Predicting individual dry matter intake in Holstein × Gyr cows using behavior-monitoring sensor, phenotypic, and weather data with supervised machine learning

JDS Communications 2026 Open access

Read full text
Authors: Camila S. da Silva, Tadeu E Silva, Anna Luiza Lacerda Sguizzato, Andréia Ferreira Machado, Abias Santos [UNESP] Silva, J.H.C. Costa, Mariana Magalhães Campos, D.S.C. Paciullo, Carlos Augusto de Miranda Gomide, Mirton José Frota Morenz
DOI: 10.3168/jdsc.2025-0850
Cited by: 0
References: 16

Abstract

= 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.

Fields of Study & Subjects

Smart Agriculture and AI Ruminant Nutrition and Digestive Physiology Effects of Environmental Stressors on Livestock

Publication details

Journal / source
JDS Communications
Volume
7
Issue
2
Pages
179–184
Publication date
16 January 2026
Language
EN