Multiple Country Approach to Improve the Test-Day Prediction of Dairy Cows’ Dry Matter Intake
We predicted dry matter intake of dairy cows using parity, week of lactation, milk yield, milk mid-infrared (MIR) spectrum, and MIR-based predictions of bodyweight, fat, protein, lactose, and fatty acids content in milk. The dataset comprised 10,711 samples of 534 dairy cows with a geographical dive...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/11/5/1316 |
| _version_ | 1797535327733153792 |
|---|---|
| author | Anthony Tedde Clément Grelet Phuong N. Ho Jennie E. Pryce Dagnachew Hailemariam Zhiquan Wang Graham Plastow Nicolas Gengler Eric Froidmont Frédéric Dehareng Carlo Bertozzi Mark A. Crowe Hélène Soyeurt on behalf of the GplusE Consortium |
| author_facet | Anthony Tedde Clément Grelet Phuong N. Ho Jennie E. Pryce Dagnachew Hailemariam Zhiquan Wang Graham Plastow Nicolas Gengler Eric Froidmont Frédéric Dehareng Carlo Bertozzi Mark A. Crowe Hélène Soyeurt on behalf of the GplusE Consortium |
| author_sort | Anthony Tedde |
| collection | DOAJ |
| description | We predicted dry matter intake of dairy cows using parity, week of lactation, milk yield, milk mid-infrared (MIR) spectrum, and MIR-based predictions of bodyweight, fat, protein, lactose, and fatty acids content in milk. The dataset comprised 10,711 samples of 534 dairy cows with a geographical diversity (Australia, Canada, Denmark, and Ireland). We set up partial least square (PLS) regressions with different constructs and a one-hidden-layer artificial neural network (ANN) using the highest contribution variables. In the ANN, we replaced the spectra with their projections to the 25 first PLS factors explaining 99% of the spectral variability to reduce the model complexity. Cow-independent 10 × 10-fold cross-validation (CV) achieved the best performance with root mean square errors (RMSE<sub>CV</sub>) of 3.27 ± 0.08 kg for the PLS regression and 3.25 ± 0.13 kg for ANN. Although the available data were significantly different, we also performed a country-independent validation (CIV) to measure the models’ performance fairly. We found RMSE<sub>CIV</sub> varying from 3.73 to 6.03 kg for PLS and 3.69 to 5.08 kg for ANN. Ultimately, based on the country-independent validation, we discussed the developed models’ performance with those achieved by the National Research Council’s equation. |
| first_indexed | 2024-03-10T11:42:53Z |
| format | Article |
| id | doaj.art-ed2a6fe4f9e648e0beefaed7f5260e47 |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-03-10T11:42:53Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-ed2a6fe4f9e648e0beefaed7f5260e472023-11-21T18:21:14ZengMDPI AGAnimals2076-26152021-05-01115131610.3390/ani11051316Multiple Country Approach to Improve the Test-Day Prediction of Dairy Cows’ Dry Matter IntakeAnthony Tedde0Clément Grelet1Phuong N. Ho2Jennie E. Pryce3Dagnachew Hailemariam4Zhiquan Wang5Graham Plastow6Nicolas Gengler7Eric Froidmont8Frédéric Dehareng9Carlo Bertozzi10Mark A. Crowe11Hélène Soyeurt12on behalf of the GplusE ConsortiumAGROBIOCHEM Department, Research and Teaching Centre (TERRA), Gembloux Agro-Bio Tech, University of Liège, 5030 Gembloux, BelgiumWalloon Agricultural Research Center (CRA-W), 5030 Gembloux, BelgiumAgriculture Victoria Research, Centre for AgriBioscience, AgriBio, Bundoora, VIC 3083, AustraliaAgriculture Victoria Research, Centre for AgriBioscience, AgriBio, Bundoora, VIC 3083, AustraliaDepartment of Agricultural, Food and Nutritional Science, University of Alberta, Edmonton, AB T6G 2P5, CanadaDepartment of Agricultural, Food and Nutritional Science, University of Alberta, Edmonton, AB T6G 2P5, CanadaDepartment of Agricultural, Food and Nutritional Science, University of Alberta, Edmonton, AB T6G 2P5, CanadaAGROBIOCHEM Department, Research and Teaching Centre (TERRA), Gembloux Agro-Bio Tech, University of Liège, 5030 Gembloux, BelgiumWalloon Agricultural Research Center (CRA-W), 5030 Gembloux, BelgiumWalloon Agricultural Research Center (CRA-W), 5030 Gembloux, BelgiumWalloon Breeding Association, 5590 