Peanut yield and grade prediction in Georgia, USA: integrating management, climate, and remote sensing data with explainable AI

Autores
Scarpin, Gonzalo Joel; Studstill, Sara Beth; Monfort, Walter Scott; Tubbs, Ronald Scott; Pilon, Cristiane; Jakhar, Amrinder; Bhattarai, Anish; Dhaliwal, Amandeep Kaur; Bastos, Leonardo M.
Año de publicación
2026
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Predicting agricultural yields and quality is essential for optimizing decision-making, food security, economic planning, and resource management. Although many studies have compared algorithms or variables for predicting yield or quality, the information on peanut (Arachis hypogaea L.) is limited. To address this, our study aims to: a) compare the performance of various machine learning (ML) models for predicting peanut yield and grade across diverse variable groups (GV); b) select the most accurate ML and GV combination; c) identify the most important factors driving outcomes using SHapley Additive exPlanations (SHAP); and d) assess the spatial generalization of the best models using a Leave-One-Site-Year-Out (LOSYO) cross-validation. A total of 540 ML were trained comparing 18 different ML with 15 GV, being these: management (M), weather (W), soil (S), and remote sensing (R) datasets and their combination. Management information was recovered from surveys performed from 2017 to 2019 on more than 200 peanut farms from Georgia, USA and open-source related data was retrieved. Results indicated that Cubist-rule and support vector machine performed better than other models achieving the lowest root mean squared error values (816 kg ha−1 for yield, 1.52 for grade). Among the different GV, M + S and M + R performed better than others for yield and grade, respectively. SHAP revealed irrigation, geographic location, and soil properties as key drivers of yield, whereas vegetation indices and management decisions influenced grade. The study underscores the value of interpretable ML models for optimizing peanut production under variable environmental conditions, offering actionable insights for farmers and agronomists.
EEA Reconquista
Fil: Scarpin, Gonzalo Joel. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Scarpin, Gonzalo Joel. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Reconquista; Argentina
Fil: Studstill, Sara Beth. Bayer Crop Sciences; Estados Unidos
Fil: Monfort, Walter Scott. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Tubbs, Ronald Scott. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Pilon, Cristiane. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Jakhar, Amrinder. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Bhattarai, Anish. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Dhaliwal, Amandeep Kaur. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Bastos, Leonardo M. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fuente
Computers and Electronics in Agriculture 241 : 111270. (February 2026)
Materia
Arachis hypogaea
Groundnuts
Yields
Crop Management
Remote Sensing
Precision Agriculture
Artificial Intelligence
Georgia (USA)
Cacahuete
Rendimiento
Manejo del Cultivo
Teledetección
Agricultura de Precisión
Inteligencia Artificial
Georgia (EUA)
Maní
Peanuts
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/4.0/
Repositorio
INTA Digital (INTA)
Institución
Instituto Nacional de Tecnología Agropecuaria
OAI Identificador
oai:localhost:20.500.12123/27771
Acceder
id INTADig_6302df30141ad17dd7fdb44307f958b8
oai_identifier_str oai:localhost:20.500.12123/27771
network_acronym_str INTADig
repository_id_str l
network_name_str INTA Digital (INTA)
spelling Peanut yield and grade prediction in Georgia, USA: integrating management, climate, and remote sensing data with explainable AIScarpin, Gonzalo JoelStudstill, Sara BethMonfort, Walter ScottTubbs, Ronald ScottPilon, CristianeJakhar, AmrinderBhattarai, AnishDhaliwal, Amandeep KaurBastos, Leonardo M.Arachis hypogaeaGroundnutsYieldsCrop ManagementRemote SensingPrecision AgricultureArtificial IntelligenceGeorgia (USA)CacahueteRendimientoManejo del CultivoTeledetecciónAgricultura de PrecisiónInteligencia ArtificialGeorgia (EUA)ManíPeanutsPredicting agricultural yields and quality is essential for optimizing decision-making, food security, economic planning, and resource management. Although many studies have compared algorithms or variables for predicting yield or quality, the information on peanut (Arachis hypogaea L.) is limited. To address this, our study aims to: a) compare the performance of various machine learning (ML) models for predicting peanut yield and grade across diverse variable groups (GV); b) select the most accurate ML and GV combination; c) identify the most important factors driving outcomes using SHapley Additive exPlanations (SHAP); and d) assess the spatial generalization of the best models using a Leave-One-Site-Year-Out (LOSYO) cross-validation. A total of 