Animal Bioscience

Asian Australasian Association of Animal Production Societies (아세아태평양축산학회)
권호 표지
DOI QR코드

DOI QR Code

Early prediction of final body weight in Hanwoo steers using machine and deep learning models

  • Eunjeong Jeon (Department of Animal Science, College of Agriculture and Natural Resources, Michigan State University) ;
  • Joonpyo Oh (Department of International Agricultural Technology, Graduate School of International Agricultural Technology, Seoul National University)
  • Received : 2025.08.21
  • Accepted : 2025.11.04
  • Published : 2026.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: Accurate early prediction of final body weight (BW) is essential for optimizing feeding strategies and slaughter planning in beef cattle production. This study compared the performance of three machine learning models (k-nearest neighbors, random forest, and eXtreme Gradient Boosting) and one deep learning model (long short-term memory [LSTM]) to forecast the final BW of Hanwoo steers at various time points prior to slaughter. Methods: A total of 196 Hanwoo steers (7 to 31 months of age) from a commercial farm were utilized. Input data included monthly BW and feed nutrient intake (crude protein, ether extract, neutral detergent fiber, and total digestible nutrients) across three growth stages. Six input configurations (I1-I6) were designed to predict the final BW at 17, 13, 9, 6, 3, and 1 month(s) before slaughter, with a target age of 31 months. The machine and deep learning models were assessed by five-fold cross-validation (training set) and a test set and evaluated via the coefficient of determination (R²) and root mean squared error (RMSE). Results: Among the tested models, the LSTM achieved the highest prediction accuracy across all the configurations. The performance of the LSTM improved as the prediction point approached the target slaughter age: I1 (R2 = 0.60, RMSE = 52.80), I2 (0.72, 45.40), I3 (0.76, 40.92), I4 (0.83, 35.84), I5 (0.90, 33.12), and I6 (0.97, 22.62). Conclusion: These results demonstrated that LSTM effectively captured temporal dependencies in sequential data, enabling more accurate BW forecasting under commercial conditions. While I6 achieved the highest prediction accuracy, the 3-6 month predictions (I4 and I5) demonstrated reasonably high accuracy, which could provide a practical time-frame for farm-level management and planning. This approach could be used in evidence-based decision-making in Hanwoo production by providing reliable predictions well before slaughter.

Keywords

References

  1. Fox DG, Van Amburgh ME, Tylutki TP. Predicting requirements for growth, maturity, and body reserves in dairy cattle. J Dairy Sci 1999;82:1968-77. https://doi.org/10.3168/jds.S0022-0302(99)75433-0
  2. Wang Z, Shadpour S, Chan E, Rotondo V, Wood KM, Tulpan D. ASAS-NANP symposium: applications of machine learning for livestock body weight prediction from digital images. J Anim Sci 2021;99:skab022. https://doi.org/10.1093/jas/skab022
  3. Gionbelli MP, Duarte MS, Valadares Filho SC, et al. Achieving body weight adjustments for feeding status and pregnant or non-pregnant condition in beef cows. PLOS ONE 2015;10:e0112111. https://doi.org/10.1371/journal.pone.0112111
  4. Yan T, Mayne CS, Patterson DC, Agnew RE. Prediction of body weight and empty body composition using body size measurements in lactating dairy cows. Livest Sci 2009;124:233-41. https://doi.org/10.1016/j.livsci.2009.02.003
  5. Grzesiak W, Zaborski D, Pilarczyk R, Wójcik J, Adamczyk K. Classification of daily body weight gains in beef calves using decision trees, artificial neural networks, and logistic regression. Animals 2023;13:1956. https://doi.org/10.3390/ani13121956
  6. Yin T, König S. Genetic parameters for body weight from birth to calving and associations between weights with testday, health, and female fertility traits. J Dairy Sci 2018;101:2158-70. https://doi.org/10.3168/jds.2017-13835
  7. Noinan K, Wicha S, Chaisricharoen R. The IoT-based weighing system for growth monitoring and evaluation of fattening process in beef cattle farm. In: Proceedings of the 2022 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON); 2022 Jan 26-28; Chiang Rai, Thailand. IEEE; 2022. pp. 384-8.
  8. Gjergji M, de Moraes Weber V, Silva LOC, et al. Deep learning techniques for beef cattle body weight prediction. In: Proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN); 2020 Jul 19-24; Glasgow, UK. IEEE; 2020. pp. 1-8.
  9. Pham X, Stack M. How data analytics is transforming agriculture. Bus Horiz 2018;61:125-33. https://doi.org/10.1016/j.bushor.2017.09.011
  10. Aiken VCF, Fernandes AFA, Passafaro TL, et al. Forecasting beef production and quality using large-scale integrated data from Brazil. J Anim Sci 2020;98:skaa089. https://doi.org/10.1093/jas/skaa089
  11. Biase AG, Albertini TZ, de Mello RF. On supervised learning to model and predict cattle weight in precision livestock breeding. Comput Electron Agric 2022;195:106706. https://doi.org/10.1016/j.compag.2022.106706
  12. Duwalage KI, Wynn MT, Mengersen K, Nyholt D, Perrin D, Robert PF. Predicting carcass weight of grass-fed beef cattle before slaughter using statistical modelling. Animals 2023;13:1968. https://doi.org/10.3390/ani13121968
  13. Heinrichs AJ, Rogers GW, Cooper JB. Predicting body weight and wither height in Holstein heifers using body measurements. J Dairy Sci 1992;75:3576-81. https://doi.org/10.3168/jds.S0022-0302(92)78134-X
  14. Miller GA, Hyslop JJ, Barclay D, Edwards A, Thomson W, Duthie CA. Using 3D imaging and machine learning to predict liveweight and carcass characteristics of live finishing beef cattle. Front Sustain Food Syst 2019;3:30. https://doi.org/10.3389/fsufs.2019.00030
  15. Xu B, Mao Y, Wang W, Chen G. Intelligent weight prediction of cows based on semantic segmentation and back propagation neural network. Front Artif Intell 2024;7:1299169. https://doi.org/10.3389/frai.2024.1299169
  16. Dang C, Choi T, Lee S, et al. Machine learning-based live weight estimation for Hanwoo cow. Sustainability 2022;14:12661. https://doi.org/10.3390/su141912661
  17. Jang DH, Kim C, Ko YG, Kim YH. Estimation of body weight for Korean cattle using three-dimensional image. J Biosyst Eng 2020;45:325-32. https://doi.org/10.1007/s42853-020-00073-8
  18. Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput 1997;9:1735-80. https://doi.org/10.1162/neco.1997.9.8.1735
  19. Van Houdt G, Mosquera C, Nápoles G. A review on the long short-term memory model. Artif Intell Rev 2020;53:5929-55. https://doi.org/10.1007/s10462-020-09838-1
  20. Hu L, Han L, Xu Z, Jiang T, Qi H. A disk failure prediction method based on LSTM network due to its individual specificity. Procedia Comput Sci 2020;176:791-9. https://doi.org/10.1016/j.procs.2020.09.074