Ciney, BelgiumUCD School of Veterinary Medicine, University College Dublin, Dublin 4, IrelandAGROBIOCHEM Department, Research and Teaching Centre (TERRA), Gembloux Agro-Bio Tech, University of Liège, 5030 Gembloux, BelgiumWe predicted dry matter intake of dairy cows using parity, week of lactation, milk yield, milk mid-infrared (MIR) spectrum, and MIR-based predictions of bodyweight, fat, protein, lactose, and fatty acids content in milk. The dataset comprised 10,711 samples of 534 dairy cows with a geographical diversity (Australia, Canada, Denmark, and Ireland). We set up partial least square (PLS) regressions with different constructs and a one-hidden-layer artificial neural network (ANN) using the highest contribution variables. In the ANN, we replaced the spectra with their projections to the 25 first PLS factors explaining 99% of the spectral variability to reduce the model complexity. Cow-independent 10 × 10-fold cross-validation (CV) achieved the best performance with root mean square errors (RMSE<sub>CV</sub>) of 3.27 ± 0.08 kg for the PLS regression and 3.25 ± 0.13 kg for ANN. Although the available data were significantly different, we also performed a country-independent validation (CIV) to measure the models’ performance fairly. We found RMSE<sub>CIV</sub> varying from 3.73 to 6.03 kg for PLS and 3.69 to 5.08 kg for ANN. Ultimately, based on the country-independent validation, we discussed the developed models’ performance with those achieved by the National Research Council’s equation.https://www.mdpi.com/2076-2615/11/5/1316dry matter intakepartial least squareartificial neural networkdimensionality reductionmachine learningdairy cows |
| spellingShingle | Anthony Tedde Clément Grelet Phuong N. Ho Jennie E. Pryce Dagnachew Hailemariam Zhiquan Wang Graham Plastow Nicolas Gengler Eric Froidmont Frédéric Dehareng Carlo Bertozzi Mark A. Crowe Hélène Soyeurt on behalf of the GplusE Consortium Multiple Country Approach to Improve the Test-Day Prediction of Dairy Cows’ Dry Matter Intake Animals dry matter intake partial least square artificial neural network dimensionality reduction machine learning dairy cows |
| title | Multiple Country Approach to Improve the Test-Day Prediction of Dairy Cows’ Dry Matter Intake |
| title_full | Multiple Country Approach to Improve the Test-Day Prediction of Dairy Cows’ Dry Matter Intake |
| title_fullStr | Multiple Country Approach to Improve the Test-Day Prediction of Dairy Cows’ Dry Matter Intake |
| title_full_unstemmed | Multiple Country Approach to Improve the Test-Day Prediction of Dairy Cows’ Dry Matter Intake |
| title_short | Multiple Country Approach to Improve the Test-Day Prediction of Dairy Cows’ Dry Matter Intake |
| title_sort | multiple country approach to improve the test day prediction of dairy cows dry matter intake |
| topic | dry matter intake partial least square artificial neural network dimensionality reduction machine learning dairy cows |
| url | https://www.mdpi.com/2076-2615/11/5/1316 |
| work_keys_str_mv | AT anthonytedde multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT clementgrelet multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT phuongnho multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT jennieepryce multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT dagnachewhailemariam multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT zhiquanwang multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT grahamplastow multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT nicolasgengler multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT ericfroidmont multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT fredericdehareng multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT carlobertozzi multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT markacrowe multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT helenesoyeurt multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake AT onbehalfofthegpluseconsortium multiplecountryapproachtoimprovethetestdaypredictionofdairycowsdrymatterintake |