{"id":"https://openalex.org/W7236432007","doi":"https://doi.org/10.1371/journal.pone.0363128","title":"LightTeaNet: SeparableConv-based lightweight CNN with Grad-CAM explainability for tea leaf disease identification","display_name":"LightTeaNet: SeparableConv-based lightweight CNN with Grad-CAM explainability for tea leaf disease identification","alternate_titles":[],"publication_year":2026,"publication_date":"2026-11-18","ids":{"openalex":"https://openalex.org/W7236432007","doi":"https://doi.org/10.1371/journal.pone.0363128"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pone.0363128","doi":"https://doi.org/10.1371/journal.pone.0363128","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0363128","pdf_url":null,"source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS One","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W7236432007"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1371/journal.pone.0363128","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5162712816","display_name":"Md Rifat Sarker","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256839","display_name":"Mymensingh Engineering College","ror":"https://ror.org/04k7exg05","country_code":"BD","type":"education","lineage":["https://openalex.org/I4405256839"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md Rifat Sarker","raw_affiliation_strings":["Mymensingh Engineering College, Mymensingh, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mymensingh Engineering College, Mymensingh, Bangladesh","institution_ids":["https://openalex.org/I4405256839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117758237","display_name":"Jonayed Al-Faruk","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256839","display_name":"Mymensingh Engineering College","ror":"https://ror.org/04k7exg05","country_code":"BD","type":"education","lineage":["https://openalex.org/I4405256839"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Jonayed Al-Faruk","raw_affiliation_strings":["Mymensingh Engineering College, Mymensingh, Bangladesh"],"raw_orcid":"https://orcid.org/0009-0004-5291-0855","affiliations":[{"raw_affiliation_string":"Mymensingh Engineering College, Mymensingh, Bangladesh","institution_ids":["https://openalex.org/I4405256839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5162765008","display_name":"Kaniz Fatema","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256839","display_name":"Mymensingh Engineering College","ror":"https://ror.org/04k7exg05","country_code":"BD","type":"education","lineage":["https://openalex.org/I4405256839"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Kaniz Fatema","raw_affiliation_strings":["Mymensingh Engineering College, Mymensingh, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mymensingh Engineering College, Mymensingh, Bangladesh","institution_ids":["https://openalex.org/I4405256839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113681618","display_name":"Joyonta Das","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256839","display_name":"Mymensingh Engineering College","ror":"https://ror.org/04k7exg05","country_code":"BD","type":"education","lineage":["https://openalex.org/I4405256839"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Joyonta Das","raw_affiliation_strings":["Mymensingh Engineering College, Mymensingh, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mymensingh Engineering College, Mymensingh, Bangladesh","institution_ids":["https://openalex.org/I4405256839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5162715464","display_name":"Md. Shahabuddin Saju","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256839","display_name":"Mymensingh Engineering College","ror":"https://ror.org/04k7exg05","country_code":"BD","type":"education","lineage":["https://openalex.org/I4405256839"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md. Shahabuddin Saju","raw_affiliation_strings":["Mymensingh Engineering College, Mymensingh, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mymensingh Engineering College, Mymensingh, Bangladesh","institution_ids":["https://openalex.org/I4405256839"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081097938","display_name":"Ozifatun Jannat Akhi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405256839","display_name":"Mymensingh Engineering College","ror":"https://ror.org/04k7exg05","country_code":"BD","type":"education","lineage":["https://openalex.org/I4405256839"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Ozifatun Jannat Akhi","raw_affiliation_strings":["Mymensingh Engineering College, Mymensingh, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mymensingh Engineering College, Mymensingh, Bangladesh","institution_ids":["https://openalex.org/I4405256839"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405256839"],"apc_list":{"value":2382,"currency":"USD","value_usd":2382},"apc_paid":{"value":2382,"currency":"USD","value_usd":2382},"fwci":0.0,"has_fulltext":false,"cited_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":"21","issue":"11","first_page":"e0363128","last_page":"e0363128"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10616","display_name":"Smart Agriculture and AI","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10616","display_name":"Smart Agriculture and AI","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.006300000008195639,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7111999988555908},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6388999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5968000292778015},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5824999809265137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5767999887466431},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.36550000309944153},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3125},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.29499998688697815},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1371/journal.pone.0363128","doi":"https://doi.org/10.1371/journal.pone.0363128","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0363128","pdf_url":null,"source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS