{"id":"https://openalex.org/W7138896889","doi":"https://doi.org/10.1016/j.asoc.2026.115061","title":"Real-time weather-adaptive water flow and leakage forecasting using an explainable unified deep neural network","display_name":"Real-time weather-adaptive water flow and leakage forecasting using an explainable unified deep neural network","publication_year":2026,"publication_date":"2026-03-19","ids":{"openalex":"https://openalex.org/W7138896889","doi":"https://doi.org/10.1016/j.asoc.2026.115061"},"language":"en","primary_location":{"id":"doi:10.1016/j.asoc.2026.115061","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.asoc.2026.115061","pdf_url":null,"source":{"id":"https://openalex.org/S140556538","display_name":"Applied Soft Computing","issn_l":"1568-4946","issn":["1568-4946","1872-9681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Soft Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.asoc.2026.115061","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018214951","display_name":"Jawad Fayaz","orcid":"https://orcid.org/0000-0003-4706-9761"},"institutions":[{"id":"https://openalex.org/I23923803","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09","country_code":"GB","type":"education","lineage":["https://openalex.org/I23923803"]},{"id":"https://openalex.org/I4210117296","display_name":"Institute of Health Visiting","ror":"https://ror.org/01p894e02","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I4210117296"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jawad Fayaz","raw_affiliation_strings":["Department of Computer Science, University of Exeter, Exeter, UK","Visiting Academic, UKCRIC Limited, London, UK"],"raw_orcid":"https://orcid.org/0000-0003-4706-9761","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Exeter, Exeter, UK","institution_ids":["https://openalex.org/I23923803"]},{"raw_affiliation_string":"Visiting Academic, UKCRIC Limited, London, UK","institution_ids":["https://openalex.org/I4210117296"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052274658","display_name":"Lauren McMillan","orcid":"https://orcid.org/0000-0003-3851-8019"},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]},{"id":"https://openalex.org/I4210117296","display_name":"Institute of Health Visiting","ror":"https://ror.org/01p894e02","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I4210117296"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lauren McMillan","raw_affiliation_strings":["School of Engineering, Physics and Mathematics, Northumbria University, Newcastle, UK","Visiting Academic, UKCRIC Limited, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Physics and Mathematics, Northumbria University, Newcastle, UK","institution_ids":["https://openalex.org/I32394136"]},{"raw_affiliation_string":"Visiting Academic, UKCRIC Limited, London, UK","institution_ids":["https://openalex.org/I4210117296"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108503473","display_name":"Vivian C\u00e1rdenas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130156","display_name":"World Cancer Research Fund UK","ror":"https://ror.org/02gc7qc02","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210114307","https://openalex.org/I4210130156"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vivian Cardenas","raw_affiliation_strings":["Department of Civil, Environmental, and Geomatic Engineering, University College London (UCL), UK","UKCRIC Limited, London, UK"],"raw_orcid":"https://orcid.org/0009-0006-3225-3354","affiliations":[{"raw_affiliation_string":"Department of Civil, Environmental, and Geomatic Engineering, University College London (UCL), UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"UKCRIC Limited, London, UK","institution_ids":["https://openalex.org/I4210130156"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130052079","display_name":"Liz Varga","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130156","display_name":"World Cancer Research Fund UK","ror":"https://ror.org/02gc7qc02","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210114307","https://openalex.org/I4210130156"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Liz Varga","raw_affiliation_strings":["Department of Civil, Environmental, and Geomatic Engineering, Infrastructure Systems Institute, University College London (UCL), UK","UKCRIC Limited, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Civil, Environmental, and Geomatic Engineering, Infrastructure Systems Institute, University College London (UCL), UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"UKCRIC Limited, London, UK","institution_ids":["https://openalex.org/I4210130156"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018214951"],"corresponding_institution_ids":["https://openalex.org/I23923803","https://openalex.org/I4210117296"],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":{"value":3350,"currency":"USD","value_usd":3350},"fwci":3.5492,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90795385,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"195","issue":null,"first_page":"115061","last_page":"115061"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11220","display_name":"Water Systems and Optimization","score":0.9549000263214111,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"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/T11220","display_name":"Water Systems and Optimization","score":0.9549000263214111,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"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/T10930","display_name":"Flood Risk Assessment and