Performance of Machine Learning Algorithms in Predicting Sheep Weight Based on Morphometric Measurements
DOI:
https://doi.org/10.22456/2175-2745.154217Keywords:
artificial intelligence, precision livestock farming, predictive modeling, zootechnical monitoring, cross-validationAbstract
Body weight estimation is an important activity in sheep management; however, direct weighing using scales may be limited by cost and operational constraints, making it necessary to seek feasible alternatives for this process. In this context, this article presents one of the first systematic comparisons of Machine Learning algorithms for predicting the body weight of Santa Inês Ewes based on morphometric measurements collected manually under field conditions. Data from 80 females evaluated in Campo Verde, Mato Grosso, Brazil, were analyzed. A formal variable selection pipeline was conducted by combining Pearson correlation analysis and the Variance Inflation Factor (VIF), which revealed severe multicollinearity among all morphometric variables (VIF ranging from 148 to 1,434), supporting the selection of thoracic circumference as the primary predictor (r = 0.92). Modeling was conducted in Python, and five regression models — Linear Regression, Random Forest, XGBoost, SVR, and MLP — were evaluated using K-Fold cross-validation (k = 10), with hyperparameter tuning performed through GridSearchCV. Results are reported as mean ± standard deviation across folds. Linear Regression achieved the best performance (R2 = 77.44% ± 13.47%, MAE = 3.021 kg), outperforming SVR, MLP, Random Forest, and XGBoost, suggesting a predominance of linear relationships in the sample. As a practical contribution, a simple estimation equation was derived: Weight(kg) = 1.298T horacicCircum f erence(cm) − 64.547, enabling producers to estimate body weight using only a measuring tape, without the need for conventional scales.
Downloads
References
[1] Instituto Brasileiro de Geografia e Estatística. Produção da Pecuária Municipal 2023. Rio de Janeiro, 2024. Available at: ⟨https://www.gov.br/mpa/pt-br/assuntos/noticias/ppm_2023_v51_br_informativo.pdf⟩.
[2] MAGALHÃES, K. A. et al. Pesquisa da Pecuária Municipal 2023: rebanhos de caprinos e ovinos. Sobral, CE, 2024. Boletim N° 24. CIM - Centro de Inteligência e Mercado de Caprinos e Ovinos. Disponível em: ⟨https://www.embrapa.br/documents/1355090/35052914/Boletim_N%C2%BA24_PPM%2B2023.pdf/1d547bbd-3198-08d5-3cf0-4552add581bd⟩.
[3] BORGES, D. M.; HEINZ, L. F. Viabilidade econômica da produção de ovinos de corte em sistema extensivo. Lages, 2016.
[4] SOUSA, W. H. d. Indicadores técnicos e econômicos de produtividade de um sistema de produção de ovinos de corte no semiárido. João Pessoa: EMEPA-PB, 2018. ISBN 978-85-64059-19-1.
[5] BROWN, D. J. et al. Monitoring liveweight in sheep is a valuable management strategy: a review of available technologies. Animal Production Science, v. 55, p. 427–436, 2015. Available at: https://doi.org/10.1071/AN13274.
[6] GRANDIS, F. A. et al. Relação entre medidas biométricas e peso corporal em ovinos da raça texel. Veterinária e Zootecnia, v. 25, n. 2, p. 1–8, 2018. ISSN 2178-3764. Disponível em: ⟨https://doi.org/10.35172/rvz.2018.v25.57⟩.
[7] YAKUBU, A. Path coefficient and path analysis of body weight and biometric traits in yankasa lambs. Slovak Journal of Animal Science, v. 43, n. 1, p. 17–25, 2010. Disponível em: ⟨https://office.sjas-journal.org/index.php/sjas/article/view/324⟩.
[8] HAMADANI, A.; GANAI, N. A. Artificial intelligence algorithm comparison and ranking for weight prediction in sheep. Scientific Reports, v. 13, p. 13242, 2023. Disponível em: ⟨https://doi.org/10.1038/s41598-023-40528-4⟩.
[9] CARHUAS, J. N. et al. Balancing accuracy, interpretability, and stability in machine-learning models: Live-weight prediction of andean sheep from morphometric traits. Scientia Agropecuaria, v. 16, n. 4, p. 487–498, 2025. Disponível em: ⟨https://doi.org/10.17268/sci.agropecu.2025.037⟩.
[10] BERCKMANS, D. General introduction to precision livestock farming. Animal Frontiers, v. 7, n. 1, p. 6–11, 2017. Disponível em: ⟨https://doi.org/10.2527/af.2017.0102⟩.
[11] BERCKMANS, D. Precision livestock farming technologies for welfare management in intensive livestock systems. Rev. sci. tech. Off. int. Epiz., v. 33, n. 1, p. 189–196, 2014. Disponível em: ⟨https://doi.org/10.20506/rst.33.1.2273⟩.
