This paper explores the feasibility of using partial data to assess the pig feed conversion ratio (FCR) and identify the optimal method to predict the overall pig FCR throughout the entire growth period.
Growth performance data, feed intake data, and the pedigree information of a total of 1084 pigs from 2021 to 2022 were used for the study. Four different machine learning methods (Random Forests (RF), Extreme Gradient Boost (XGBoost), Support Vector Regression (SVR), and linear regression (LR)) were compared with the baseline method that simply utilized the known portion of FCR as a proxy for the target prediction. The analysis utilized single-week data as well as different ranges of early-stage and late-stage growth period data. The Pearson correlation coefficient between the overall pig FCR estimated breeding values (EBVs) and the predicted EBVs was used as an indicator to evaluate the prediction accuracy under different scenarios.
The correlation between the FCR of each week and the entire duration FCR was weak, and the entire duration FCR may be affected by a combination of factors rather than just a single week. When using data from a single week to predict the entire duration FCR, RF showed the most stability and accuracy of all models. When using data from the first and second halves to predict the FCR over different time horizons, the predictive performance of all models declined as the prediction span increased. Among them, RF and SVR had better prediction performances across the time windows. Notably, when using the latter half of the data for prediction, the LR model had the best prediction performance.
For the mid-term measurements, when only accuracy is considered, using the latter half of the data is recommended due to its higher representativeness. When the available data cover less than half of the growth period, RF performs better for the prediction, regardless of whether early or late data are used. In contrast, when the measurement data extend beyond the halfway point, a linear model is preferable to predict the overall FCR, as it better captures the representativeness of incomplete FCR data for the overall assessment.
Citation: Di Pan, Caiyun Zhang, Tuowu Li, Zhe Zhang, Qishan Wang, Yuchun Pan, Peipei Ma. Study on pig feed conversion ratio prediction based on machine learning[J]. AIMS Animal Science, 2025, 1(1): 196-215. doi: 10.3934/aas.2025010
This paper explores the feasibility of using partial data to assess the pig feed conversion ratio (FCR) and identify the optimal method to predict the overall pig FCR throughout the entire growth period.
Growth performance data, feed intake data, and the pedigree information of a total of 1084 pigs from 2021 to 2022 were used for the study. Four different machine learning methods (Random Forests (RF), Extreme Gradient Boost (XGBoost), Support Vector Regression (SVR), and linear regression (LR)) were compared with the baseline method that simply utilized the known portion of FCR as a proxy for the target prediction. The analysis utilized single-week data as well as different ranges of early-stage and late-stage growth period data. The Pearson correlation coefficient between the overall pig FCR estimated breeding values (EBVs) and the predicted EBVs was used as an indicator to evaluate the prediction accuracy under different scenarios.
The correlation between the FCR of each week and the entire duration FCR was weak, and the entire duration FCR may be affected by a combination of factors rather than just a single week. When using data from a single week to predict the entire duration FCR, RF showed the most stability and accuracy of all models. When using data from the first and second halves to predict the FCR over different time horizons, the predictive performance of all models declined as the prediction span increased. Among them, RF and SVR had better prediction performances across the time windows. Notably, when using the latter half of the data for prediction, the LR model had the best prediction performance.
For the mid-term measurements, when only accuracy is considered, using the latter half of the data is recommended due to its higher representativeness. When the available data cover less than half of the growth period, RF performs better for the prediction, regardless of whether early or late data are used. In contrast, when the measurement data extend beyond the halfway point, a linear model is preferable to predict the overall FCR, as it better captures the representativeness of incomplete FCR data for the overall assessment.