540 ML were trained comparing 18 different ML with 15 GV, being these: management (M), weather (W), soil (S), and remote sensing (R) datasets and their combination. Management information was recovered from surveys performed from 2017 to 2019 on more than 200 peanut farms from Georgia, USA and open-source related data was retrieved. Results indicated that Cubist-rule and support vector machine performed better than other models achieving the lowest root mean squared error values (816 kg ha−1 for yield, 1.52 for grade). Among the different GV, M + S and M + R performed better than others for yield and grade, respectively. SHAP revealed irrigation, geographic location, and soil properties as key drivers of yield, whereas vegetation indices and management decisions influenced grade. The study underscores the value of interpretable ML models for optimizing peanut production under variable environmental conditions, offering actionable insights for farmers and agronomists.EEA ReconquistaFil: Scarpin, Gonzalo Joel. University of Georgia. Department of Crop and Soil Sciences; Estados UnidosFil: Scarpin, Gonzalo Joel. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Reconquista; ArgentinaFil: Studstill, Sara Beth. Bayer Crop Sciences; Estados UnidosFil: Monfort, Walter Scott. University of Georgia. Department of Crop and Soil Sciences; Estados UnidosFil: Tubbs, Ronald Scott. University of Georgia. Department of Crop and Soil Sciences; Estados UnidosFil: Pilon, Cristiane. University of Georgia. Department of Crop and Soil Sciences; Estados UnidosFil: Jakhar, Amrinder. University of Georgia. Department of Crop and Soil Sciences; Estados UnidosFil: Bhattarai, Anish. University of Georgia. Department of Crop and Soil Sciences; Estados UnidosFil: Dhaliwal, Amandeep Kaur. University of Georgia. Department of Crop and Soil Sciences; Estados UnidosFil: Bastos, Leonardo M. University of Georgia. Department of Crop and Soil Sciences; Estados UnidosElsevier2026-09-14T10:14:12Z2026-09-14T10:14:12Z2026-02info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfhttp://hdl.handle.net/20.500.12123/27771https://www.sciencedirect.com/science/article/pii/S01681699250137660168-16991872-7107https://doi.org/10.1016/j.compag.2025.111270Computers and Electronics in Agriculture 241 : 111270. (February 2026)reponame:INTA Digital (INTA)instname:Instituto Nacional de Tecnología AgropecuariaengGeorgia .......... (state) (World, North and Central America, United States)7007248info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)2026-09-24T11:43:50Zoai:localhost:20.500.12123/27771instacron:INTAInstitucionalhttp://repositorio.inta.gob.ar/Organismo científico-tecnológicoNo correspondehttp://repositorio.inta.gob.ar/oai/requesttripaldi.nicolas@inta.gob.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:l2026-09-24 11:43:50.562INTA Digital (INTA) - Instituto Nacional de Tecnología Agropecuariafalse
dc.title.none.fl_str_mv Peanut yield and grade prediction in Georgia, USA: integrating management, climate, and remote sensing data with explainable AI
title Peanut yield and grade prediction in Georgia, USA: integrating management, climate, and remote sensing data with explainable AI
spellingShingle Peanut yield and grade prediction in Georgia, USA: integrating management, climate, and remote sensing data with explainable AI
Scarpin, Gonzalo Joel
Arachis hypogaea
Groundnuts
Yields
Crop Management
Remote Sensing
Precision Agriculture
Artificial Intelligence
Georgia (USA)
Cacahuete
Rendimiento
Manejo del Cultivo
Teledetección
Agricultura de Precisión
Inteligencia Artificial
Georgia (EUA)
Maní
Peanuts
title_short Peanut yield and grade prediction in Georgia, USA: integrating management, climate, and remote sensing data with explainable AI
title_full Peanut yield and grade prediction in Georgia, USA: integrating management, climate, and remote sensing data with explainable AI
title_fullStr Peanut yield and grade prediction in Georgia, USA: integrating management, climate, and remote sensing data with explainable AI
title_full_unstemmed Peanut yield and grade prediction in Georgia, USA: integrating management, climate, and remote sensing data with explainable AI
title_sort Peanut yield and grade prediction in Georgia, USA: integrating management, climate, and remote sensing data with explainable AI
dc.creator.none.fl_str_mv Scarpin, Gonzalo Joel
Studstill, Sara Beth
Monfort, Walter Scott
Tubbs, Ronald Scott
Pilon, Cristiane
Jakhar, Amrinder
Bhattarai, Anish
Dhaliwal, Amandeep Kaur
Bastos, Leonardo M.
author Scarpin, Gonzalo Joel
author_facet Scarpin, Gonzalo Joel
Studstill, Sara Beth
Monfort, Walter Scott
Tubbs, Ronald Scott
Pilon, Cristiane
Jakhar, Amrinder
Bhattarai, Anish
Dhaliwal, Amandeep Kaur
Bastos, Leonardo M.
author_role author
author2 Studstill, Sara Beth
Monfort, Walter Scott
Tubbs, Ronald Scott
Pilon, Cristiane
Jakhar, Amrinder
Bhattarai, Anish
Dhaliwal, Amandeep Kaur
Bastos, Leonardo M.
