{"id":"https://openalex.org/W7215111187","doi":"https://doi.org/10.48550/arxiv.2609.38447","title":"An Input-Frugal Deep Learning Framework for Weather-Driven National Crop-Yield Forecasting: A Case Study of Brazilian Soybean","display_name":"An Input-Frugal Deep Learning Framework for Weather-Driven National Crop-Yield Forecasting: A Case Study of Brazilian Soybean","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7215111187","doi":"https://doi.org/10.48550/arxiv.2609.38447"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.38447","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38447","pdf_url":"https://arxiv.org/pdf/2609.38447","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.38447","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008943776","display_name":"Fernando Dupin da Cunha Mello","orcid":"https://orcid.org/0009-0006-9922-2763","observed_orcids":["https://orcid.org/0009-0006-9922-2763"]},"institutions":[{"id":"https://openalex.org/I1329807341","display_name":"Servi\u00e7o Nacional de Aprendizagem Industrial","ror":"https://ror.org/035c3nf67","country_code":"BR","type":"nonprofit","lineage":["https://openalex.org/I1329807341"]},{"id":"https://openalex.org/I4405256755","display_name":"Universidade SENAI CIMATEC","ror":"https://ror.org/04gkha250","country_code":"BR","type":"education","lineage":["https://openalex.org/I4405256755"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Mello, Fernando Dupin da Cunha","raw_affiliation_strings":["Stricto Sensu Department, SENAI CIMATEC University, Salvador, Bahia, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stricto Sensu Department, SENAI CIMATEC University, Salvador, Bahia, Brazil","institution_ids":["https://openalex.org/I1329807341","https://openalex.org/I4405256755"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5154115091","display_name":"Prashant Kumar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Prashant","raw_affiliation_strings":["Global Centre for Clean Air Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Global Centre for Clean Air Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5154149479","display_name":"Erick G. Sperandio Nascimento","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1329807341","display_name":"Servi\u00e7o Nacional de Aprendizagem Industrial","ror":"https://ror.org/035c3nf67","country_code":"BR","type":"nonprofit","lineage":["https://openalex.org/I1329807341"]},{"id":"https://openalex.org/I4405256755","display_name":"Universidade SENAI CIMATEC","ror":"https://ror.org/04gkha250","country_code":"BR","type":"education","lineage":["https://openalex.org/I4405256755"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Nascimento, Erick G. Sperandio","raw_affiliation_strings":["Stricto Sensu Department, SENAI CIMATEC University, Salvador, Bahia, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stricto Sensu Department, SENAI CIMATEC University, Salvador, Bahia, Brazil","institution_ids":["https://openalex.org/I1329807341","https://openalex.org/I4405256755"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10616","display_name":"Smart Agriculture and AI","score":0.9653000235557556,"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":0.9653000235557556,"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/T10439","display_name":"Climate change impacts on agriculture","score":0.026200000196695328,"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/T10111","display_name":"Remote Sensing in Agriculture","score":0.006300000008195639,"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":0.8999999761581421},{"id":"https://openalex.org/keywords/soybean","display_name":"soybean","score":0.6930000185966492},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.5759999752044678},{"id":"https://openalex.org/keywords/mamba","display_name":"Mamba","score":0.7910000085830688},{"id":"https://openalex.org/keywords/transformer-encoder","display_name":"Transformer encoder","score":0.9100000262260437},{"id":"https://openalex.org/keywords/cnn-lstm","display_name":"CNN-LSTM","score":0.7149999737739563},{"id":"https://openalex.org/keywords/shap","display_name":"SHAP","score":0.6660000085830688}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6679999828338623},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5273000001907349},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4875999987125397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48260000348091125},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4296000003814697},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3855000138282776},{"id":"https://openalex.org/C170061395","wikidata":"https://www.wikidata.org/wiki/Q5468164","display_name":"Forecast