Identification of soybean planting gaps using machine learning

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversity of Connecticut-
Autor(es): dc.contributorLouisiana State University-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorUniversity Center of Hermínio Ometto Foundation-
Autor(es): dc.contributorCollege Station-
Autor(es): dc.creatorde Souza, Flávia Luize Pereira-
Autor(es): dc.creatorDias, Maurício Acconcia-
Autor(es): dc.creatorSetiyono, Tri Deri-
Autor(es): dc.creatorCampos, Sérgio-
Autor(es): dc.creatorShiratsuchi, Luciano Shozo-
Autor(es): dc.creatorTao, Haiying-
Data de aceite: dc.date.accessioned2025-08-21T17:22:38Z-
Data de disponibilização: dc.date.available2025-08-21T17:22:38Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2025-03-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1016/j.atech.2025.100779-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/305541-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/305541-
Descrição: dc.descriptionThe identification of planting gaps is essential for optimizing crop management in precision agriculture. Traditional methods, such as manual scouting, are limited in scale and precision. This study evaluates the performance of three machine learning algorithms—Decision Trees, Support Vector Machines (SVM), and Multilayer Perceptron (MLP) Neural Networks—for classifying planting gaps in soybean fields using UAV imagery during the V4 growth stage. The Neural Network and SVM models demonstrated similar results, with the Neural Network achieving an AUC of 0.984, accuracy of 94.5 %, F1 score of 0.945, precision of 94.5 %, and recall of 94.5 %. The SVM model with a Polynomial kernel achieved an AUC of 0.989, accuracy of 95.5 %, F1 score of 0.955, precision of 95.5 %, and recall of 95.5 %. In contrast, the Decision Tree model performed lower, with an AUC of 0.805 and accuracy of 79 %. These results demonstrate the effectiveness of machine learning algorithms, particularly Neural Networks and SVM, in improving planting gap detection, contributing to more precise crop management decisions.-
Descrição: dc.descriptionDepartment of Plant Science and Landscape Architecture University of Connecticut-
Descrição: dc.descriptionSchool of Plant Environmental and Soil Sciences Louisiana State University-
Descrição: dc.descriptionSão Paulo State University, SP-
Descrição: dc.descriptionUniversity Center of Hermínio Ometto Foundation-
Descrição: dc.descriptionPrecision AgX LLC PO box 9617 College Station-
Descrição: dc.descriptionSão Paulo State University, SP-
Idioma: dc.languageen-
Relação: dc.relationSmart Agricultural Technology-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectMachine learning-
Palavras-chave: dc.subjectPlanting gaps-
Palavras-chave: dc.subjectPrecision agriculture-
Palavras-chave: dc.subjectSoybean-
Palavras-chave: dc.subjectUAV-
Título: dc.titleIdentification of soybean planting gaps using machine learning-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.