Abstract :
[en] Body weight (BW) of dairy cows is relevant for breeding programs and farm management to assess the maintenance requirements, reproduction performance, or health status of cow. Currently, it is still difficult to follow BW changes of individual cows routinely in large herds. Combined with animal characteristics, milk mid-infrared (MIR) spectrum was proposed as an additional source of information to predict BW under the framework of dairy herd improvement (DHI) programs. However, the presence of less informative variables in the prediction equation could impact negatively its robustness. This research aims to improve the robustness of BW regression models by applying a feature selection before modeling. A total of 5,920 BW records composed of animal characteristics and milk MIR spectrum were collected from Holstein cows. Three feature selection algorithms were applied to select the most informative variables: partial least squares regression (PLS) combined with sum of ranking difference (PLS-SRD), PLS combined with uninformative variables elimination (PLS-UVE), and the output of Elastic Net regression (EN). Four herd independent validation sets and the corresponding remained calibration datasets having on average 163 and 1,708 records, respectively, were used to develop models using PLS or EN approaches. Ten-fold cross-validation was conducted to parametrize each model. Parity, days in milk (DIM), milk yield (MY), and two MIR spectral points were selected as relevant variables to predict BW. PLS (root mean square error of validation, RMSEp = 60 kg) and EN (RMSEp = 60 kg) regressions employing these 5 predictors were more robust than the models developed without MIR or using MIR without feature selection. The EN models had a cross-validation root mean square error of around 53 kg. The 2 MIR points explained up to 4.20% variation in predicting BW. The RMSE of validation sets using another brand of spectrometer were around 64 kg. This study confirms the possibility to predict an indicator of BW from animal characteristics and MIR variables. The variable selection procedures improved the model's robustness and transferability. The accuracy of BW prediction seems to be sufficient to provide useful information for breeding program and farm management decisions under a DHI framework.
Funding text :
The Genotype Plus Environment (GplusE) Project has received funding from the European Union’s Seventh Framework Programme for research, technological development, and demonstration under grant agreement no. 613689. The authors also acknowledge the National Fund for Scientific Research for its support through the PDR SimBa project (T022119F).The China Scholarship Council ( CSC ) is gratefully acknowledged for funding Mr. Zhang’s PhD grant.The China Scholarship Council (CSC) is gratefully acknowledged for funding Mr. Zhang's PhD grant. The members of GplusE Consortium which including: Mark Crowe, Alan Fahey, Fiona Carter, Elizabeth Matthews, Andreia Santoro, Colin Byrne, Pauline Rudd, Roisin O'Flaherty, Sinead Hallinan, Claire Wathes, Mazdak Salavati, Zhangrui Cheng, Ali Fouladi, Geoff Pollott, Dirk Werling, Beatriz Sanz Bernardo, Conrad Ferris, Alistair Wylie, Matt Bell, Mieke Vaneetvelde, Kristof Hermans, Miel Hostens, Geert Opsomer, Sander Moerman, Jenne De Koster, Hannes Bogaert, Jan Vandepitte, Leila Vandevelde, Bonny Vanranst, Klaus Ingvartsen, Martin Tang Sorensen, Johanna Hoglund, Susanne Dahl, Soren Ostergaard, Janne Rothmann, Mogens Krogh, Else Meyer, Leslie Foldager, Charlotte Gaillard, Jehan Ettema, Tine Rousing, Torben Larsen, Victor H. Silva de Oliveira, Cinzia Marchitelli, Federica Signorelli, Francesco Napolitano, Bianca Moioli, Alessandra Cris?, Luca Buttazzoni, Jennifer McClure, Daragh Matthews, Francis Kearney, Andrew Cromie, Matt McClure, Shujun Zhang, Xing Chen, Huanchun Chen, Junlong Zhao, Liguo Yang, Guohua Hua, Chen Tan, Guiqiang Wang, Michel Bonneau, Marl?ne Sciarretta, Armin Pearn, Arnold Evertson, Linda Kosten, Anders Fogh, Thomas Andersen, Matthew Lucy, Chris Elsik, Gavin Conant, Jerry Taylor, Deborah Triant, Nicolas Gengler, Michel Georges, Frederic Colinet, Marilou Ramos Pamplona, Hedi Hammami, Catherine Bastin, Haruko Takeda, Aurelie Laine, Anne-Sophie Van Laere, Rodrigo Mota, Saied Naderi Darbagshahi, Frederic Dehareng, Clement Grelet, Amelie Vanlierde, Eric Froidmont, Frank Becker, Martin Schulze, and Sergio Palma Vera are deeply acknowledged in this study. The authors gratefully thank the farmers and staff of milk recording organizations for the collection of data used in this study: Ellinbank (Australia), University of liege (Liege, Belgium), Walloon Agricultural Research Centre (Gembloux, Belgium), University of Alberta (Alberta, Canada), Aarhus University (Tjele, Denmark), Agri-Food and Biosciences Institute (Northern Ireland), University College Dublin (Dublin, Ireland), Walloon Breeding Association (Ciney, Belgium), and Leibniz Institute for Farm Animal Biology (Dummerstorf, Germany). The Genotype Plus Environment (GplusE) Project has received funding from the European Union's Seventh Framework Programme for research, technological development, and demonstration under grant agreement no. 613689. The authors also acknowledge the National Fund for Scientific Research for its support through the PDR SimBa project (T022119F). This work was carried out in accordance with the EU Directive 2010/63/EU for animal experiments.
Scopus citations®
without self-citations
11
