Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 2.19 MB
Add to list
  1. Search results
  2. Leveraging latent representations for...

Leveraging latent representations for milk yield prediction and interpolation using deep learning

Arno Liseune, Matthieu Salamone (UGent) , Dirk Van den Poel (UGent) , Bonifacius Van Ranst (UGent) and Miel Hostens (UGent)
(2020) COMPUTERS AND ELECTRONICS IN AGRICULTURE. 175.
Author
Organization
Abstract
In this study, we propose a lactation model that estimates the daily milk yield by using autoencoders to generate a latent representation of all milk yields observed during the entire lactation cycle, irrespective of the length of the time interval between the different measurements. More specifically, we propose a sequential autoencoder (SAE) to process the sequential data, extract and decode the low-dimensional representations and generate the milk yield sequences. The SAE is compared with a more traditional multilayer perceptron model (MLP) which uses herd and parity information and lagged milk yields as input. Results show that incorporating the recorded daily milk yields, lactation number, herd statistics as well as reproduction and health events the cow encountered during the lactation cycle results in the most qualitative latent representations. Moreover, by leveraging these low-dimensional encodings, the SAE reconstructed the entire milk yield curve with a higher accuracy than the MLP. Hence, we present a framework that is able to infer missing milk yields along the entire lactation curve which facilitates selection and culling decisions as well as the estimation of future earnings and costs. Furthermore, the model allows farmers to enhance their animal monitoring systems as it incorporates the sequence of health and reproduction events to forecast the cow's future productivity.
Keywords
Milk yield prediction, Milk yield interpolation, Animal monitoring, Deep learning, Autoencoder, Convolutional neural network

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 2.19 MB

Citation

Please use this url to cite or link to this publication:

MLA
Liseune, Arno, et al. “Leveraging Latent Representations for Milk Yield Prediction and Interpolation Using Deep Learning.” COMPUTERS AND ELECTRONICS IN AGRICULTURE, vol. 175, 2020, doi:10.1016/j.compag.2020.105600.
APA
Liseune, A., Salamone, M., Van den Poel, D., Van Ranst, B., & Hostens, M. (2020). Leveraging latent representations for milk yield prediction and interpolation using deep learning. COMPUTERS AND ELECTRONICS IN AGRICULTURE, 175. https://doi.org/10.1016/j.compag.2020.105600
Chicago author-date
Liseune, Arno, Matthieu Salamone, Dirk Van den Poel, Bonifacius Van Ranst, and Miel Hostens. 2020. “Leveraging Latent Representations for Milk Yield Prediction and Interpolation Using Deep Learning.” COMPUTERS AND ELECTRONICS IN AGRICULTURE 175. https://doi.org/10.1016/j.compag.2020.105600.
Chicago author-date (all authors)
Liseune, Arno, Matthieu Salamone, Dirk Van den Poel, Bonifacius Van Ranst, and Miel Hostens. 2020. “Leveraging Latent Representations for Milk Yield Prediction and Interpolation Using Deep Learning.” COMPUTERS AND ELECTRONICS IN AGRICULTURE 175. doi:10.1016/j.compag.2020.105600.
Vancouver
1.
Liseune A, Salamone M, Van den Poel D, Van Ranst B, Hostens M. Leveraging latent representations for milk yield prediction and interpolation using deep learning. COMPUTERS AND ELECTRONICS IN AGRICULTURE. 2020;175.
IEEE
[1]
A. Liseune, M. Salamone, D. Van den Poel, B. Van Ranst, and M. Hostens, “Leveraging latent representations for milk yield prediction and interpolation using deep learning,” COMPUTERS AND ELECTRONICS IN AGRICULTURE, vol. 175, 2020.
@article{8682760,
  abstract     = {{In this study, we propose a lactation model that estimates the daily milk yield by using autoencoders to generate a latent representation of all milk yields observed during the entire lactation cycle, irrespective of the length of the time interval between the different measurements. More specifically, we propose a sequential autoencoder (SAE) to process the sequential data, extract and decode the low-dimensional representations and generate the milk yield sequences. The SAE is compared with a more traditional multilayer perceptron model (MLP) which uses herd and parity information and lagged milk yields as input. Results show that incorporating the recorded daily milk yields, lactation number, herd statistics as well as reproduction and health events the cow encountered during the lactation cycle results in the most qualitative latent representations. Moreover, by leveraging these low-dimensional encodings, the SAE reconstructed the entire milk yield curve with a higher accuracy than the MLP. Hence, we present a framework that is able to infer missing milk yields along the entire lactation curve which facilitates selection and culling decisions as well as the estimation of future earnings and costs. Furthermore, the model allows farmers to enhance their animal monitoring systems as it incorporates the sequence of health and reproduction events to forecast the cow's future productivity.}},
  articleno    = {{105600}},
  author       = {{Liseune, Arno and Salamone, Matthieu and Van den Poel, Dirk and Van Ranst, Bonifacius and Hostens, Miel}},
  issn         = {{0168-1699}},
  journal      = {{COMPUTERS AND ELECTRONICS IN AGRICULTURE}},
  keywords     = {{Milk yield prediction,Milk yield interpolation,Animal monitoring,Deep learning,Autoencoder,Convolutional neural network}},
  language     = {{eng}},
  pages        = {{11}},
  title        = {{Leveraging latent representations for milk yield prediction and interpolation using deep learning}},
  url          = {{http://doi.org/10.1016/j.compag.2020.105600}},
  volume       = {{175}},
  year         = {{2020}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: