{"id":"https://openalex.org/W7204262400","doi":"https://doi.org/10.1016/j.atech.2026.102518","title":"Multi-strategy deep learning for crop yield prediction","display_name":"Multi-strategy deep learning for crop yield prediction","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204262400","doi":"https://doi.org/10.1016/j.atech.2026.102518"},"language":"en","primary_location":{"id":"doi:10.1016/j.atech.2026.102518","doi":"https://doi.org/10.1016/j.atech.2026.102518","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.atech.2026.102518","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2772375526007434/pdf","source":{"id":"https://openalex.org/S4210238883","display_name":"Smart Agricultural Technology","issn_l":"2772-3755","issn":["2772-3755"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Smart Agricultural Technology","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.sciencedirect.com/science/article/pii/S2772375526007434/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058990705","display_name":"Daniyal Durmu\u015f K\u00f6ksal","orcid":"https://orcid.org/0000-0001-8199-9044","observed_orcids":["https://orcid.org/0000-0001-8199-9044"]},"institutions":[{"id":"https://openalex.org/I4405259662","display_name":"DSI Genel Mudurlugu","ror":"https://ror.org/02h7ap815","country_code":"TR","type":"government","lineage":["https://openalex.org/I4405259662"]},{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL","TR"],"is_corresponding":false,"raw_author_name":"Daniyal Durmu\u015f K\u00f6ksal","raw_affiliation_strings":["Department of Land Consolidation and On-Farm Development Services, General Directorate of State Hydraulic Works (DS\u0130), Mustafa Kemal Neighborhood, Anadolu Boulevard No:9, 06530 \u00c7ankaya, Ankara, Turkey","Information Technology Group, Wageningen University & Research, Building No. 201 (Leeuwenborch), Hollandseweg 1, 6706 KN, Wageningen, the Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-8199-9044","affiliations":[{"raw_affiliation_string":"Department of Land Consolidation and On-Farm Development Services, General Directorate of State Hydraulic Works (DS\u0130), Mustafa Kemal Neighborhood, Anadolu Boulevard No:9, 06530 \u00c7ankaya, Ankara, Turkey","institution_ids":["https://openalex.org/I4405259662"]},{"raw_affiliation_string":"Information Technology Group, Wageningen University & Research, Building No. 201 (Leeuwenborch), Hollandseweg 1, 6706 KN, Wageningen, the Netherlands","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012394915","display_name":"Kwabena Ebo Bennin","orcid":"https://orcid.org/0000-0001-9140-9271","observed_orcids":["https://orcid.org/0000-0001-9140-9271"]},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kwabena Ebo Bennin","raw_affiliation_strings":["Information Technology Group, Wageningen University & Research, Building No. 201 (Leeuwenborch), Hollandseweg 1, 6706 KN, Wageningen, the Netherlands"],"raw_orcid":"https://orcid.org/0000-0001-9140-9271","affiliations":[{"raw_affiliation_string":"Information Technology Group, Wageningen University & Research, Building No. 201 (Leeuwenborch), Hollandseweg 1, 6706 KN, Wageningen, the Netherlands","institution_ids":["https://openalex.org/I913481162"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002683918","display_name":"Bedir Tekinerdo\u011fan","orcid":"https://orcid.org/0000-0002-8538-7261","observed_orcids":["https://orcid.org/0000-0002-8538-7261","https://orcid.org/0000-0001-9696-3626"]},"institutions":[{"id":"https://openalex.org/I913481162","display_name":"Wageningen University & Research","ror":"https://ror.org/04qw24q55","country_code":"NL","type":"education","lineage":["https://openalex.org/I913481162"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Bedir Tekinerdo\u011fan","raw_affiliation_strings":["Information Technology Group, Wageningen University & Research, Building No. 201 (Leeuwenborch), Hollandseweg 1, 6706 KN, Wageningen, the Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-8538-7261","affiliations":[{"raw_affiliation_string":"Information Technology Group, Wageningen University & Research, Building No. 201 (Leeuwenborch), Hollandseweg 1, 6706 KN, Wageningen, the Netherlands","institution_ids":["https://openalex.org/I913481162"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002683918"],"corresponding_institution_ids":["https://openalex.org/I913481162"],"apc_list":{"value":1770,"currency":"USD","value_usd":1770},"apc_paid":{"value":1770,"currency":"USD","value_usd":1770},"fwci":0.0,"has_fulltext":true,"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":"15","issue":null,"first_page":"102518","last_page":"102518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10439","display_name":"Climate change impacts on agriculture","score":0.82669997215271,"subfield":{"id":"https://openalex.org/subfields/1102","display_name":"Agronomy and Crop 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/T10439","display_name":"Climate change impacts on