  21. Wu H, Huang A, Sutherland JW. Avoiding environmental consequences of equipment failure via an LSTM-based model for predictive maintenance. Procedia Manuf 2020;43:666-73. https://doi.org/10.1016/j.promfg.2020.02.131
  22. Guo A, Smith S, Khan YM, Langabeer II JR, Foraker RE. Application of a time-series deep learning model to predict cardiac dysrhythmias in electronic health records. PLOS ONE 2021;16:e0239007. https://doi.org/10.1371/journal.pone.0239007
  23. Teixeira VA, Lana AMQ, Bresolin T, et al. Using rumination and activity data for early detection of anaplasmosis disease in dairy heifer calves. J Dairy Sci 2022;105:4421-33. https://doi.org/10.3168/jds.2021-20952
  24. Taechachokevivat N, Kou B, Zhang T, et al. Evaluating the performance of herd-specific long short-term memory models to identify automated health alerts associated with a ketosis diagnosis in early-lactation cows. J Dairy Sci 2024;107:11489-501. https://doi.org/10.3168/jds.2023-24513
  25. Association of Official Analytical Chemists (AOAC) International. Official methods of analysis. 17th ed. AOAC International; 2000.
  26. National Research Council. Nutrient requirements of dairy cattle. 7th ed. National Academies Press; 2001.
  27. Jeon E, Cho S, Hwang S, Cho K, Gondro C, Choi NJ. Development of prediction model for body weight and energy balance indicators from milk traits in lactating dairy cows based on deep neural networks. J King Saud Univ Sci 2024;36:103008. https://doi.org/10.1016/j.jksus.2023.103008
  28. R Core Team. R: a language and environment for statistical computing. R Foundation; 2020.
  29. Cho H, Jeon S, Lee M, et al. Analysis of the factors influencing body weight variation in Hanwoo steers using an automated weighing system. Animals 2020;10:1270. https://doi.org/10.3390/ani10081270
  30. Dórea JRR, Rosa GJM, Weld KA, Armentano LE. Mining data from milk infrared spectroscopy to improve feed intake predictions in lactating dairy cows. J Dairy Sci 2018;101:5878-89. https://doi.org/10.3168/jds.2017-13997
  31. Ahn JS, Son GH, Kim MJ, et al. Effect of total digestible nutrients level of concentrates on growth performance, carcass characteristics, and meat composition of Korean Hanwoo steers. Food Sci Anim Resour 2019;39:388-401. https://doi.org/10.5851/kosfa.2019.e32
  32. Kim D, Jung JS, Choi KC. A preliminary study on effects of fermented feed supplementation on growth performance, carcass characteristics, and meat quality of Hanwoo steers during the early and late fattening period. Appl Sci 2021;11:5202. https://doi.org/10.3390/app11115202
  33. Ramos SC, Kim SH, Jeong CD, et al. Increasing buffering capacity enhances rumen fermentation characteristics and alters rumen microbiota composition of high-concentrate fed Hanwoo steers. Sci Rep 2022;12:20739. https://doi.org/10.1038/s41598-022-24777-3
  34. Damanik N, Liu CM. Advanced fraud detection: leveraging K-SMOTEENN and stacking ensemble to tackle data imbalance and extract insights. IEEE Access 2025;13:10356-70. https://doi.org/10.1109/ACCESS.2025.3528079
  35. Silva FG, Carreira E, Ramalho JM, et al. Predicting body weight in pre-weaned Holstein-Friesian calves using morphometric measurements. Animals 2024;14:2129. https://doi.org/10.3390/ani14142129
  36. Alonso J, Castañón ÁR, Bahamonde A. Support vector regression to predict carcass weight in beef cattle in advance of the slaughter. Comput Electron Agric 2013;91:116-20. https://doi.org/10.1016/j.compag.2012.08.009
  37. Davison C, Bowen JM, Michie C, et al. Predicting feed intake using modelling based on feeding behaviour in finishing beef steers. Animal 2021;15:100231. https://doi.org/10.1016/j.animal.2021.100231
  38. Xiong Y, Condotta ICFS, Musgrave JA, Brown-Brandl TM, Mulliniks JT. Estimating body weight and body condition score of mature beef cows using depth images. Transl Anim Sci 2023;7:txad085. https://doi.org/10.1093/tas/txad085
  39. Adadi A, Berrada M. Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 2018;6:52138-60. https://doi.org/10.1109/ACCESS.2018.2870052
  40. Islam MN, Yoder J, Nasiri A, Burns RT, Gan H. Analysis of the drinking behavior of beef cattle using computer vision. Animals 2023;13:2984. https://doi.org/10.3390/ani13182984