,310,318,350,361,367,385,404,441],"last":[18],"15":[19],"years,":[20],"which":[21,134,175,253],"are":[22,42,90,246],"fueled":[23],"by":[24],"old":[25],"infrastructure,":[26,270,317],"chronic":[27],"pipeline":[28,320,331],"vandalism":[29],"lack":[31,59],"of":[32,40,65,86,95,122,155,163,184,210,230,301,369],"intelligent":[33],"real":[34,445],"time":[35],"monitoring.":[36,160],"Traditional":[37],"sensor-based":[38],"systems":[39],"detection":[41,164,355,374,390],"limited":[43],"in":[44,53,120,152,366,396,403,444],"their":[45],"spatial":[46],"coverage,":[47],"a":[49,129,136,147,221,243,249,258,335,380],"high":[50,87,104],"false-alarming":[51],"rate":[52],"flare-rich":[54],"conditions,":[55],"and,":[56],"most":[57],"importantly,":[58],"contextual":[60,149,250],"information":[61],"concerning":[62],"severity":[64,279],"emergency":[70,296],"response":[71,397],"that":[72,116,383],"is":[73,113,132,176,321],"advisable.":[74],"meantime,":[77],"state-of-the-art":[79],"detectors,":[80],"based":[81],"on":[82,166,178,215,220,268,315,375,412],"deep":[83],"learning,":[84],"boast":[85],"localization":[88],"blind":[91],"to":[92,248,271,360,398,425],"context":[94,154],"scenes,":[97],"whereas":[98],"Vision":[99,262],"Language":[100,263],"Models":[101],"(VLMs)":[102],"show":[103],"scene":[105],"reasoning":[106,150,251,312],"cannot":[108],"support":[109],"real-time":[110,141,339],"alerting.":[111],"There":[112],"no":[114],"system":[115,443],"combines":[117,135],"these":[118],"capabilities":[119],"terms":[121],"petroleum":[123,362,435],"facility":[124,418,429],"safety.":[125],"this":[127],"paper,":[128],"hybrid":[130],"model":[131,432],"introduced,":[133],"Convolutional":[137],"Neural":[138],"Network":[139],"(CNN)-based":[140],"smoke":[144,239,281,373],"detector":[145,308],"with":[146,422],"Vlm-based":[148],"layer,":[151],"facilities":[159],"The":[161,329],"stage":[162],"relies":[165],"YOLO26s":[168,219],"architecture":[169,382],"(9.95":[170],"million":[171],"parameters,":[172],"22.5":[173],"GFLOPs)":[174],"trained":[177],"combined":[180],"quality-controlled":[182],"dataset":[183],"30,337":[185],"annotated":[186],"images":[187],"obtained":[188],"using":[189],"Fire":[191],"Smoke":[193],"Detection":[194],"Dataset":[195],"(FASDD)":[196],"Middle":[199],"East":[200],"Technical":[201],"University":[202],"(METU)":[203],"dataset.":[205],"At":[206],"an":[207,216],"inference":[208,327],"latency":[209],"0.5":[211],"ms":[212],"per":[213],"frame":[214,302],"NVIDIA":[217,256],"A100,":[218],"validation":[222],"set":[223],"reached":[224],"mean":[225],"Average":[226],"Precision":[227],"(mAP":[228],"50)":[229],"83.4%":[231],"balanced":[233],"per-class":[234],"performance,":[235],"(83.4)":[237],"(83.3).":[240],"Frames":[241],"meeting":[242],"confidence":[244],"threshold":[245],"sent":[247],"stage,":[252],"uses":[254],"DAM-3B,":[257],"fully":[259],"open-source,":[260],"3-billion-parameter":[261],"Model":[264],"(VLM)":[265],"hosted":[266],"entirely":[267],"local":[269,423],"produce":[272],"structured,":[273],"natural-language":[274],"safety":[275,393,436],"reports,":[276],"including":[277],"classification,":[280],"density":[282],"combustion":[284],"completeness":[285],"analysis,":[286,289],"infrastructure":[287],"proximity":[288],"Health,":[291],"Safety":[292],"Environment":[294],"(HSE)-consistent":[295],"advice":[297],"within":[298],"2\u20133":[299],"seconds":[300],"capture.":[303],"Because":[304],"both":[305],"CNN":[307],"VLM":[311,345],"layer":[313],"run":[314],"self-hosted":[316],"end-to-end":[319,352],"highly":[322],"cost-effective":[323],"delivers":[325],"near-instantaneous":[326],"speeds.":[328],"entire":[330],"was":[332],"implemented":[333],"as":[334,401],"web":[336],"application":[337],"supporting":[338],"image":[340],"video":[342],"analysis":[343],"reporting.":[346],"This":[347],"paper":[348],"provides":[349],"first":[351],"CNN-VLM":[353],"decision-support":[357],"framework":[358],"specialised":[359],"quantitative":[364],"benchmarks":[365],"use":[368],"YOLO26-based":[370],"fused":[376],"industrial":[377],"data,":[378,420],"deployable":[381],"closes":[384],"gap":[386],"between":[387],"automated":[388],"human-explainable":[392],"intelligence,":[394],"directly":[395],"regulatory":[399],"requirements":[400],"stipulated":[402],"Petroleum":[405],"Industry":[406],"Act":[407],"2021.":[408],"Future":[409],"work":[410],"focuses":[411],"collecting":[413],"Nigerian":[414,428],"collaborating":[421],"operators":[424],"incorporate":[426],"localized":[427],"imagery,":[430],"validating":[431],"outputs":[433],"against":[434],"expert":[437],"consensus,":[438],"testing":[440],"full":[442],"operational":[446],"environments.":[447]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7202042467","counts_by_year":[],"updated_date":"2026-11-21T10:27:49.728292","created_date":"2026-08-10T00:00:00"}