agriculture","score":0.82669997215271,"subfield":{"id":"https://openalex.org/subfields/1102","display_name":"Agronomy and Crop 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/T10616","display_name":"Smart Agriculture and AI","score":0.16910000145435333,"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/T10111","display_name":"Remote Sensing in Agriculture","score":0.0020000000949949026,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/crop-yield-prediction","display_name":"crop yield prediction","score":0.9980000257492065},{"id":"https://openalex.org/keywords/maize-yield","display_name":"maize yield","score":0.8519999980926514},{"id":"https://openalex.org/keywords/wheat-yield","display_name":"wheat yield","score":1.0},{"id":"https://openalex.org/keywords/multi-task-deep-neural-network","display_name":"multi-task deep neural network","score":0.746999979019165},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"ensemble learning","score":0.609000027179718},{"id":"https://openalex.org/keywords/monte-carlo-dropout","display_name":"Monte Carlo dropout","score":0.859000027179718},{"id":"https://openalex.org/keywords/forecast-uncertainty","display_name":"forecast uncertainty","score":0.8659999966621399},{"id":"https://openalex.org/keywords/climate-variability","display_name":"climate variability","score":0.5929999947547913},{"id":"https://openalex.org/keywords/dssat-crop-model","display_name":"DSSAT crop model","score":0.8080000281333923},{"id":"https://openalex.org/keywords/shared-latent-representation","display_name":"shared latent representation","score":0.7009999752044678},{"id":"https://openalex.org/keywords/ethiopia","display_name":"Ethiopia","score":0.5360000133514404}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42750000953674316},{"id":"https://openalex.org/C137580998","wikidata":"https://www.wikidata.org/wiki/Q235352","display_name":"Crop","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4104999899864197},{"id":"https://openalex.org/C126343540","wikidata":"https://www.wikidata.org/wiki/Q889514","display_name":"Crop yield","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C88463610","wikidata":"https://www.wikidata.org/wiki/Q194118","display_name":"Agricultural engineering","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C2989409935","wikidata":"https://www.wikidata.org/wiki/Q11451","display_name":"Crop production","level":3,"score":0.28679999709129333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2759999930858612},{"id":"https://openalex.org/C2992336426","wikidata":"https://www.wikidata.org/wiki/Q5187949","display_name":"Crop loss","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2590000033378601}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.atech.2026.102518","doi":"https://doi.org/10.1016/j.atech.2026.102518","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.atech.2026.102518","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2772375526007434/pdf","source":{"id":"https://openalex.org/S4210238883","display_name":"Smart Agricultural Technology","issn_l":"2772-3755","issn":["2772-3755"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Smart Agricultural Technology","raw_type":"journal-article"},{"id":"pmh:oai:library.wur.nl:wurpubs/b6c403cf-bf9a-472c-b3f5-82c6811ed32b","doi":null,"is_oa":true,"landing_page_url":"https://research.wur.nl/en/publications/multi-strategy-deep-learning-for-crop-yield-prediction","pdf_url":"https://edepot.wur.nl/724065","source":{"id":"https://openalex.org/S4210201231","display_name":"Socio-Environmental Systems Modeling","issn_l":"2663-3027","issn":["2663-3027"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 2772-3755","raw_type":"Article/Letter to editor"}],"best_oa_location":{"id":"doi:10.1016/j.atech.2026.102518","doi":"https://doi.org/10.1016/j.atech.2026.102518","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.atech.2026.102518","pdf_url":"https://www.sciencedirect.com/science/article/pii/S2772375526007434/pdf","source":{"id":"https://openalex.org/S4210238883","display_name":"Smart Agricultural Technology","issn_l":"2772-3755","issn":["2772-3755"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Smart Agricultural Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.991100013256073},{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.9786999821662903}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204262400.pdf","grobid_xml":"https://content.openalex.org/works/W7204262400.