skill","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C2775907726","wikidata":"https://www.wikidata.org/wiki/Q714439","display_name":"Oak Ridge National Laboratory","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C188154048","wikidata":"https://www.wikidata.org/wiki/Q6803609","display_name":"Mean absolute error","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C32277403","wikidata":"https://www.wikidata.org/wiki/Q740445","display_name":"Ridge","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2639999985694885},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C21001229","wikidata":"https://www.wikidata.org/wiki/Q182868","display_name":"Weather forecasting","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.25459998846054077},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C205537798","wikidata":"https://www.wikidata.org/wiki/Q1277161","display_name":"Extreme weather","level":3,"score":0.25029999017715454},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.38447","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38447","pdf_url":"https://arxiv.org/pdf/2609.38447","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.38447","doi":"https://doi.org/10.48550/arxiv.2609.38447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.38447","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.38447","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38447","pdf_url":"https://arxiv.org/pdf/2609.38447","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.991100013256073,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"},{"score":0.821399986743927,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1123372118","display_name":null,"funder_award_id":"EP/ W034034 /1","funder_id":"https://openalex.org/F4320334609","funder_display_name":"Arts and Humanities Research Council"},{"id":"https://openalex.org/G1412047520","display_name":null,"funder_award_id":"308963/2022-9","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G255510393","display_name":null,"funder_award_id":"EP/W034034/1","funder_id":"https://openalex.org/F4320334631","funder_display_name":"Natural Environment Research Council"},{"id":"https://openalex.org/G5899837305","display_name":null,"funder_award_id":"EP/W034034/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"},{"id":"https://openalex.org/G6756993358","display_name":null,"funder_award_id":"/2022-9","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G6815844370","display_name":null,"funder_award_id":"88881","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G8524700199","display_name":"Reclaiming Forgotten Cities - Turning cities from vulnerable spaces to healthy places for people [RECLAIM]","funder_award_id":"EP/W034034/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320317600","display_name":"SENAI CIMATEC","ror":"https://ror.org/04gkha250"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320321979","display_name":"University of Surrey","ror":"https://ror.org/00ks66431"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320323681","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado da Bahia","ror":"https://ror.org/0473khm44"},{"id":"https://openalex.org/F4320334609","display_name":"Arts and Humanities Research Council","ror":"https://ror.org/0505m1554"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334631","display_name":"Natural Environment Research Council","ror":"https://ror.org/02b5d8509"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215111187.pdf","grobid_xml":"https://content.openalex.org/works/W7215111187.