Management","score":0.006800000090152025,"subfield":{"id":"https://openalex.org/subfields/2306","display_name":"Global and Planetary Change"},"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/T11807","display_name":"Infrastructure Resilience and Vulnerability Analysis","score":0.003000000026077032,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"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/robustness","display_name":"Robustness (evolution)","score":0.6287000179290771},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6000999808311462},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49900001287460327},{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.4668999910354614},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42089998722076416},{"id":"https://openalex.org/keywords/water-flow","display_name":"Water flow","score":0.3919999897480011},{"id":"https://openalex.org/keywords/false-positive-rate","display_name":"False positive rate","score":0.38690000772476196},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6535999774932861},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6287000179290771},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6000999808311462},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C2988574769","wikidata":"https://www.wikidata.org/wiki/Q2259545","display_name":"Water flow","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3873000144958496},{"id":"https://openalex.org/C95922358","wikidata":"https://www.wikidata.org/wiki/Q5432725","display_name":"False positive rate","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.34529998898506165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C153823671","wikidata":"https://www.wikidata.org/wiki/Q1049799","display_name":"Water resources","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2780378346","wikidata":"https://www.wikidata.org/wiki/Q1349983","display_name":"Leak","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.32280001044273376},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.299699991941452},{"id":"https://openalex.org/C172120300","wikidata":"https://www.wikidata.org/wiki/Q1134348","display_name":"Volumetric flow rate","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C135510737","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance indicator","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C105306849","wikidata":"https://www.wikidata.org/wiki/Q81054","display_name":"Storm","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.asoc.2026.115061","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.asoc.2026.115061","pdf_url":null,"source":{"id":"https://openalex.org/S140556538","display_name":"Applied Soft Computing","issn_l":"1568-4946","issn":["1568-4946","1872-9681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Soft Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.asoc.2026.115061","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.asoc.2026.115061","pdf_url":null,"source":{"id":"https://openalex.org/S140556538","display_name":"Applied Soft Computing","issn_l":"1568-4946","issn":["1568-4946","1872-9681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Soft Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.5790300965309143}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320275","display_name":"University of Exeter","ror":"https://ror.org/03yghzc09"},{"id":"https://openalex.org/F4320320310","display_name":"National Endowment for Science Technology and the Arts","ror":"https://ror.org/02rqc5533"},{"id":"https://openalex.org/F7705544900","display_name":"Department for Science, Innovation and Technology","ror":"https://ror.org/028z36n30"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1258423074","https://openalex.org/W1510386221","https://openalex.org/W1982494603","https://openalex.org/W1986113717","https://openalex.org/W1990606395","https://openalex.org/W1991429615","https://openalex.org/W1995443851","https://openalex.org/W2008868646","https://openalex.org/W2016722587","https://openalex.org/W2025518472","https://openalex.org/W2044606383","https://openalex.org/W2050692164","https://openalex.org/W2052306804","https://openalex.org/W2069143585","https://openalex.org/W2074299896","https://openalex.org/W2076751630","https://openalex.org/W2113952909","https://openalex.org/W2125848133","https://openalex.org/W2142635246","https://openalex.org/W2146574767","https://openalex.org/W2148608678","https://openalex.org/W2171901943","https://openalex.org/W2296719434","https://openalex.org/W2322728333","https://openalex.org/W2326425082","https://openalex.org/W2612634788","https://openalex.org/W2767035496","https://openalex.org/W2801354606","https://openalex.org/W2903101325","https://openalex.org/W2903940442","https://openalex.org/W2911964244","https://openalex.org/W2955863859","https://openalex.org/W2965502148","https://openalex.org/W3021781416","https://openalex.org/W3033450399","https://openalex.org/W3103467282","https://openalex.org/W3109795660","https://openalex.org/W3130963780","https://openalex.org/W3174560814","https://openalex.org/W3206462402","https://openalex.org/W3211739873","https://openalex.org/W4200032871","https://openalex.org/W4221052882","https://openalex.org/W4223594669","https://openalex.org/W4283021405","https://openalex.org/W4283452708","https://openalex.org/W4288738995","https://openalex.org/W4366778955","https://openalex.org/W4367016885","https://openalex.org/W4381571905","https://openalex.org/W4381848566","https://openalex.org/W4386142022","https://openalex.org/W4386640160","https://openalex.org/W4388281482","https://openalex.org/W4389390104","https://openalex.org/W4395049097","https://openalex.org