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W2085541073","https://openalex.org/W2158883105","https://openalex.org/W2949642792","https://openalex.org/W2953686964","https://openalex.org/W3079760979","https://openalex.org/W3146049777","https://openalex.org/W3167105002","https://openalex.org/W3172362740","https://openalex.org/W4205589426","https://openalex.org/W4206678546","https://openalex.org/W4280504002","https://openalex.org/W4281489023","https://openalex.org/W4289515874","https://openalex.org/W4361026558","https://openalex.org/W4383498186","https://openalex.org/W4385405260","https://openalex.org/W4389301635","https://openalex.org/W4391138050","https://openalex.org/W4401216918","https://openalex.org/W4402332371","https://openalex.org/W4403042392","https://openalex.org/W4403976848","https://openalex.org/W4404237979","https://openalex.org/W4404614783","https://openalex.org/W4404864862","https://openalex.org/W4404880194","https://openalex.org/W4405139381","https://openalex.org/W4405301470","https://openalex.org/W4405993102","https://openalex.org/W4406117927","https://openalex.org/W4406884574","https://openalex.org/W4406985820","https://openalex.org/W4407030761","https://openalex.org/W4407182771","https://openalex.org/W4407807196","https://openalex.org/W4408747064","https://openalex.org/W4410195866","https://openalex.org/W4410219213","https://openalex.org/W4410759251","https://openalex.org/W4411255151","https://openalex.org/W4411577563","https://openalex.org/W4412107693","https://openalex.org/W4412830240","https://openalex.org/W4413015148","https://openalex.org/W4415064897","https://openalex.org/W4416722114","https://openalex.org/W6929337193","https://openalex.org/W6963959162","https://openalex.org/W7154460281"],"related_works":["https://openalex.org/W3052013913","https://openalex.org/W7154115954","https://openalex.org/W6958426884","https://openalex.org/W4200414142","https://openalex.org/W4411577563","https://openalex.org/W7126176924","https://openalex.org/W7155508821","https://openalex.org/W7215769090","https://openalex.org/W7148591008","https://openalex.org/W7215032967"],"abstract_inverted_index":{"Reliable":[0],"crop":[1,115,248],"yield":[2,71,108,138,198,249],"estimation":[3],"under":[4,53,117],"climate":[5,105],"variability":[6,211],"requires":[7],"modeling":[8],"frameworks":[9],"that":[10,46,73,164,205,224],"balance":[11],"predictive":[12,156,171],"accuracy,":[13],"robustness,":[14],"and":[15,49,60,69,87,113,119,181,190,212,218,227,243],"structural":[16,214],"consistency":[17],"across":[18],"heterogeneous":[19],"simulation":[20],"environments.":[21],"Although":[22],"deep":[23,64],"neural":[24],"networks":[25,133],"(DNNs)":[26],"have":[27],"demonstrated":[28],"strong":[29],"capability":[30],"in":[31,149],"capturing":[32],"nonlinear":[33],"climate\u2013crop":[34],"relationships,":[35],"limited":[36],"attention":[37],"has":[38],"been":[39],"given":[40],"to":[41,145,177,186],"systematically":[42],"comparing":[43],"architectural":[44,236],"strategies":[45,230],"influence":[47],"stability":[48],"uncertainty":[50,157],"characterization,":[51],"particularly":[52],"minimum":[54],"input":[55],"configurations.":[56],"This":[57],"study":[58],"develops":[59],"evaluates":[61],"a":[62,100,201,241],"multi-strategy":[63],"learning":[65],"framework":[66,245],"for":[67,127,179,183,188,192,246],"maize":[68],"wheat":[70,180],"prediction":[72],"integrates":[74],"independent":[75],"single-task":[76,189],"DNNs,":[77],"multi-task":[78,132,193],"DNNs":[79,207],"with":[80,107],"shared":[81],"latent":[82],"representations,":[83],"deterministic":[84],"averaging":[85],"ensembles,":[86],"stochastic":[88,160],"ensembles":[89],"based":[90],"on":[91],"Monte":[92],"Carlo":[93],"(MC)":[94],"Dropout.":[95],"Ethiopia":[96],"is":[97],"used":[98],"as":[99],"case":[101,151],"study,":[102],"combining":[103],"ERA5-derived":[104],"variables":[106],"simulations":[109],"from":[110],"the":[111,150,169],"DSSAT":[112],"LPJmL":[114],"models":[116,123],"irrigated":[118],"rainfed":[120],"conditions.":[121],"Single-task":[122],"are":[124],"trained":[125],"separately":[126],"each":[128],"crop\u2013regime\u2013simulation":[129],"combination,":[130],"while":[131],"jointly":[134],"learn":[135],"structurally":[136],"related":[137],"targets.":[139],"Ensemble":[140],"approaches":[141],"aggregate":[142],"model":[143],"realizations":[144],"reduce":[146],"variance":[147,225],"and,":[148],"of":[152],"MC":[153],"Dropout,":[154],"approximate":[155],"through":[158],"repeated":[159],"inference.":[161],"Results":[162],"indicate":[163],"ensemble":[165,206,229],"configurations":[166],"consistently":[167],"deliver":[168],"highest":[170],"performance,":[172],"achieving":[173],"R\u00b2":[174],"values":[175],"up":[176],"0.94":[178],"0.88":[182],"maize,":[184],"compared":[185],"0.77\u20130.92":[187],"0.76\u20130.94":[191],"models.":[194],"Validation":[195],"against":[196],"FAO":[197],"statistics":[199],"over":[200],"15-year":[202],"period":[203],"confirms":[204],"better":[208],"reproduce":[209],"interannual":[210],"moderate":[213],"divergence":[215],"between":[216],"DSSAT-":[217],"LPJmL-driven":[219],"outputs.":[220],"The":[221],"findings":[222],"demonstrate":[223],"reduction":[226],"uncertainty-aware":[228],"provide":[231],"more":[232],"consistent":[233],"generalization":[234],"than":[235],"task":[237],"coupling":[238],"alone,":[239],"offering":[240],"scalable":[242],"robustness-oriented":[244],"climate-sensitive":[247],"assessment":[250],"using":[251],"parsimonious":[252],"environmental":[253],"inputs.":[254]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-08-27T00:00:00"}