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2072671535","https://openalex.org/W2126728600","https://openalex.org/W2131241448","https://openalex.org/W2158883105","https://openalex.org/W2604645045","https://openalex.org/W2810601729","https://openalex.org/W2949642792","https://openalex.org/W2995665326","https://openalex.org/W3000098473","https://openalex.org/W3079760979","https://openalex.org/W3087546776","https://openalex.org/W3146049777","https://openalex.org/W3162411720","https://openalex.org/W3209676059","https://openalex.org/W4200337258","https://openalex.org/W4205915228","https://openalex.org/W4210675531","https://openalex.org/W4252684946","https://openalex.org/W4294883934","https://openalex.org/W4297978097","https://openalex.org/W4298872162","https://openalex.org/W4299627282","https://openalex.org/W4313641523","https://openalex.org/W4322632436","https://openalex.org/W4361026558","https://openalex.org/W4361276701","https://openalex.org/W4386188621","https://openalex.org/W4390563562","https://openalex.org/W4403042392","https://openalex.org/W4404462604","https://openalex.org/W4405523058","https://openalex.org/W4409441283"],"related_works":["https://openalex.org/W7155508821","https://openalex.org/W7213456137","https://openalex.org/W4394912339","https://openalex.org/W4402992072","https://openalex.org/W7214980743","https://openalex.org/W4406586325","https://openalex.org/W7126176924","https://openalex.org/W4415560923","https://openalex.org/W7171383389","https://openalex.org/W3182380878"],"abstract_inverted_index":{"Reliable,":[0],"timely":[1],"crop-yield":[2],"forecasts":[3,143,233],"are":[4],"essential":[5],"for":[6,234],"market":[7],"stability":[8],"and":[9,26,48,56,88,97,109,170,200,209,223,226],"risk":[10],"management,":[11],"yet":[12],"many":[13],"approaches":[14],"rely":[15],"on":[16],"costly":[17],"or":[18],"hard-to-scale":[19],"inputs.":[20],"We":[21],"present":[22],"a":[23,69,85,98],"frugal,":[24],"transferable,":[25],"architecture-agnostic":[27],"deep":[28,104],"learning":[29,105],"framework":[30,215],"that":[31,166],"uses":[32],"routine":[33,235],"weather":[34,176,199,232],"as":[35],"the":[36,89,114,120,139,157,160,167,194,214],"only":[37],"time-varying":[38],"input":[39,184],"plus":[40],"two":[41],"lightweight":[42],"static":[43],"context":[44,202],"inputs":[45],"(crop":[46],"year":[47,190],"an":[49],"agro-environmental":[50,168,201],"label)":[51],"to":[52,138,148,218],"capture":[53],"long-run":[54,195],"change":[55],"regional":[57],"heterogeneity,":[58],"while":[59],"supporting":[60],"multiple":[61],"sequence":[62],"encoders":[63,112],"under":[64],"identical":[65],"data":[66],"requirements.":[67],"Using":[68],"20-season":[70],"Brazilian":[71],"soybean":[72],"case":[73],"study":[74],"(2001/02-2020/21)":[75],"with":[76,207,230],"leave-one-year-out":[77],"cross-validation,":[78],"we":[79],"benchmark":[80],"MLP,":[81],"CNN,":[82],"LSTM,":[83],"CNN-LSTM,":[84],"Transformer":[86,118],"encoder":[87],"Mamba":[90],"state-space":[91],"model":[92],"against":[93],"linear":[94],"ridge":[95],"regression":[96],"five-year":[99],"moving-average":[100],"\"farmer\"":[101],"baseline.":[102,141],"All":[103],"variants":[106],"outperform":[107],"ridge,":[108],"all":[110],"sequential":[111],"surpass":[113],"non-sequential":[115],"MLP.":[116],"The":[117],"achieves":[119],"best":[121],"national":[122],"accuracy":[123],"(RMSE":[124],"149":[125],"kg":[126],"ha^-1;":[127],"rRMSE":[128],"5.3%;":[129],"R^2":[130],"=":[131],"0.784),":[132],"reducing":[133],"error":[134,155],"by":[135],"47.6%":[136],"relative":[137],"farmer":[140],"In-season":[142],"improve":[144],"monotonically":[145],"from":[146],"early-":[147],"late-season":[149],"issuance,":[150],"reaching":[151],"approximately":[152],"50%":[153],"lower":[154],"than":[156],"baseline":[158],"at":[159],"latest":[161],"forecast":[162],"point.":[163],"Ablations":[164],"indicate":[165],"label":[169],"spatial":[171],"instance":[172],"expansion":[173],"(multiple":[174],"grid-node":[175],"sequences":[177],"per":[178],"municipality-year)":[179],"contribute":[180],"positively":[181],"without":[182],"increasing":[183],"complexity.":[185],"SHAP":[186],"diagnostics":[187],"suggest":[188],"crop":[189],"explains":[191],"most":[192],"of":[193],"trajectory,":[196],"whereas":[197],"within-season":[198],"primarily":[203],"drive":[204],"interannual":[205],"deviations,":[206],"moisture/cloud":[208],"thermal-demand":[210],"variables":[211],"dominating.":[212],"Overall,":[213],"is":[216,227],"straightforward":[217],"deploy":[219],"across":[220],"other":[221],"crops":[222],"geographic":[224],"regions":[225],"naturally":[228],"compatible":[229],"operational":[231],"monitoring.":[236]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-02T00:00:00"}