Validation of Dairy Cow Bodyweight Prediction Using Traits Easily Recorded by Dairy Herd Improvement Organizations and Its Potential Improvement Using Feature Selection Algorithms

Anthony Tedde; Clément Grelet; Phuong N. Ho; Jennie E. Pryce; Dagnachew Hailemariam; Zhiquan Wang; Graham Plastow; Nicolas Gengler; Yves Brostaux; Eric Froidmont; Frédéric Dehareng; Carlo Bertozzi; Mark Crowe; Isabelle Dufrasne; Hélène Soyeurt; GplusE Consortium Group

doi:10.3390/ani11051288

Validation of Dairy Cow Bodyweight Prediction Using Traits Easily Recorded by Dairy Herd Improvement Organizations and Its Potential Improvement Using Feature Selection Algorithms

Anthony Tedde^*, Clément Grelet, Phuong N. Ho, Jennie E. Pryce, Dagnachew Hailemariam, Zhiquan Wang, Graham Plastow, Nicolas Gengler, Yves Brostaux, Eric Froidmont, Frédéric Dehareng, Carlo Bertozzi, Mark Crowe, Isabelle Dufrasne, Hélène Soyeurt, GplusE Consortium Group

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

10 Citations (Scopus)

Abstract

Knowing the body weight (BW) of a cow at a specific moment or measuring its changes through time is of interest for management purposes. The current work aimed to validate the feasibility of predicting BW using the day in milk, parity, milk yield, and milk mid-infrared (MIR) spectrum from a multiple-country dataset and reduce the number of predictors to limit the risk of over-fitting and potentially improve its accuracy. The BW modeling procedure involved feature selections and herd-independent validation in identifying the most interesting subsets of predictors and then external validation of the models. From 1849 records collected in 9 herds from 360 Holstein cows, the best performing models achieved a root mean square error (RMSE) for the herd-independent validation between 52 ± 2.34 kg to 56 ± 3.16 kg, including from 5 to 62 predictors. Among these models, three performed remarkably well in external validation using an independent dataset (N = 4067), resulting in RMSE ranging from 52 to 56 kg. The results suggest that multiple optimal BW predictive models coexist due to the high correlations between adjacent spectral points.

Original language	English
Article number	1288
Journal	Animals
Volume	11
Issue number	5
DOIs	https://doi.org/10.3390/ani11051288
Publication status	Print publication - 30 Apr 2021
Externally published	Yes

Bibliographical note

Funding Information:
Acknowledgments: This work is Supported by the Luxembourg National Research Fund (INTER/FNRS/18/12987586/SimBa) and by the Fonds de la Recherche Scientifique-FNRS under Grant n◦ T.0221.19. 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. List of authors in the GplusE consortium: Mark Crowe, Alan Fahey, Fiona Carter, Elizabeth Matthews, An-dreia 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 Moer-man, 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 Crisà, 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, Marlène 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. The views expressed in this publication are the authors’ sole responsibility and do not necessarily reflect the views of the European Commission. The authors acknowledge the laboratory “Comité du Lait” (Battice, Belgium) for the Walloon milk mid-infrared spectra. The authors acknowledge the financial support of the National Fund for the Scientific Research (F.R.S-FNRS) for the SimBa research project (T02211). This project is also co-financed by the Luxembourg National Research Fund (FNR). Computational resources have been provided by the Consortium des Équipements de Calcul Intensif (CÉCI), funded by the Fonds de la Recherche Scientifique de Belgique (F.R.S.-FNRS) under Grant No. 2.5020.11 and by the Walloon Region.

Funding Information:
Funding: This research was funded by National Fund for the Scientific Research (F.R.S-FNRS) for the SimBa research project, grant number T.0221.19.

Publisher Copyright:
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.

Keywords

Dairy cow bodyweight
Dairy cows
Dimensionality reduction
Feature selection
Machine learning
Mid infrared spectra
Partial least square

Access to Document

10.3390/ani11051288

Cite this

Tedde, A., Grelet, C., Ho, P. N., Pryce, J. E., Hailemariam, D., Wang, Z., Plastow, G., Gengler, N., Brostaux, Y., Froidmont, E., Dehareng, F., Bertozzi, C., Crowe, M., Dufrasne, I., Soyeurt, H., & GplusE Consortium Group (2021). Validation of Dairy Cow Bodyweight Prediction Using Traits Easily Recorded by Dairy Herd Improvement Organizations and Its Potential Improvement Using Feature Selection Algorithms. Animals, 11(5), Article 1288. https://doi.org/10.3390/ani11051288

@article{472360351d674897b628a2bdef9fea9c,

title = "Validation of Dairy Cow Bodyweight Prediction Using Traits Easily Recorded by Dairy Herd Improvement Organizations and Its Potential Improvement Using Feature Selection Algorithms",

abstract = "Knowing the body weight (BW) of a cow at a specific moment or measuring its changes through time is of interest for management purposes. The current work aimed to validate the feasibility of predicting BW using the day in milk, parity, milk yield, and milk mid-infrared (MIR) spectrum from a multiple-country dataset and reduce the number of predictors to limit the risk of over-fitting and potentially improve its accuracy. The BW modeling procedure involved feature selections and herd-independent validation in identifying the most interesting subsets of predictors and then external validation of the models. From 1849 records collected in 9 herds from 360 Holstein cows, the best performing models achieved a root mean square error (RMSE) for the herd-independent validation between 52 ± 2.34 kg to 56 ± 3.16 kg, including from 5 to 62 predictors. Among these models, three performed remarkably well in external validation using an independent dataset (N = 4067), resulting in RMSE ranging from 52 to 56 kg. The results suggest that multiple optimal BW predictive models coexist due to the high correlations between adjacent spectral points.",

keywords = "Dairy cow bodyweight, Dairy cows, Dimensionality reduction, Feature selection, Machine learning, Mid infrared spectra, Partial least square",

author = "Anthony Tedde and Cl{\'e}ment Grelet and Ho, {Phuong N.} and Pryce, {Jennie E.} and Dagnachew Hailemariam and Zhiquan Wang and Graham Plastow and Nicolas Gengler and Yves Brostaux and Eric Froidmont and Fr{\'e}d{\'e}ric Dehareng and Carlo Bertozzi and Mark Crowe and Isabelle Dufrasne and H{\'e}l{\`e}ne Soyeurt and Mark Crowe and Alan Fahey and Fiona Carter and Elizabeth Matthews and Santoro, {An Dreia} and Colin Byrne and Pauline Rudd and Roisin O{\textquoteright}flaherty and Sinead Hallinan and Claire Wathes and Mazdak Salavati and Zhangrui Cheng and Ali Fouladi and Geoff Pollott and Dirk Werling and Bernardo, {Beatriz Sanz} and Conrad Ferris and Alistair Wylie and Matt Bell and Mieke Vaneetvelde and Kristof Hermans and Miel Hostens and Geert Opsomer and Sander Moer-Man and {De Koster}, Jenne and Hannes Bogaert and Jan Vandepitte and Leila Vandevelde and Bonny Vanranst and Klaus Ingvartsen and Sorensen, {Martin Tang} and Johanna Hoglund and Susanne Dahl and Soren Ostergaard and Janne Rothmann and Mogens Krogh and Else Meyer and Leslie Foldager and Charlotte Gaillard and Jehan Ettema and Tine Rousing and Torben Larsen and {Silva de Oliveira}, {Victor H.} and Cinzia Marchitelli and Federica Signorelli and Francesco Napolitano and Bianca Moioli and Alessandra Cris{\`a} and Luca Buttazzoni and Jennifer McClure and Daragh Matthews and Francis Kearney and Andrew Cromie and Matt McClure and Shujun Zhang and Xing Chen and Huanchun Chen and Junlong Zhao and Liguo Yang and Guohua Hua and Chen Tan and Guiqiang Wang and Michel Bonneau and Marl{\`e}ne Sciarretta and Armin Pearn and {GplusE Consortium Group}",