[12] NETO, M. R. T. et al. Evolução da biometria corporal de ovinos da raça santa inês. Agropecuária Científica no Semiárido, v. 12, n. 2, p. 170–180, 2016. Disponível em: ⟨https://doi.org/10.30969/acsa.v12i2.737⟩.
[13] SOUSA, W. H. d.; LÔBO, R. N. B.; MORAIS, O. R. Ovinos santa inês: Estado de arte e perspectivas. In: Anais do Simpósio Internacional Sobre Caprinos e Ovinos de Corte. João Pessoa: [s.n.], 2003. p. 501–522. Disponível em: ⟨https://www.alice.cnptia.embrapa.br/alice/handle/doc/529936⟩.
[14] SENA, L. S. et al. Avanços no melhoramento genético de ovinos da raça santa inês. Revista Científica de Produção Animal, v. 23, n. 1, p. 37–45, 2021. ISSN 2176-4158.
[15] QUADROS, D. G. d.; CRUZ, J. F. d. Produção de Ovinos e Caprinos de Corte. Salvador: EDUNEB, 2017. ISBN 978-85-7887-331-8. Disponível em: ⟨https://saberaberto.uneb.br/handle/20.500.11896/863⟩.
[16] GÉRON, A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. 2nd. ed. Sebastopol, CA: O’Reilly Media, Inc., 2019. ISBN 978-1492032649.
[17] CHOLLET, F. Deep Learning with Python. 2nd. ed. Shelter Island, NY: Manning Publications Co., 2021. ISBN 978-1617296864.
[18] BISHOP, C. M. Pattern Recognition and Machine Learning. New York, NY: Springer, 2006. ISBN 978-0387310732.
[19] MURPHY, K. P. Machine Learning: A Probabilistic Perspective. Cambridge, MA: The MIT Press, 2012. ISBN 978-0262018029.
[20] SILVA, D. C. d. et al. Estimativa do peso vivo através do perímetro torácico de ovinos santa inês. Revista Científica de Produção Animal, v. 8, n. 2, p. 41–46, 2006.
[21] SOUZA, D. S. et al. Desenvolvimento corporal e relação entre biometria e peso de cordeiros lactantes da raça santa inês criados na amazônia. Arquivo Brasileiro de Medicina Veterinária e Zootecnia, v. 66, n. 6, p. 1787–1794, 2014. Disponível em: ⟨https://www.scielo.br/j/abmvz/a/kRsz99PV5kdMNFKrvZDsrRL/⟩.
[22] BREIMAN, L. Random forests. Machine Learning, v. 45, n. 1, p. 5–32, 2001. ISSN 0885-6125. Disponível em: ⟨https://doi.org/10.1023/A:1010933404324⟩.
[23] SCHÖLKOPF, B.; SMOLA, A. J. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. 1. ed. Cambridge: MIT Press, 2001. 644 p.
[24] AGGARWAL, C. C. Neural Networks and Deep Learning: A Textbook. Cham: Springer International Publishing AG, 2018. ISBN 978-3319944623.
[25] GOODFELLOW, I.; BENGIO, Y.; COURVILLE, A. Deep Learning. Cambridge, MA: The MIT Press, 2016. ISBN 978-0262035613.
[26] HASTIE, T.; TIBSHIRANI, R.; FRIEDMAN, J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2. ed. New York: Springer, 2009.
[27] HYNDMAN, R. J.; ATHANASOPOULOS, G. Forecasting: Principles and Practice. 3. ed. Melbourne, Australia: OTexts, 2021. v. 3. 384 p. (Forecasting Series, v. 3).
[28] JÚNIOR, G. S. C. et al. Caracterização morfométrica de ovinos da raça santa inês criados nas microrregiões de teresina e campo maior, piauí. Revista Brasileira de Zootecnia, v. 35, n. 6, p. 2260–2267, 2006. Disponível em: ⟨https://doi.org/10.1590/S1516-35982006000800009⟩.
[29] TU, G. J.; JØRGENSEN, E. Vision analysis and prediction for estimation of pig weight in slaughter pens. Expert Systems with Applications, v. 220, p. 119684, 2023. Disponível em: ⟨https://doi.org/10.1016/j.eswa.2023.119684⟩.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Leonardo Antunes, Ana Flávia da Guia Miranda, João Batista Gonçalves Costa Júnior, Caroline Lima Amorim, Maria Eduarda Garcia Corrêa, Adrielly Kamile Silva Bezerra, Kauane Ferreira da Silva, Shara Luzia Cavalcante Souza, Juliana Fonseca Antunes
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Autorizo aos editores a publicação de meu artigo, caso seja aceito, em meio eletrônico de acordo com as regras do Public Knowledge Project.Accepted 2026-06-27
Published 2026-08-10