author2_role author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Arachis hypogaea
Groundnuts
Yields
Crop Management
Remote Sensing
Precision Agriculture
Artificial Intelligence
Georgia (USA)
Cacahuete
Rendimiento
Manejo del Cultivo
Teledetección
Agricultura de Precisión
Inteligencia Artificial
Georgia (EUA)
Maní
Peanuts
topic Arachis hypogaea
Groundnuts
Yields
Crop Management
Remote Sensing
Precision Agriculture
Artificial Intelligence
Georgia (USA)
Cacahuete
Rendimiento
Manejo del Cultivo
Teledetección
Agricultura de Precisión
Inteligencia Artificial
Georgia (EUA)
Maní
Peanuts
dc.description.none.fl_txt_mv Predicting agricultural yields and quality is essential for optimizing decision-making, food security, economic planning, and resource management. Although many studies have compared algorithms or variables for predicting yield or quality, the information on peanut (Arachis hypogaea L.) is limited. To address this, our study aims to: a) compare the performance of various machine learning (ML) models for predicting peanut yield and grade across diverse variable groups (GV); b) select the most accurate ML and GV combination; c) identify the most important factors driving outcomes using SHapley Additive exPlanations (SHAP); and d) assess the spatial generalization of the best models using a Leave-One-Site-Year-Out (LOSYO) cross-validation. A total of 540 ML were trained comparing 18 different ML with 15 GV, being these: management (M), weather (W), soil (S), and remote sensing (R) datasets and their combination. Management information was recovered from surveys performed from 2017 to 2019 on more than 200 peanut farms from Georgia, USA and open-source related data was retrieved. Results indicated that Cubist-rule and support vector machine performed better than other models achieving the lowest root mean squared error values (816 kg ha−1 for yield, 1.52 for grade). Among the different GV, M + S and M + R performed better than others for yield and grade, respectively. SHAP revealed irrigation, geographic location, and soil properties as key drivers of yield, whereas vegetation indices and management decisions influenced grade. The study underscores the value of interpretable ML models for optimizing peanut production under variable environmental conditions, offering actionable insights for farmers and agronomists.
EEA Reconquista
Fil: Scarpin, Gonzalo Joel. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Scarpin, Gonzalo Joel. Instituto Nacional de Tecnología Agropecuaria (INTA). Estación Experimental Agropecuaria Reconquista; Argentina
Fil: Studstill, Sara Beth. Bayer Crop Sciences; Estados Unidos
Fil: Monfort, Walter Scott. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Tubbs, Ronald Scott. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Pilon, Cristiane. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Jakhar, Amrinder. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Bhattarai, Anish. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Dhaliwal, Amandeep Kaur. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
Fil: Bastos, Leonardo M. University of Georgia. Department of Crop and Soil Sciences; Estados Unidos
description Predicting agricultural yields and quality is essential for optimizing decision-making, food security, economic planning, and resource management. Although many studies have compared algorithms or variables for predicting yield or quality, the information on peanut (Arachis hypogaea L.) is limited. To address this, our study aims to: a) compare the performance of various machine learning (ML) models for predicting peanut yield and grade across diverse variable groups (GV); b) select the most accurate ML and GV combination; c) identify the most important factors driving outcomes using SHapley Additive exPlanations (SHAP); and d) assess the spatial generalization of the best models using a Leave-One-Site-Year-Out (LOSYO) cross-validation. A total of 540 ML were trained comparing 18 different ML with 15 GV, being these: management (M), weather (W), soil (S), and remote sensing (R) datasets and their combination. Management information was recovered from surveys performed from 2017 to 2019 on more than 200 peanut farms from Georgia, USA and open-source related data was retrieved. Results indicated that Cubist-rule and support vector machine performed better than other models achieving the lowest root mean squared error values (816 kg ha−1 for yield, 1.52 for grade). Among the different GV, M + S and M + R performed better than others for yield and grade, respectively. SHAP revealed irrigation, geographic location, and soil properties as key drivers of yield, whereas vegetation indices and management decisions influenced grade. The study underscores the value of interpretable ML models for optimizing peanut production under variable environmental conditions, offering actionable insights for farmers and agronomists.
publishDate 2026
dc.date.none.fl_str_mv 2026-09-14T10:14:12Z
2026-09-14T10:14:12Z
2026-02
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/20.500.12123/27771
https://www.sciencedirect.com/science/article/pii/S0168169925013766
0168-1699
1872-7107
https://doi.org/10.1016/j.compag.2025.111270
url http://hdl.handle.net/20.500.12123/27771
https://www.sciencedirect.com/science/article/pii/S0168169925013766
https://doi.org/10.1016/j.compag.2025.111270
identifier_str_mv 0168-1699
1872-7107
dc.language.none.fl_str_mv eng
language eng
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/4.0/
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)
dc.format.none.fl_str_mv application/pdf
dc.coverage.none.fl_str_mv Georgia .......... (state) (World, North and Central America, United States)
7007248
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv Computers and Electronics in Agriculture 241 : 111270. (February 2026)
reponame:INTA Digital (INTA)
instname:Instituto Nacional de Tecnología Agropecuaria
reponame_str INTA Digital (INTA)
collection INTA Digital (INTA)
instname_str Instituto Nacional de Tecnología Agropecuaria
repository.name.fl_str_mv INTA Digital (INTA) - Instituto Nacional de Tecnología Agropecuaria
repository.mail.fl_str_mv tripaldi.nicolas@inta.gob.ar
_version_ 1877227358363058176
score 13.265058

Publicaciones similares