{"id":"https://openalex.org/W7214766294","doi":"https://doi.org/10.56201/ijemt.vol.12.no1.2026.pg300.326","title":"Explainable Lightweight Deep Learning for Solar Radiation Prediction Using Mobilenet-Bilstm with Multi-Head Attention","display_name":"Explainable Lightweight Deep Learning for Solar Radiation Prediction Using Mobilenet-Bilstm with Multi-Head Attention","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214766294","doi":"https://doi.org/10.56201/ijemt.vol.12.no1.2026.pg300.326"},"language":"en","primary_location":{"id":"doi:10.56201/ijemt.vol.12.no1.2026.pg300.326","doi":"https://doi.org/10.56201/ijemt.vol.12.no1.2026.pg300.326","is_oa":true,"landing_page_url":"https://doi.org/10.56201/ijemt.vol.12.no1.2026.pg300.326","pdf_url":"https://iiardjournals.org/get/IJEMT/VOL. 12 NO. 1 2026/Explainable Lightweight Deep Learning 300-326.pdf","source":{"id":"https://openalex.org/S4387281528","display_name":"INTERNATIONAL JOURNAL OF ENGINEERING AND MODERN TECHNOLOGY","issn_l":"2504-8848","issn":["2504-8848","2695-2149"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL JOURNAL OF ENGINEERING AND MODERN TECHNOLOGY","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://iiardjournals.org/get/IJEMT/VOL. 12 NO. 1 2026/Explainable Lightweight Deep Learning 300-326.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038502990","display_name":"Richard Iherorochi Nneji","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Richard Iherorochi Nneji","raw_affiliation_strings":["Intelligent Computing Lab, Hace LLC, North Carolina, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Computing Lab, Hace LLC, North Carolina, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5038502990"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50962072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"300","last_page":"300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11276","display_name":"Solar Radiation and Photovoltaics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11276","display_name":"Solar Radiation and Photovoltaics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11052","display_name":"Energy Load and Power Forecasting","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/solar-irradiance-forecasting","display_name":"solar irradiance forecasting","score":0.9980000257492065},{"id":"https://openalex.org/keywords/lightweight-deep-learning-models","display_name":"lightweight deep learning","score":0.6809999942779541},{"id":"https://openalex.org/keywords/mobilenet","display_name":"MobileNet","score":0.9390000104904175},{"id":"https://openalex.org/keywords/bidirectional-lstm","display_name":"bidirectional LSTM","score":0.9449999928474426},{"id":"https://openalex.org/keywords/multi-head-attention","display_name":"multi-head attention","score":0.996999979019165},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.9819999933242798},{"id":"https://openalex.org/keywords/grad-cam","display_name":"Grad-CAM","score":0.9940000176429749},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":1.0},{"id":"https://openalex.org/keywords/lime","display_name":"lime","score":0.9980000257492065},{"id":"https://openalex.org/keywords/solar-power-generation","display_name":"solar power generation","score":0.7419999837875366},{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.8759999871253967}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6632000207901001},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5888000130653381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5580000281333923},{"id":"https://openalex.org/C541104983","wikidata":"https://www.wikidata.org/wiki/Q40015","display_name":"Solar energy","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C150217764","wikidata":"https://www.wikidata.org/wiki/Q6803607","display_name":"Mean absolute percentage error","level":3,"score":0.4683000147342682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496999979019165},{"id":"https://openalex.org/C41291067","wikidata":"https://www.wikidata.org/wiki/Q1897785","display_name":"Photovoltaic system","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C2777618391","wikidata":"https://www.wikidata.org/wiki/Q1483757","display_name":"Solar power","level":3,"score":0.349700003862381},{"id":"https://openalex.org/C153385146","wikidata":"https://www.wikidata.org/wiki/Q18335","display_name":"Radiation","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C188573790","wikidata":"https://www.wikidata.org/wiki/Q12705","display_name":"Renewable energy","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C9695528","wikidata":"https://www.wikidata.org/wiki/Q7556707","display_name":"Solar irradiance","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C423512","wikidata":"https://www.wikidata.org/wiki/Q383973","display_name":"Electricity generation","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2922999858856201},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C9466671","wikidata":"https://www.wikidata.org/wiki/Q1259526","display_name":"Radiant energy","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.56201/ijemt.vol.12.no1.2026.pg300.326","doi":"https://doi.org/10.56201/ijemt.vol.12.no1.2026.pg300.326","is_oa":true,"landing_page_url":"https://doi.org/10.56201/ijemt.vol.12.no1.2026.pg300.326","pdf_url":"https://iiardjournals.org/get/IJEMT/VOL. 