Prediction of the growth in grower-finisher pigs using biologically constrained machine learning under small-sample data conditions
Abstract
Accurate prediction of pig growth is essential for feed planning and market decisions in precision pig farming, but farm data are often small and fragmented. To address this challenge, a biologically constrained machine learning framework is proposed to predict the time required for grower-finisher pigs to reach the target weight of 100 kg under small sample conditions. By applying biologically constrained modifications to machine learning models (SC-GAM and Monotone XGBoost), the constrained models outperformed unconstrained baselines, which achieved higher accuracy (RMSE ≤ 4.73 d, ACC±7d ≥ 92%), greater robustness, and improved biological realism. An evaluation system was developed that combines traditional accuracy indicators with biologically grounded metrics. Practical applicability was examined via an on-farm shadow test on an independent batch. The models delivered reliable predictions that support finishing scheduling and feed-related management decisions. These findings highlight the potential of biologically constrained models to improve operational efficiency and reduce resource wastage in commercial pig farming.
Keywords: biologically constrained machine learning, pig growth prediction, small-sample data, precision livestock farming
DOI: 10.25165/j.ijabe.20261902.10243
Citation: Cheng Y, Tong Y F, Huan H H. Prediction of the growth in grower-finisher pigs using biologically constrained machine learning under small-sample data conditions. Int J Agric & Biol Eng, 2026; 19(2): 88–102.
References
[1] Trabachini A, Moreira M R, Harada E S, Amorim M N, Silva-Miranda K O. Precision livestock farming applied to swine farms—A systematic literature review. Animals, 2025; 15: 2138.
[2] Marić K. Smart pig farms: Integration and application of digital technologies in pig production. Agriculture, 2025; 15: 937.
[3] Zhou R, Gutzwiller A, Hua J, Weary D M, von Keyserlingk M A G, Tullo E. Data recording and use of data tools for pig health management: A review. Front Vet Sci., 2024; 11: 1490770.
[4] Wang Z, Li Q, Yu Q, Qian W, Gao R, Wang R, Wu T, Li X. A review of visual estimation research on live pig weight. Sensors, 2024; 24: 7093. DOI: 10.3390/s24217093
[5] Paudel S, de Sousa R V, Sharma S R, Brown-Brandl T. Deep learning models to predict finishing pig weight using point clouds. Animals, 2024; 14: 31.
[6] Kwon K, Park A, Lee H, Mun D. Deep learning-based weight estimation using a fast-reconstructed mesh model from the point cloud of a pig. Comput Electron Agric., 2023; 210: 107903.
[7] Pya N, Wood S N. Shape constrained additive models. Stat Comput, 2015; 25: 543–559.
[8] XGBoost Developers. XGBoost parameters. Available from: https://xgboost.readthedocs.io/en/release_3.0.0/
[9] Hasan M A, Li F, Gouverneur P, Piet A, Grzegorzek M. A comprehensive survey and comparative analysis of time series data augmentation in medical wearable computing. PLoS One, 2025; 20: e0315343.
[10] Iglesias A, Talavera E, González-Prieto A, Mozo A, Gómez-Canaval S. A survey on data augmentation for time series: Taxonomy, directions, and applications. Neurocomputing, 2023; 558: 126678.
[11] Kotelnikov A, Baranchuk D, Rubachev I, Babenko A. TabDDPM: Modelling tabular data with diffusion models. In: Proceedings of the 40th International Conference on Machine Learning （ICML 2023）, PMLR, 2023; Vol. 202. Paper kotelnikov23a.
[12] Sun Q, Zhou X, Zhao S, Gao M, Zhang Q. A comprehensive survey on constrained machine learning: Approaches, models, and applications. Pattern Recognit, 2023; 141: 109529.
[13] Hu Y, Taylor G, Narayan A, Coleman E, Song Y, Sagawa S, et al. Training models that conform to a specification: A practical guide to constrained learning. In: Proceedings of the 40th International Conference on Machine Learning （ICML 2023）, PMLR, 2023; pp.14397–14437.
[14] Roberts D R, Bahn V, Ciuti S, Boyce M S, Elith J, Guillera-Arroita G. Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography, 2017; 40: 913–929.
[15] Angelopoulos A N, Bates S. A gentle introduction to conformal prediction and distribution-free uncertainty quantification. Found Trends Mach Learn, 2023; 16: 1–140.
[16] Camp Montoro J, Solà-Oriol D, Manteca X, Llonch P, Gasa J, Fàbrega E, et al. Predicting productive performance in grow-finisher pigs using birth and weaning body weight. Animals, 2020; 10: 1017.
[17] Yehoshua A, Bechar A, Cohen Y, Shmuel L, Edan Y. Dynamic sampling algorithm for agriculture-monitoring ground robot. Int J Simul Model, 2023; 22: 392–403.
[18] Cleveland W S. Robust locally weighted regression and smoothing scatterplots. J Am Stat Assoc., 1979; 74: 829–836.
[19] Cleveland W S, Devlin S J. Locally weighted regression: An approach to regression analysis by local fitting. J Am Stat Assoc., 1988; 83: 596–610.
[20] Chatfield C. Prediction intervals for the Holt-Winters forecasting procedure. J R Stat Soc Ser C App.Stat, 1978; 27: 264–279.
[21] Besteiro J, Góis Á, Madeira M, Manteca-Vilanova R, Rodríguez M R, Fernández M D. Linear and nonlinear mixed models to determine the growth of weaned piglets. Animals, 2023; 13: 2212.
[22] Che Z X, Qiao J K, Xu F J, Li X Y, Zhao Y X, Zhu M J. Integrated analysis reveals genetic basis of growth curve parameters in an F2 designed pig population based on genome and transcriptome data. Agriculture, 2024; 14（10）: 1704.
[23] Henderson C R. Best linear unbiased estimation and prediction under a selection model. Biometrics, 1975; 31: 423–447.
[24] Mrode R A. Linear models for the prediction of animal breeding values. 3rd ed. Wallingford （UK）, CABI, 2014.
[25] Akinyemi B E, Vigors B, Turner S P, Akaichi F, Benjamin M, Johnson A K, et al. Precision livestock farming: A qualitative exploration of opportunities and challenges for the commercial pig industry. Front Anim Sci., 2023; 4: 1150528.
[26] Valavi R, Elith J, Lahoz-Monfort J J, Guillera-Arroita G. blockCV: An R package for generating spatially or environmentally separated folds for k-fold cross-validation of species distribution models. Methods Ecol Evol., 2019; 10: 225–232.
[27] Romano Y, Patterson E, Candès E. Conformalized quantile regression. Adv Neural Inf Process Syst., 2019; 32: 3543–3553.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Agricultural and Biological Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