One","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1371/journal.pone.0363128","doi":"https://doi.org/10.1371/journal.pone.0363128","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0363128","pdf_url":null,"source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS One","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2962858109","https://openalex.org/W2966086598","https://openalex.org/W3137947626","https://openalex.org/W4391789614","https://openalex.org/W4392141791","https://openalex.org/W4393045549","https://openalex.org/W4393142434","https://openalex.org/W4393932480","https://openalex.org/W4394565371","https://openalex.org/W4396552855","https://openalex.org/W4398236587","https://openalex.org/W4399766518","https://openalex.org/W4400013939","https://openalex.org/W4401083100","https://openalex.org/W4401548825","https://openalex.org/W4402933663","https://openalex.org/W4402994936","https://openalex.org/W4404506518","https://openalex.org/W4404912936","https://openalex.org/W4405594810","https://openalex.org/W4406812021","https://openalex.org/W4407230547","https://openalex.org/W4409607242","https://openalex.org/W4410130400","https://openalex.org/W4410573838","https://openalex.org/W4410766829","https://openalex.org/W4413401717","https://openalex.org/W4414437109","https://openalex.org/W7128088011","https://openalex.org/W7162690661","https://openalex.org/W7169044397"],"related_works":[],"abstract_inverted_index":{"Global":[0,94],"tea":[1,52,275],"production,":[2],"valued":[3],"at":[4],"USD":[5],"25.6":[6],"billion":[7],"in":[8,278],"2024,":[9],"faces":[10],"annual":[11],"yield":[12],"losses":[13],"of":[14,142,168,179,300],"approximately":[15,152],"20%":[16],"due":[17,32],"to":[18,33,100,135,296],"foliar":[19],"diseases,":[20],"yet":[21],"existing":[22],"deep":[23],"learning-based":[24],"detection":[25],"systems":[26],"remain":[27],"impractical":[28],"for":[29,50,181,214,251,273],"real-world":[30],"deployment":[31,299],"prohibitive":[34],"computational":[35,75,246],"requirements":[36],"and":[37,63,74,97,175,192,226,242,286,310],"limited":[38],"interpretability.":[39],"This":[40],"paper":[41],"presents":[42],"a":[43,131,139,270],"purpose-built":[44],"lightweight":[45],"convolutional":[46],"neural":[47],"network":[48],"architecture":[49,261],"four-class":[51],"leaf":[53,208],"disease":[54,276,289],"classification":[55,72,124],"(Brown":[56],"Blight,":[57],"Red":[58,60],"Rust,":[59],"Spider":[61],"Mite,":[62],"Healthy":[64],"Leaves)":[65],"that":[66,199,228],"achieves":[67,122,231],"an":[68],"exceptional":[69],"balance":[70],"between":[71],"accuracy":[73,125,234],"efficiency.":[76],"The":[77,160,254],"proposed":[78,255],"model":[79,121,140,161,211],"leverages":[80],"depthwise":[81],"separable":[82],"convolutions":[83],"across":[84,117,172],"four":[85,118],"progressive":[86],"feature":[87,107],"extraction":[88],"blocks,":[89],"integrated":[90],"with":[91,126,166,266],"Batch":[92],"Normalization,":[93],"Average":[95],"Pooling,":[96],"Dropout":[98],"regularization":[99],"minimize":[101],"parameter":[102],"count":[103],"while":[104,146,229],"maintaining":[105],"discriminative":[106],"learning.":[108],"Evaluated":[109],"on":[110,304],"the":[111,120,200,258,297],"TeaLeafNet":[112],"dataset":[113],"(5,000":[114],"balanced":[115],"images":[116],"categories),":[119],"98.14%":[123],"only":[127,148],"80,959":[128],"trainable":[129],"parameters\u2014representing":[130],"90-fold":[132],"reduction":[133],"compared":[134],"DenseNet121":[136,230],"(7.3M":[137],"parameters)\u2014and":[138],"size":[141],"merely":[143],"0.31":[144],"MB,":[145],"requiring":[147],"191.29":[149],"million":[150],"FLOPs,":[151],"160":[153],"\u00d7":[154,239,244],"fewer":[155],"than":[156],"VGG16":[157],"(30.71B":[158],"FLOPs).":[159],"demonstrates":[162],"robust":[163],"per-class":[164],"performance":[165],"F1-scores":[167],"0.97":[169],"or":[170],"higher":[171,233],"all":[173,263],"categories":[174],"perfect":[176],"ROC-AUC":[177],"values":[178],"1.000":[180],"two":[182],"classes.":[183],"Grad-CAM":[184],"visualization,":[185],"validated":[186],"through":[187],"quantitative":[188],"Insertion":[189],"(AUC:":[190,194],"0.972)":[191],"Deletion":[193],"0.181)":[195],"faithfulness":[196],"evaluation,":[197],"confirms":[198],"model\u2019s":[201],"predictions":[202],"are":[203],"driven":[204],"by":[205],"diagnostically":[206],"relevant":[207],"regions,":[209],"achieving":[210],"transparency":[212],"essential":[213],"agricultural":[215,312],"adoption.":[216],"Comparative":[217],"analysis":[218],"against":[219],"nine":[220],"state-of-the-art":[221],"architectures\u2014including":[222],"DenseNet121,":[223],"MobileNetV2,":[224],"ResNet50,":[225],"EfficientNetB1\u2014reveals":[227],"marginally":[232],"(99.20%),":[235],"it":[236,249],"requires":[237],"90":[238],"more":[240,245],"parameters":[241],"30":[243],"operations,":[247],"rendering":[248],"unsuitable":[250],"edge":[252],"deployment.":[253],"framework":[256],"offers":[257],"most":[259],"compact":[260],"among":[262],"evaluated":[264],"models":[265],"competitive":[267],"accuracy,":[268],"establishing":[269],"new":[271],"benchmark":[272],"resource-constrained":[274],"diagnosis":[277],"precision":[279],"agriculture":[280],"systems.":[281],"By":[282],"enabling":[283],"accurate,":[284],"interpretable,":[285],"computationally":[287],"efficient":[288],"detection,":[290],"this":[291],"work":[292],"addresses":[293],"critical":[294],"barriers":[295],"practical":[298],"AI-driven":[301],"crop":[302],"monitoring":[303],"mobile":[305],"devices,":[306],"unmanned":[307],"aerial":[308],"vehicles,":[309],"IoT-enabled":[311],"sensors.":[313]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7236432007","counts_by_year":[],"updated_date":"2026-11-19T14:11:59.513116","created_date":"2026-11-19T00:00:00"}