12 NO. 1 2026/Explainable Lightweight Deep Learning 300-326.pdf","source":{"id":"https://openalex.org/S4387281528","display_name":"INTERNATIONAL JOURNAL OF ENGINEERING AND MODERN TECHNOLOGY","issn_l":"2504-8848","issn":["2504-8848","2695-2149"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL JOURNAL OF ENGINEERING AND MODERN TECHNOLOGY","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.56201/ijemt.vol.12.no1.2026.pg300.326","doi":"https://doi.org/10.56201/ijemt.vol.12.no1.2026.pg300.326","is_oa":true,"landing_page_url":"https://doi.org/10.56201/ijemt.vol.12.no1.2026.pg300.326","pdf_url":"https://iiardjournals.org/get/IJEMT/VOL. 12 NO. 1 2026/Explainable Lightweight Deep Learning 300-326.pdf","source":{"id":"https://openalex.org/S4387281528","display_name":"INTERNATIONAL JOURNAL OF ENGINEERING AND MODERN TECHNOLOGY","issn_l":"2504-8848","issn":["2504-8848","2695-2149"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL JOURNAL OF ENGINEERING AND MODERN TECHNOLOGY","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9853000044822693},{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5378999710083008},{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.5351999998092651}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214766294.pdf","grobid_xml":"https://content.openalex.org/works/W7214766294.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2049626702","https://openalex.org/W2169424769","https://openalex.org/W2412821675","https://openalex.org/W2762053209","https://openalex.org/W2766623285","https://openalex.org/W2795706541","https://openalex.org/W2806919104","https://openalex.org/W2945968483","https://openalex.org/W3094277745","https://openalex.org/W3159574193","https://openalex.org/W3206626384","https://openalex.org/W4210364757","https://openalex.org/W4212982341","https://openalex.org/W4213225299","https://openalex.org/W4220782672","https://openalex.org/W4220910982","https://openalex.org/W4221134600","https://openalex.org/W4224326657","https://openalex.org/W4292379757","https://openalex.org/W4308216819","https://openalex.org/W4312997694","https://openalex.org/W4313289173","https://openalex.org/W4379179858","https://openalex.org/W4399827649","https://openalex.org/W4402650945"],"related_works":["https://openalex.org/W7119911872","https://openalex.org/W4407755427","https://openalex.org/W4388233122","https://openalex.org/W7164306208","https://openalex.org/W4401754489","https://openalex.org/W4281672534","https://openalex.org/W4408998216","https://openalex.org/W7171716506","https://openalex.org/W4414010012","https://openalex.org/W4407576844"],"abstract_inverted_index":{"As":[0],"the":[1,8,26,38,52,88,107,112,124,128,132,178,181,185,190,197,218],"global":[2],"demand":[3],"for":[4,73,217],"sustainable":[5],"energy":[6,12,20,223],"grows,":[7],"importance":[9],"of":[10,19,30,45,54,114,146,152,160,180,189,221],"solar":[11,31,39,46,55,74,222],"as":[13,121],"a":[14,62,99,214],"clean":[15],"and":[16,28,87,154,172,183,187,209],"inexhaustible":[17],"source":[18],"has":[21,200],"become":[22],"increasingly":[23],"prominent.":[24],"However,":[25],"efficiency":[27],"yield":[29],"power":[32,56],"generation":[33,57],"are":[34,174],"directly":[35],"affected":[36],"by":[37],"radiation":[40,47,75],"intensity,":[41],"so":[42,120],"accurate":[43],"prediction":[44,125,205],"is":[48,81,91,103],"crucial":[49],"to":[50,83,93,105,110,122,176],"improve":[51,123,184],"performance":[53,130],"systems.":[58],"This":[59],"paper":[60],"proposes":[61],"hybrid":[63,133,198],"Mobilenet-BiLSTM":[64],"deep":[65],"learning":[66],"model":[67,79,90,129,134,182,199,207],"combined":[68,92],"with":[69,141],"multi-head":[70,100],"attention":[71,101],"mechanism":[72,102],"prediction.":[76],"The":[77,192],"lightweight":[78],"MobileNet":[80],"used":[82],"extract":[84],"image":[85],"features,":[86],"BiLSTM":[89],"process":[94],"time":[95],"series":[96],"features.":[97],"Moreover,":[98],"introduced":[104],"enhance":[106],"model's":[108],"ability":[109],"capture":[111],"correlation":[113],"input":[115],"sequences":[116],"at":[117],"different":[118],"positions,":[119],"accuracy.":[126],"In":[127,162],"evaluation,":[131],"performs":[135],"well":[136],"on":[137],"multiple":[138],"key":[139],"indicators,":[140],"Mean":[142,148,156],"Absolute":[143],"Error":[144,150,158],"(MAE)":[145],"0.2355,":[147],"Square":[149,157],"(MSE)":[151],"0.1159,":[153],"Root":[155],"(RMSE)":[159],"0.3405.":[161],"addition,":[163],"Explainable":[164],"Artificial":[165],"Intelligence":[166],"(XAI)":[167],"techniques,":[168],"including":[169],"Grad-CAM,":[170],"SHAP,":[171],"LIME,":[173],"integrated":[175],"interpret":[177],"predictions":[179],"transparency":[186],"reliability":[188],"model.":[191],"experimental":[193],"results":[194,203],"show":[195],"that":[196],"achieved":[201],"remarkable":[202],"in":[204],"accuracy,":[206],"interpretability":[208],"practical":[210],"application,":[211],"which":[212],"provides":[213],"new":[215],"solution":[216],"efficient":[219],"utilization":[220],"resources.":[224]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-30T00:00:00"}