Body condition score; Dairy cows; Data imputation; Machine learning; Bi-directional; Dairy cattles; Dairy cow; Machine learning methods; Machine-learning; Performance; Root mean squared errors; Short term memory; Forestry; Agronomy and Crop Science; Computer Science Applications; Horticulture
Abstract :
[en] Regular monitoring of body condition score (BCS) changes during lactation is an essential management tool in dairy cattle; however, the current BCS measurements are often discontinuous and unevenly spaced in time. The imputation of BCS values is useful for two main reasons: i) achieving completeness of data is necessary to be able to relate BCS to other traits (e.g. milk yield and milk composition) that have been routinely recorded at different times and with a different frequency, and ii) having expected BCS values provides the possibility to trigger early warnings for animals with certain unexpected conditions. The contribution of this study was to propose and evaluate potential methods useful to smooth and impute device-based BCS values recorded during lactation in dairy cattle. In total, 26,207 BCS records were collected from 3,038 cows (9,199 and 14,462 BCS records on 1,546 Holstein and 1,211 Montbéliarde cows respectively, and the rest corresponded to other minority cattle breeds). Six methods were evaluated to predict BCS values: the traditional methods of test interval method (TIM), and multiple-trait procedure (MTP), and the machine learning (ML) methods of multi-layer perceptron (MLP), Elman network (Elman), long-short term memories (LSTM) and bi-directional LSTM (BiLSTM). The performance of each method was evaluated by a hold-out validation approach using statistics of the root mean squared error (RMSE) and Pearson correlation (r). TIM, MTP, MLP, and BiLSTM were assessed for the imputation of intermediate missing values, while MTP, Elman, and LSTM were evaluated for the forecasting of future BCS values. Regarding the machine learning methods, BiLSTM demonstrated the best performance for the intermediate value imputation task (RMSE = 0.295, r = 0.845), while LSTM demonstrated the best performance for the future value forecasting task (RMSE = 0.356, r = 0.751). Among the methods evaluated, MTP showed the best performance for imputation of intermediate missing values in terms of RMSE (0.288) and r (0.856). MTP also achieved the best performance for forecasting of future BCS values in terms of RMSE (0.348) and r (0.760). This study demonstrates the ability of MTP and machine learning methods to impute missing BCS data and provides a cost-effective solution for the application area.
Disciplines :
Animal production & animal husbandry
Author, co-author :
Chelotti, J.; TERRA Teaching and Research Center, University of Liège, Gembloux Agro-Bio Tech (ULiège-GxABT), Gembloux, Belgium ; Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional, sinc(i), FICH-UNL/CONICET, Santa Fe, Argentina
Atashi, Hadi ; Université de Liège - ULiège > Département GxABT > Animal Sciences (AS) ; Department of Animal Science, Shiraz University, Shiraz, Iran
Ferrero, M.; Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional, sinc(i), FICH-UNL/CONICET, Santa Fe, Argentina
Grelet, C.; Walloon Agricultural Research Center (CRA-W), Gembloux, Belgium
Soyeurt, Hélène ; Université de Liège - ULiège > Département GxABT > Modélisation et développement
Giovanini, L.; Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional, sinc(i), FICH-UNL/CONICET, Santa Fe, Argentina
Rufiner, H.L.; Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional, sinc(i), FICH-UNL/CONICET, Santa Fe, Argentina ; Facultad de Ingeniería, Universidad Nacional de Entre Ríos, Argentina
Gengler, Nicolas ; Université de Liège - ULiège > TERRA Research Centre > Animal Sciences (AS)
Language :
English
Title :
Assessing traditional and machine learning methods to smooth and impute device-based body condition score throughout the lactation in dairy cows
Acknowledgment, The authors acknowledge the INTERREG NWE HappyMoo project, grant agreement NWE 730, co-financed by the Walloon Government (Service Public de Wallonie, Namur, Belgium). The providing of BCS data by the DHI organizations 3CE (Strasbourg, France) and Conseil \u00C9levage 25-90 (Roulans, France) is recognized. Nicolas Gengler, as a former senior research associate, acknowledges the support of the National Fund for Scientific Research (Brussels, Belgium) also through the grant no. T.0095.19 (PDR \u201CDEEPSELECT\u201D). The authors have not stated any conflicts of interest.The authors acknowledge the INTERREG NWE HappyMoo project, grant agreement NWE 730, co-financed by the Walloon Government ( Service Public de Wallonie , Namur, Belgium). The providing of BCS data by the DHI organizations 3CE (Strasbourg, France) and Conseil \u00C9levage 25-90 (Roulans, France) is recognized. Nicolas Gengler, as a former senior research associate, acknowledges the support of the National Fund for Scientific Research (Brussels, Belgium) also through the grant no. T.0095.19 (PDR \u201CDEEPSELECT\u201D). The authors have not stated any conflicts of interest.