note = "Funding Information: Acknowledgments: This work is Supported by the Luxembourg National Research Fund (INTER/FNRS/18/12987586/SimBa) and by the Fonds de la Recherche Scientifique-FNRS under Grant n◦ T.0221.19. The Genotype Plus Environment (GplusE) Project has received funding from the European Union{\textquoteright}s Seventh Framework Programme for research, technological development, and demonstration under grant agreement no. 613689. List of authors in the GplusE consortium: Mark Crowe, Alan Fahey, Fiona Carter, Elizabeth Matthews, An-dreia Santoro, Colin Byrne, Pauline Rudd, Roisin O{\textquoteright}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 Moer-man, 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{\`a}, 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{\`e}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. The views expressed in this publication are the authors{\textquoteright} sole responsibility and do not necessarily reflect the views of the European Commission. The authors acknowledge the laboratory “Comit{\'e} du Lait” (Battice, Belgium) for the Walloon milk mid-infrared spectra. The authors acknowledge the financial support of the National Fund for the Scientific Research (F.R.S-FNRS) for the SimBa research project (T02211). This project is also co-financed by the Luxembourg National Research Fund (FNR). Computational resources have been provided by the Consortium des {\'E}quipements de Calcul Intensif (C{\'E}CI), funded by the Fonds de la Recherche Scientifique de Belgique (F.R.S.-FNRS) under Grant No. 2.5020.11 and by the Walloon Region. Funding Information: Funding: This research was funded by National Fund for the Scientific Research (F.R.S-FNRS) for the SimBa research project, grant number T.0221.19. Publisher Copyright: {\textcopyright} 2021 by the authors. Licensee MDPI, Basel, Switzerland.",

year = "2021",

month = apr,

day = "30",

doi = "10.3390/ani11051288",

language = "English",

volume = "11",

journal = "Animals",

issn = "2076-2615",

publisher = "MDPI Multidisciplinary Digital Publishing Institute",

number = "5",

}

Tedde, A, Grelet, C, Ho, PN, Pryce, JE, Hailemariam, D, Wang, Z, Plastow, G, Gengler, N, Brostaux, Y, Froidmont, E, Dehareng, F, Bertozzi, C, Crowe, M, Dufrasne, I, Soyeurt, H & GplusE Consortium Group 2021, 'Validation of Dairy Cow Bodyweight Prediction Using Traits Easily Recorded by Dairy Herd Improvement Organizations and Its Potential Improvement Using Feature Selection Algorithms', Animals, vol. 11, no. 5, 1288. https://doi.org/10.3390/ani11051288

TY - JOUR

T1 - Validation of Dairy Cow Bodyweight Prediction Using Traits Easily Recorded by Dairy Herd Improvement Organizations and Its Potential Improvement Using Feature Selection Algorithms

AU - Tedde, Anthony

AU - Grelet, Clément

AU - Ho, Phuong N.

AU - Pryce, Jennie E.

AU - Hailemariam, Dagnachew

AU - Wang, Zhiquan

AU - Plastow, Graham

AU - Gengler, Nicolas

AU - Brostaux, Yves

AU - Froidmont, Eric

AU - Dehareng, Frédéric

AU - Bertozzi, Carlo

AU - Crowe, Mark

AU - Dufrasne, Isabelle

AU - Soyeurt, Hélène

AU - Crowe, Mark

AU - Fahey, Alan

AU - Carter, Fiona

AU - Matthews, Elizabeth

AU - Santoro, An Dreia

AU - Byrne, Colin

AU - Rudd, Pauline

AU - O’flaherty, Roisin

AU - Hallinan, Sinead

AU - Wathes, Claire

AU - Salavati, Mazdak

AU - Cheng, Zhangrui

AU - Fouladi, Ali

AU - Pollott, Geoff

AU - Werling, Dirk

AU - Bernardo, Beatriz Sanz

AU - Ferris, Conrad

AU - Wylie, Alistair

AU - Bell, Matt

AU - Vaneetvelde, Mieke

AU - Hermans, Kristof

AU - Hostens, Miel

AU - Opsomer, Geert

AU - Moer-Man, Sander

AU - De Koster, Jenne

AU - Bogaert, Hannes

AU - Vandepitte, Jan

AU - Vandevelde, Leila

AU - Vanranst, Bonny

AU - Ingvartsen, Klaus

AU - Sorensen, Martin Tang

AU - Hoglund, Johanna

AU - Dahl, Susanne

AU - Ostergaard, Soren

AU - Rothmann, Janne

AU - Krogh, Mogens

AU - Meyer, Else

AU - Foldager, Leslie

AU - Gaillard, Charlotte

AU - Ettema, Jehan

AU - Rousing, Tine

AU - Larsen, Torben

AU - Silva de Oliveira, Victor H.