/W4396946432","https://openalex.org/W4399731855","https://openalex.org/W4401020226","https://openalex.org/W4401870955","https://openalex.org/W4405190399","https://openalex.org/W4407597486"],"related_works":[],"abstract_inverted_index":{"Leakage":[0],"in":[1,28,127,257,312,366,411,431],"water":[2,16,66,169,182,300,308,336,456],"distribution":[3,79],"systems":[4],"worldwide":[5],"has":[6],"an":[7],"estimated":[8],"annual":[9,307],"cost":[10],"of":[11,78,167,198,224,239,249,255,276,346,400,422,429],"$7":[12],"billion":[13],"and":[14,33,42,69,110,135,139,148,160,171,187,209,215,245,251,274,315,338,348,375,382,387,408,413,424,459,470],"threatens":[15],"security":[17],"amid":[18],"growing":[19],"climate":[20],"pressures.":[21],"Traditional":[22],"leakage":[23,129,188,341,360,407,432,471],"management":[24,318],"approaches":[25,84],"are":[26,201,462],"reactive":[27],"their":[29],"approach,":[30],"wasting":[31],"time":[32],"resources.":[34],"This":[35],"study":[36],"introduces":[37],"FLOWAID":[38,81,230,298,325,416],"(":[39],"f":[40,45],"low":[41],"l":[43],"eakage":[44],"o":[46],"recasting":[47],"using":[48,343],"w":[49],"eather-":[50],"a":[51,60,90,118,232,327,418,425],"daptive":[52],"neural":[53],"network":[54],"for":[55,97,107,114,190,221,242,405],"i":[56],"ntelligent":[57],"d":[58],"ecision-making),":[59],"deep":[61,329],"learning":[62,294,330],"framework":[63,439],"that":[64,122,332,454],"unifies":[65],"flow":[67,170,185,228,243,347,395,469],"forecasting":[68,244,396],"proactive":[70],"leak":[71,136,258,279],"detection":[72,137,259,280],"to":[73,157,180,305,320,358],"enable":[74],"continuous,":[75],"time-agnostic":[76],"monitoring":[77],"networks.":[80],"advances":[82],"existing":[83],"through":[85],"three":[86],"key":[87,204],"innovations:":[88],"(1)":[89],"hybrid":[91],"architecture":[92],"combining":[93],"convolutional":[94],"residual":[95],"networks":[96],"spatial":[98],"weather-flow":[99],"dependency":[100],"extraction,":[101],"bidirectional":[102],"long":[103],"short-term":[104],"memory":[105],"cells":[106],"temporal":[108],"modelling,":[109],"multi-task":[111],"multi-layer":[112],"perceptrons":[113],"simultaneous":[115],"predictions;":[116],"(2)":[117],"class-specific":[119,353],"attention":[120,354],"mechanism":[121,355],"amplifies":[123],"critical":[124,364],"leakage-related":[125],"features":[126,365,466],"underrepresented":[128,367],"class,":[130],"improving":[131],"the":[132,191,463],"model\u2019s":[133],"sensitivity":[134,357],"performance;":[138],"(3)":[140],"adaptive":[141,372],"novel":[142,371],"loss":[143,147,374],"functions":[144,379],"(adaptive":[145],"Huber":[146,373],"weighted":[149,376],"binary":[150,377],"cross-entropy)":[151],"paired":[152],"with":[153,236,295,302,398],"Shapley":[154],"additive":[155],"explanations":[156],"ensure":[158],"robustness":[159],"transparency.":[161],"The":[162,263,391,438],"model":[163,264,331,392],"processes":[164],"five":[165,344],"days":[166,345],"historical":[168],"weather":[172,196,270,322,349],"data":[173],"from":[174],"over":[175,222,441],"2000":[176],"district":[177],"metered":[178],"areas":[179],"predict":[181],"demand":[183,337],"(i.e.,":[184],"rate)":[186],"probability":[189,342],"subsequent":[192],"12":[193],"hours.":[194],"Six":[195],"variables":[197],"ten":[199],"analysed,":[200],"identified":[202],"as":[203],"predictors":[205],"-":[206,217],"temperature,":[207,458],"specific":[208,460],"relative":[210],"humidity,":[211],"solar":[212],"radiation,":[213],"evaporation,":[214],"precipitation":[216],"which":[218],"collectively":[219],"account":[220],"90%":[223,442],"environmental":[225],"influence":[226],"on":[227,434],"behavior.":[229],"achieves":[231,393,417],"good":[233],"predictive":[234],"performance":[235,384],"average":[237],"index":[238,399],"agreement":[240,401],"~0.7":[241],"true":[246,252,419,426],"positive":[247,420],"rate":[248,254,421,428],"88.2%":[250],"negative":[253,427],"99.2%":[256],"across":[260,268],"imbalanced":[261,386],"datasets.":[262],"maintains":[265,440],"consistent":[266],"accuracy":[267,397,443],"diverse":[269],"conditions,":[271],"seasonal":[272],"variations,":[273],"times":[275],"day,":[277],"enabling":[278],"at":[281],"any":[282],"hour":[283],"rather":[284],"than":[285],"only":[286],"during":[287],"nighttime":[288],"periods.":[289],"By":[290],"integrating":[291],"interpretable":[292],"machine":[293],"weather-adaptive":[296],"forecasting,":[297],"provides":[299],"utilities":[301],"actionable":[303],"tools":[304],"reduce":[306],"losses,":[309],"prioritize":[310],"repairs":[311],"high-risk":[313],"zones,":[314],"adapt":[316],"infrastructure":[317],"strategies":[319],"climate-driven":[321],"extremes.":[323],"\u2022":[324,351,369,390,415,450],"is":[326],"unified":[328],"simultaneously":[333],"forecasts":[334],"12-hour":[335],"predicts":[339],"future":[340],"data.":[350,437],"A":[352,370],"improves":[356],"rare":[359],"events":[361],"by":[362],"emphasizing":[363],"classes.":[368],"cross-entropy":[378],"improve":[380],"regression":[381],"classification":[383],"under":[385,445],"zero-padded":[388],"conditions.":[389],"high":[394],"values":[402],"averaging":[403],"~0.75":[404],"both":[406,468],"non-leakage":[409],"cases":[410],"training":[412],"testing.":[414],"96.7%":[423],"95.9%":[430],"prediction":[433],"unseen":[435],"test":[436],"even":[444],"extreme":[446],"class":[447],"imbalance":[448],"scenarios.":[449],"SHAP-based":[451],"explainability":[452],"reveals":[453],"previous-day":[455],"flow,":[457],"humidity":[461],"most":[464],"influential":[465],"driving":[467],"predictions.":[472]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2026-03-20T00:00:00"}