Alvarez, J.R., Arroqui, M., Mangudo, P., Toloza, J., Jatip, D., Rodriguez, J.M., Teyseyre, A., Sanz, C., Zunino, A., Machado, C., Mateos, C., Estimating body condition score in dairy cows from depth images using convolutional neural networks, transfer learning and model ensembling techniques. Agronomy, 9, 2019, 90, 10.3390/agronomy9020090.
Anglart, D., Hallén-Sandgren, C., Emanuelson, U., Rönnegård, L., Comparison of methods for predicting cow composite somatic cell counts. J. Dairy Sci. 103 (2020), 8433–8442.
Ankinakatte, S., Norberg, E., Løvendahl, P., Edwards, D., Højsgaard, S., Predicting mastitis in dairy cows using neural networks and generalized additive models: A comparison. Comput. Electron. Agric. 99 (2013), 1–6, 10.1016/j.compag.2013.08.024.
Arrieta, A.B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., Herrera, F., Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58 (2020), 82–115, 10.1016/j.inffus.2019.12.012.
Bastin, C., Gengler, N., Genetics of body condition score as an indicator of dairy cattle fertility. A Review. Biotechnol. Agron. Soc. Environ. 17 (2013), 64–75.
Bastin, C., Laloux, L., Gillon, A., Bertozzi, C., Vanderick, S., Gengler, N., First results of body condition score modeling for Walloon Holstein cows. Interbull Bull. 37 (2007), 170–174 https://journal.interbull.org/index.php/ib/article/view/1371/1371.
Beam, S., Butler, W., Effects of energy balance on follicular development and first ovulation in postpartum. J. Reprod. Fertil. Suppl. 54 (1999), 411–424.
Berghof, T.V., Poppe, M., Mulder, H.A., Opportunities to improve resilience in animal breeding programs. Front. Genet., 9, 2019, 692, 10.3389/fgene.2018.00692.
Bernabucci, U., Ronchi, B., Lacetera, N., Nardone, A., Influence of body condition score on relationships between metabolic status and oxidative stress in periparturient dairy cows. J. Dairy Sci. 88 (2005), 2017–2026, 10.3168/jds.S0022-0302(05)72878-2.
Bishop, C. M. and N. M. Nasrabadi. 2006. Pattern recognition and machine learning. Vol. 4. No. 4. Springer, New York, NY.
Chollet, F. 2015. Keras. https://github. com/fchollet/keras.
Coffey, M.P., Simm, G., Brotherstone, S., Energy balance profiles for the first three lactations of dairy cows estimated using random regression. J. Dairy Sci. 85 (2002), 2669–2678, 10.3168/jds.S0022-0302(02)74352-X.
Collard, B.L., Boettcher, P.J., Dekkers, J.C.M., Petitclerc, D., Schaeffer, L.R., Relationships between energy balance and health traits of dairy cattle in early lactation. J. Dairy Sci. 83 (2000), 2683–2690, 10.3168/jds.s0022-0302(00)75162-9.
Du, A., Guo, H., Lu, J., Su, Y., Ma, Q., Ruchay, A., et al. Automatic livestock body measurement based on keypoint detection with multiple depth cameras. Computers and Electronics in Agriculture, 198, 2022, 107059, 10.1016/j.compag.2022.107059.
Edmonson, A.J., Lean, I.J., Weaver, L.D., Farver, T., Webster, G., A body condition scoring chart for Holstein dairy cows. J. Dairy Sci. 72 (1989), 68–78, 10.3168/jds.S0022-0302(89)79081-0.
Everett, R.W., Carter, H.W., Accuracy of test interval method of calculating dairy herd improvement association records. J. Dairy Sci. 51 (1968), 1936–1941, 10.3168/jds.S0022-0302(68)87317-5.
Ferguson, J.D., Galligan, D.T., Thomsen, N., Principal descriptors of body condition score in Holstein cows. J. Dairy Sci. 77 (1994), 2695–2703, 10.3168/jds.S0022-0302(94)77212-X.
Friggens, N.C., Berg, P., Theilgaard, P., Korsgaard, I.R., Ingvartsen, K.L., Løvendahl, P., Jensen, J., Breed and parity effects on energy balance profiles through lactation: Evidence of genetically driven body energy change. J. Dairy Sci. 90 (2007), 5291–5305, 10.3168/jds.2007-0173.
Gengler, N., Soyeurt, H., Dehareng, F., Bastin, C., Colinet, F., Hammami, H., Vanrobays, M.-L., Lainé, A., Vanderick, S., Grelet, C., Capitalizing on fine milk composition for breeding and management of dairy cows. J. Dairy Sci. 99 (2016), 4071–4079, 10.3168/jds.2015-10140.