AU - Marchitelli, Cinzia

AU - Signorelli, Federica

AU - Napolitano, Francesco

AU - Moioli, Bianca

AU - Crisà, Alessandra

AU - Buttazzoni, Luca

AU - McClure, Jennifer

AU - Matthews, Daragh

AU - Kearney, Francis

AU - Cromie, Andrew

AU - McClure, Matt

AU - Zhang, Shujun

AU - Chen, Xing

AU - Chen, Huanchun

AU - Zhao, Junlong

AU - Yang, Liguo

AU - Hua, Guohua

AU - Tan, Chen

AU - Wang, Guiqiang

AU - Bonneau, Michel

AU - Sciarretta, Marlène

AU - Pearn, Armin

AU - GplusE Consortium Group

N1 - Funding Information: Acknowledgments: This work is Supported by the Luxembourg National Research Fund (INTER/FNRS/18/12987586/SimBa) and by the Fonds de la Recherche Scientifique-FNRS under Grant n◦ T.0221.19. 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. List of authors in the GplusE consortium: Mark Crowe, Alan Fahey, Fiona Carter, Elizabeth Matthews, An-dreia 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 Moer-man, 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 Crisà, 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, Marlène 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. The views expressed in this publication are the authors’ sole responsibility and do not necessarily reflect the views of the European Commission. The authors acknowledge the laboratory “Comité du Lait” (Battice, Belgium) for the Walloon milk mid-infrared spectra. The authors acknowledge the financial support of the National Fund for the Scientific Research (F.R.S-FNRS) for the SimBa research project (T02211). This project is also co-financed by the Luxembourg National Research Fund (FNR). Computational resources have been provided by the Consortium des Équipements de Calcul Intensif (CÉCI), funded by the Fonds de la Recherche Scientifique de Belgique (F.R.S.-FNRS) under Grant No. 2.5020.11 and by the Walloon Region. Funding Information: Funding: This research was funded by National Fund for the Scientific Research (F.R.S-FNRS) for the SimBa research project, grant number T.0221.19. Publisher Copyright: © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

PY - 2021/4/30

Y1 - 2021/4/30

N2 - Knowing the body weight (BW) of a cow at a specific moment or measuring its changes through time is of interest for management purposes. The current work aimed to validate the feasibility of predicting BW using the day in milk, parity, milk yield, and milk mid-infrared (MIR) spectrum from a multiple-country dataset and reduce the number of predictors to limit the risk of over-fitting and potentially improve its accuracy. The BW modeling procedure involved feature selections and herd-independent validation in identifying the most interesting subsets of predictors and then external validation of the models. From 1849 records collected in 9 herds from 360 Holstein cows, the best performing models achieved a root mean square error (RMSE) for the herd-independent validation between 52 ± 2.34 kg to 56 ± 3.16 kg, including from 5 to 62 predictors. Among these models, three performed remarkably well in external validation using an independent dataset (N = 4067), resulting in RMSE ranging from 52 to 56 kg. The results suggest that multiple optimal BW predictive models coexist due to the high correlations between adjacent spectral points.

AB - Knowing the body weight (BW) of a cow at a specific moment or measuring its changes through time is of interest for management purposes. The current work aimed to validate the feasibility of predicting BW using the day in milk, parity, milk yield, and milk mid-infrared (MIR) spectrum from a multiple-country dataset and reduce the number of predictors to limit the risk of over-fitting and potentially improve its accuracy. The BW modeling procedure involved feature selections and herd-independent validation in identifying the most interesting subsets of predictors and then external validation of the models. From 1849 records collected in 9 herds from 360 Holstein cows, the best performing models achieved a root mean square error (RMSE) for the herd-independent validation between 52 ± 2.34 kg to 56 ± 3.16 kg, including from 5 to 62 predictors. Among these models, three performed remarkably well in external validation using an independent dataset (N = 4067), resulting in RMSE ranging from 52 to 56 kg. The results suggest that multiple optimal BW predictive models coexist due to the high correlations between adjacent spectral points.

KW - Dairy cow bodyweight

KW - Dairy cows

KW - Dimensionality reduction

KW - Feature selection

KW - Machine learning

KW - Mid infrared spectra

KW - Partial least square

UR - http://www.scopus.com/inward/record.url?scp=85106548935&partnerID=8YFLogxK

U2 - 10.3390/ani11051288

DO - 10.3390/ani11051288

M3 - Article

C2 - 33946238

AN - SCOPUS:85106548935

SN - 2076-2615

VL - 11

JO - Animals

JF - Animals

IS - 5

M1 - 1288

ER -

Validation of Dairy Cow Bodyweight Prediction Using Traits Easily Recorded by Dairy Herd Improvement Organizations and Its Potential Improvement Using Feature Selection Algorithms

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this