| [1] |
Pierozan CR, Agostini PDS, Gasa J, et al. (2016) Factors affecting the daily feed intake and feed conversion ratio of pigs in grow-finishing units: The case of a company. Porc Health Manag 2: 1-8. https://doi.org/10.1186/s40813-016-0023-4 doi: 10.1186/s40813-016-0023-4
|
| [2] |
Tusell L, Bergsma R, Gilbert H, et al. (2020) Machine learning prediction of crossbred pig feed efficiency and growth rate from single nucleotide polymorphisms. Front Genet 11: 567818. https://doi.org/10.3389/fgene.2020.567818 doi: 10.3389/fgene.2020.567818
|
| [3] |
Wang L, Hu Q, Wang L, et al. (2022) Predicting the growth performance of growing-finishing pigs based on net energy and digestible lysine intake using multiple regression and artificial neural networks models. J Anim Sci Biotechnol 13: 57. https://doi.org/10.1186/s40104-022-00707-1 doi: 10.1186/s40104-022-00707-1
|
| [4] |
Yin C, Shi H, Zhou P, et al. (2024) Genomic prediction of growth traits in Yorkshire pigs of different reference group sizes using different estimated breeding value models. Animals 14: 1098. https://doi.org/10.3390/ani14071098 doi: 10.3390/ani14071098
|
| [5] |
He Y, Tiezzi F, Howard J, et al. (2021) Predicting body weight in growing pigs from feeding behavior data using machine learning algorithms. Comput Electron Agri 184: 106085. https://doi.org/10.1016/j.compag.2021.106085 doi: 10.1016/j.compag.2021.106085
|
| [6] |
Casey DS, Stern HS, Dekkers JC (2005) Identification of errors and factors associated with errors in data from electronic swine feeders. J Anim Sci 83: 969-982. https://doi.org/10.2527/2005.835969x doi: 10.2527/2005.835969x
|
| [7] |
Poulsen BG, Ask B, Nielsen HM, et al. (2020) Prediction of genetic merit for growth rate in pigs using animal models with indirect genetic effects and genomic information. Genet Select Evolut 52: 58. https://doi.org/10.1186/s12711-020-00578-y doi: 10.1186/s12711-020-00578-y
|
| [8] |
Maltecca C, Lu D, Schillebeeckx C, et al. (2019) Predicting growth and carcass traits in swine using microbiome data and machine learning algorithms. Sci Rep 9: 6574. https://doi.org/10.1038/s41598-019-43031-x doi: 10.1038/s41598-019-43031-x
|
| [9] |
Do DN, Strathe AB, Jensen J, et al. (2013) Genetic parameters for different measures of feed efficiency and related traits in boars of three pig breeds. J Anim Sci 91: 4069-4079. https://doi.org/10.2527/jas.2012-6197 doi: 10.2527/jas.2012-6197
|
| [10] |
Zebua C, Siagian PH (2017) Comparative performance of Landrace, Yorkshire and Duroc breeds of swine. J Indones Trop Anim Agri 42: 145-153. https://doi.org/10.14710/jitaa.42.3.147-152 doi: 10.14710/jitaa.42.3.147-152
|
| [11] |
Yin C, Shi H, Zhou P, et al. (2024) Genomic prediction of growth traits in Yorkshire pigs of different reference group sizes using different estimated breeding value models. Animals 14: 1098. https://doi.org/10.3390/ani14071098 doi: 10.3390/ani14071098
|
| [12] |
Taylor C, Guy J, Bacardit J (2023) Estimating individual-level pig growth trajectories from group-level weight time series using machine learning. Comput Electron Agri 208: 107790. https://doi.org/10.1016/j.compag.2023.107790 doi: 10.1016/j.compag.2023.107790
|
| [13] |
Alsahaf A, Azzopardi G, Ducro B, et al. (2018) Prediction of slaughter age in pigs and assessment of the predictive value of phenotypic and genetic information using random forest. J Anim Sci 96: 4935-4943. https://doi.org/10.1093/jas/sky359 doi: 10.1093/jas/sky359
|
| [14] |
Pierozan CR, Agostini PDS, Gasa J, et al. (2016) Factors affecting the daily feed intake and feed conversion ratio of pigs in grow-finishing units: the case of a company. Porc Health Manag 2: 1-8. https://doi.org/10.1186/s40813-016-0023-4 doi: 10.1186/s40813-016-0023-4
|
| [15] | Biau G (2012) Analysis of a random forests model. J Machine Learn Res 13: 1063-1095. |
| [16] |
Tang F, Ishwaran H (2017) Random Forest Missing Data Algorithms. Stat Anal Data Min ASA Data Sci J 10: 363-377. https://doi.org/10.1002/sam.11348 doi: 10.1002/sam.11348
|
| [17] | Dong C, Shu-Jie W, Zhen-Jian Z, et al. (2023) Genomic prediction of pig growth traits based on machine learning. Yi Chuan 45: 922-932. |
| [18] |
Xu J, Ye J, Zhou S, et al. (2023) Automatic quantification and assessment of grouped pig movement using the XGBoost and YOLOv5s models. Biosyst Eng 230: 145-158. https://doi.org/10.1016/j.biosystemseng.2023.04.010 doi: 10.1016/j.biosystemseng.2023.04.010
|
| [19] |
Vasconcelos L, Dias L G, Leite A, et al. (2023) SVM regression to assess meat characteristics of Bísaro pig loins using NIRS methodology. Foods 12: 470. https://doi.org/10.3390/foods12030470 doi: 10.3390/foods12030470
|
Figures(7) / Tables(4)
Di Pan, Caiyun Zhang, Tuowu Li, Zhe Zhang, Qishan Wang, Yuchun Pan, Peipei Ma. Study on pig feed conversion ratio prediction based on machine learning[J]. AIMS Animal Science, 2025, 1(1): 196-215. doi: 10.3934/aas.2025010
DownLoad: