Por favor, use este identificador para citar o enlazar este ítem: http://www.alice.cnptia.embrapa.br/alice/handle/doc/1185326
Registro completo de metadatos
Campo DCValorLengua/Idioma
dc.contributor.authorSILVA, C. S. D.
dc.contributor.authorSILVA, T. E. da
dc.contributor.authorSGUIZATTO, A. L. L.
dc.contributor.authorMACHADO, A. F.
dc.contributor.authorSILVA, A. S.
dc.contributor.authorCOSTA, J. H. C.
dc.contributor.authorCAMPOS, M. M.
dc.contributor.authorPACIULLO, D. S. C.
dc.contributor.authorGOMIDE, C. A. de M.
dc.contributor.authorMORENZ, M. J. F.
dc.date.accessioned2026-03-12T13:56:55Z-
dc.date.available2026-03-12T13:56:55Z-
dc.date.created2026-03-12
dc.date.issued2026
dc.identifier.citationJDS Communications, v. 7, n. 2, p. 179-184, Mar. 2026.
dc.identifier.urihttp://www.alice.cnptia.embrapa.br/alice/handle/doc/1185326-
dc.descriptionAccurate estimation of DMI is essential for optimizing nutrition, efficiency, and economic performance in modern dairy herds. However, most existing equations to estimate DMI are designed for herd-level predictions in purebred Holstein cows. This study evaluated the accuracy and precision of machine learning (ML) algorithms to predict daily individual DMI in Holstein × Gyr crossbred lactating cows using a supervised and integrative approach that combined behavior monitoring data, cow phenotypes, and weather features. Data from 31 cows were individually and consecutively collected over 18 d. Twenty-two cows (71% of the dataset) were used to train 4 linear regression models (multiple linear, ridge, lasso, and elastic net) and 3 ensemble algorithms (random forest, gradient boosting, and extreme gradient boosting) through leave-one-group-out cross-validation, with the number of folds equal to the number of cows (k = 22). The remaining 9 cows were used as an external test set. Among all algorithms, Gradient boosting achieved the best overall performance, yielding moderate precision (R2 = 0.68) and accuracy (root mean squared error = 1.60 kg/d) metrics on test data. Our results indicate that gradient boosting is more suitable for capturing complex nonlinear relationships underlying daily DMI compared with the other models evaluated. Further advancements in ML-based DMI prediction should consider integrating intra- and interindividual variability in feeding behavior and accounting for animal-specific effects.
dc.language.isoeng
dc.rightsopenAccess
dc.titlePredicting individual dry matter intake in Holstein × Gyr cows using behavior-monitoring sensor, phenotypic, and weather data with supervised machine learning.
dc.typeArtigo de periódico
dc.subject.thesagroBovino
dc.subject.thesagroGado Leiteiro
dc.subject.thesagroMatéria Seca
dc.subject.thesagroIngestão
dc.subject.thesagroNutrição Animal
dc.subject.thesagroGado Mestiço
dc.subject.thesagroVaca Leiteira
dc.subject.thesagroGado Holandês
dc.subject.thesagroGado Gir
dc.subject.nalthesaurusDairy cattle
dc.subject.nalthesaurusAnimal nutrition
dc.subject.nalthesaurusCrossbreds
dc.subject.nalthesaurusDairy cows
dc.subject.nalthesaurusDry matter intake
dc.description.notesShort communication.
riaa.ainfo.id1185326
riaa.ainfo.lastupdate2026-03-12
dc.identifier.doihttps://doi.org/10.3168/jdsc.2025-0850
dc.contributor.institutionCAMILA SOUSA DA SILVA, CPAMN; TADEU E. DA SILVA, UNIVERSITY OF VERMONT; ANNA L. L. SGUIZATTO, UNIVERSIDADE FEDERAL DE VIÇOSA.; ANDREIA FERREIRA MACHADO, CNPGL; ABIAS SANTOS SILVA, CPAA; JOÃO H. C. COSTA, UNIVERSITY OF VERMONT; MARIANA MAGALHAES CAMPOS, CNPGL; DOMINGOS SAVIO CAMPOS PACIULLO, CNPGL; CARLOS AUGUSTO DE MIRANDA GOMIDE, CNPGL; MIRTON JOSE FROTA MORENZ, CNPGL.
Aparece en las colecciones:Nota Técnica/Nota científica (CPAMN)

Ficheros en este ítem:
Fichero Descripción TamañoFormato 
PredictingIndividualDryMatterIntakeHolstein.pdf921,85 kBAdobe PDFVista previa
Visualizar/Abrir
Mostrar el registro sencillo del ítem

FacebookTwitterDeliciousLinkedInGoogle BookmarksMySpace