Graham, P., Young, J., Penny, R., Multiply imputed synthetic data: Evaluation of hierarchical Bayesian imputation models. Journal of Official Statistics 25:2 (2009), 245–268.
Graves, A., Schmidhuber, J., Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18 (2005), 602–610, 10.1016/j.neunet.2005.06.042.
ICAR. 2020. Procedure 2 of Section 2 of ICAR Guidelines computing of accumulated lactation yield. Accessed March. 26, 2023. https://www.icar.org/Guidelines/02-Procedure-2-Computing-Lactation-Yield.pdf.
ICAR. 2022. Appendix 1 of Section 5 of ICAR Standard trait definition for dairy cattle. Accessed March. 26, 2023. https://www.icar.org/Guidelines/05-Conformation-recording-Appendix-1.pdf.
Kristensen, E., Dueholm, L., Vink, D., Andersen, J., Jakobsen, E., Illum-Nielsen, S., Petersen, F., Enevoldsen, C., Within-and across-person uniformity of body condition scoring in Danish Holstein cattle. J. Dairy Sci. 89 (2006), 3721–3728.
Kuzuhara, Y., Kawamura, K., Yoshitoshi, R., Tamaki, T., Sugai, S., Ikegami, M., Kurokawa, Y., Obitsu, T., Okita, M., Sugino, T., A preliminarily study for predicting body weight and milk properties in lactating Holstein cows using a three-dimensional camera system. Comput. Electron. Agric. 111 (2015), 186–193, 10.1016/j.compag.2014.12.020.
Leary, N.O., Leso, L., Buckley, F., Kenneally, J., McSweeney, D., Shalloo, L., Validation of an automated body condition scoring system using 3D imaging. Agriculture, 10(6), 2020, 246, 10.3390/agriculture10060246.
Lobato, F., Sales, C., Araujo, I., Tadaiesky, V., Dias, L., Ramos, L., Santana, A., Multi-objective genetic algorithm for missing data imputation. Pattern Recognit. Lett. 68 (2015), 126–131, 10.1016/j.patrec.2015.08.023.
Luo, X., Hu, Y., Gao, Z., Guo, H., Su, Y., Automated measurement of livestock body based on pose normalisation using statistical shape model. Biosyst. Eng. 227 (2023), 36–51, 10.1016/j.biosystemseng.2023.01.016.
Macciotta, N.P.P., Vicario, D., Cappio-Borlino, A., Detection of different shapes of lactation curve for milk yield in dairy cattle by empirical mathematical models. J. Dairy Sci. 88 (2005), 1178–1191, 10.3168/jds.S0022-0302(05)72784-3.
Mao, I., Sloniewski, K., Madsen, P., Jensen, J., Changes in body condition score and in its genetic variation during lactation. Livest. Prod. Sci. 89 (2004), 55–65, 10.1016/j.livprodsci.2003.12.005.
Martins, B.M., Mendes, A.L.C., Silva, L.F., Moreira, T.R., Costa, J.H.C., Rotta, P.P., Chizzotti, M.L., Marcondes, M.I., Estimating body weight, body condition score, and type traits in dairy cows using three dimensional cameras and manual body measurements. Livestock Science, 236, 2020, 104054, 10.1016/j.livsci.2020.104054.
Mayeres, P., Stoll, J., Bormann, J., Reents, R., Gengler, N., Prediction of daily milk, fat, and protein production by a random regression test-day model. J. Dairy Sci. 87 (2004), 1925–1933, 10.3168/jds.S0022-0302(04)73351-2.
McParland, S., Banos, G., Wall, E., Coffey, M., Soyeurt, H., Veerkamp, R., Berry, D., The use of mid-infrared spectrometry to predict body energy status of Holstein cows. J. Dairy Sci. 94 (2011), 3651–3661, 10.3168/jds.2010-3965.
Mota, L.F.M., Pegolo, S., Baba, T., Peñagaricano, F., Morota, G., Bittante, G., Cecchinato, A., Evaluating the performance of machine learning methods and variable selection methods for predicting difficult-to-measure traits in Holstein dairy cattle using milk infrared spectral data. J. Dairy Sci. 104 (2021), 8107–8121, 10.3168/jds.2020-19861.
Mullins, I.L., Truman, C.M., Campler, M.R., Bewley, J.M., Costa, J.H., Validation of a commercial automated body condition scoring system on a commercial dairy farm. Animals, 9(6), 2019, 287, 10.3390/ani9060287.
Poppe, M., Veerkamp, R.F., van Pelt, M.L., Mulder, H.A., Exploration of variance, autocorrelation, and skewness of deviations from lactation curves as resilience indicators for breeding. J. Dairy Sci. 103 (2020), 1667–1684, 10.3168/jds.2019-17290.
