DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication
Artículo científico (JournalArticle)
Harnessing ensemble models for improved lactation curve modeling: The R package EMOTIONS
16 páginas, 6 figuras., Lactation curve modeling plays a key role in dairy production, supporting on-farm management decisions and the selection of animals with superior productivity and resilience. However, accurately choosing a single model to represent the diversity of lactation patterns across individuals remains challenging. In this context, we presented in this study a flexible ensemble modeling (EM) framework, implemented in the EMOTIONS R package, to improve the prediction of daily milk yield and related traits in dairy cows and ewes. The EMOTIONS package integrates a wide set of lactation curve models and allows users to generate ensembles by weighting model predictions based on multiple criteria. The package provides tools for model fitting, ensemble creation, visualization, milk yield imputation, detection of milk loss events, and the estimation of residual-based resilience indicators. The advantages of the ensembles were evident in subsets of animals with poor individual model fits, underscoring the value of EM in capturing individual variation and reducing underfitting. In datasets from both ewes and cows analyzed as examples, the EM advantages were clear for subsets of individual lactations with overall poor model fittings (based on the Bayesian information criterion). Overall, EM represent a robust and adaptable approach for modeling lactation data, offering improved predictive accuracy while retaining the ability to interpret biologically meaningful model parameters., This work was co-funded by the European Union’s
Horizon Europe Project 101136346 EUPAHW (Brussels,
Belgium). Views and opinions expressed are, however,
those of the authors only and do not necessarily reflect
those of the European Union or the European Research
Executive Agency. Neither the European Union nor the
granting authority can be held responsible for them. R.
Arribas-Gonzalo holds a predoctoral grant from the MCIN
(Ref. PRE2022-000439; Madrid, Spain). A. C. de Faria
was funded by a predoctoral fellowship from the European Social Fund Plus (Brussels, Belgium), the Operational
Programme of Castilla y León (Valladolid, Spain), and
the Junta de Castilla y León, represented by the Consejería de Educación (Valladolid, Spain). The sheep milk
production data were provided by collaborating farmers
of the ASSAFE breeders’ association for the development
of the ResilSheep-Database within the framework of the
Spanish national project RESILSHEEP (Ref. PID2022-
138676OB-100, MCIN/AEI/10.13039/501100011033/
FEDER, UE; Madrid, Spain). We sincerely acknowledge
the valuable contribution of the collaborating farmers
and the ASSAFE association for providing the data, as
well as DeLaval (Tumba, Sweden) for technical support.
Luiz F. Brito thanks the Purdue College of Agriculture
and Purdue Ag Data Services for supporting the development of the Purdue Animal Sciences Data Ecosystem
(PASDE; Boerman et al., 2025; West Lafayette, IN). The
authors also thank Homestead Dairy LLC (Plymouth,
IN), and especially Brian and Jill Houin, for allowing our
research group to use their farm records for research purposes. Supplemental material for this article is available at https://zenodo.org/records/18558032. Approval from
an Institutional Animal Care and Use Committee was not
required for the purpose of this study, as all necessary
information was obtained from pre-existing databases.
The authors have not stated any conflicts of interest., Peer reviewed
DOI: http://hdl.handle.net/10261/446706, https://api.elsevier.com/content/abstract/scopus_id/105051621245
HANDLE: http://hdl.handle.net/10261/446706, https://api.elsevier.com/content/abstract/scopus_id/105051621245