Poppe, M., Bonekamp, G., van Pelt, M.L., Mulder, H.A., Genetic analysis of resilience indicators based on milk yield records in different lactations and at different lactation stages. J. Dairy Sci. 104 (2021), 1967–1981, 10.3168/jds.2020-19245.
Pryce, J.E., Coffey, M.P., Simm, G., The relationship between body condition score and reproductive performance. J. Dairy Sci. 84 (2001), 1508–1515, 10.3168/jds.S0022-0302(01)70184-1.
Roche, J.R., Dillon, P.G., Stockdale, C.R., Baumgard, L.H., VanBaale, M.J., Relationships among international body condition scoring systems. J. Dairy Sci. 87 (2004), 3076–3079, 10.3168/jds.s0022-0302(04)73441-4.
Roche, J.R., Friggens, N.C., Kay, J.K., Fisher, M.W., Stafford, K.J., Berry, D.P., Invited review: Body condition score and its association with dairy cow productivity, health, and welfare. J. Dairy Sci. 92 (2009), 5769–5801, 10.3168/jds.2009-2431.
Rumelhart, D. E., G. E. Hinton, and R. J. Williams. 1985. Learning internal representations by error propagation. California Univ San Diego La Jolla Inst for Cognitive Science, San Diego, CA. https://apps.dtic.mil/sti/pdfs/ADA164453.pdf.
Sainani, K.L., Dealing with missing data. PM&R 7:9 (2015), 990–994.
Sakaguchi, M., Differences between body condition scores and body weight changes in postpartum dairy cows in relation to parity and reproductive indices. Can. Vet. J. 50 (2009), 649–656.
Sargent, F., Lytton, V., Wall, O. Jr., Test interval method of calculating dairy herd improvement association records. J. Dairy Sci. 51 (1968), 170–179, 10.3168/jds.S0022-0302(68)86943-7.
Schaeffer, L.R., Jamrozik, J., Multiple-trait prediction of lactation yields for dairy cows. J. Dairy Sci. 79 (1996), 2044–2055, 10.3168/jds.S0022-0302(96)76578-5.
Schröder, U.J., Staufenbiel, R., Invited review: Methods to determine body fat reserves in the dairy cow with special regard to ultrasonographic measurement of backfat thickness. J. Dairy Sci. 89 (2006), 1–14, 10.3168/jds.S0022-0302(06)72064-1.
Song, X., Bokkers, E.A.M., van Mourik, S., Groot Koerkamp, P.W.G., van der Tol, P., Automated body condition scoring of dairy cows using 3-dimensional feature extraction from multiple body regions. J. Dairy Sci. 102 (2019), 4294–4308, 10.3168/jds.2018-15238.
Spoliansky, R., Edan, Y., Parmet, Y., Halachmi, I., Development of automatic body condition scoring using a low-cost 3-dimensional Kinect camera. J. Dairy Sci. 99 (2016), 7714–7725, 10.3168/jds.2015-10607.
Truman, C.M., Campler, M.R., Costa, J.H., Body condition score change throughout lactation utilizing an automated BCS System: A descriptive study. Animals, 12, 2022, 601, 10.3390/ani12050601.
Van Buuren, S., Flexible imputation of missing data. 2018, CRC Press, New-York, NY.
Walsh, S., Buckley, F., Pierce, K., Byrne, N., Patton, J., Dillon, P., Effects of breed and feeding system on milk production, body weight, body condition score, reproductive performance, and postpartum ovarian function. J. Dairy Sci. 91 (2008), 4401–4413, 10.3168/jds.2007-0818.
Wathes, D.C., Cheng, Z., Bourne, N., Taylor, V.J., Coffey, M.P., Brotherstone, S., Differences between primiparous and multiparous dairy cows in the inter-relationships between metabolic traits, milk yield and body condition score in the periparturient period. Domest. Anim. Endocrinol. 33 (2007), 203–225, 10.1016/j.domaniend.2006.05.004.
Wildman, E., Jones, G., Wagner, P., Boman, R., Troutt, H. Jr, Lesch, T., A dairy cow body condition scoring system and its relationship to selected production characteristics. J. Dairy Sci. 65 (1982), 495–501, 10.3168/jds.S0022-0302(82)82223-6.
Wilmink, J., Adjustment of test-day milk, fat and protein yield for age, season and stage of lactation. Livest. Prod. Sci. 16 (1987), 335–348, 10.1016/0301-6226(87)90003-0.
Woolson, R. F. 2007. Wilcoxon signed‐rank test. Wiley Encyclopedia of Clinical Trials:1-3.
Zhang, J., Lei, J., Wu, J., Lu, H., Guo, H., Pezzuolo, A., et al. Automatic method for quantitatively analyzing the body condition of livestock from 3D shape. Comput. Electron. Agric., 214, 2023, 108307, 10.1016/j.compag.2023.108307.