Estimation of 305-day milk yield from test-day records of Chinese Holstein cattle

Abstract

This study compared six models, namely the Gaines, Sikka, Nelder, Wood, Dhanoa and Hayashi models, for the estimation of 305 days milk yield in Chinese Holstein cattle. We compared their ability to reliably predict 305-day lactation yield from incomplete (3 or 6 test-day (TD)) records. Our findings revealed that the accuracies (ACC) were 0.6655-0.9948, 0.8652-0.9977 and 0.9169-0.9968, whereas the mean square errors (MSE) were 0.0121-2.4807, 0.0139-1.0716 and 0.0170-0.5528 when 3 TD records were used in the first, second and higher lactations, respectively; when 6 TD records were used, the ACC were 0.8800-0.9992, 0.8742-0.9998 and 0.7950-0.9996, whereas the MSE values were 0.0017-0.3348, 0.0011-0.8605 and 0.0021-1.4869 in the first, second and higher lactations, respectively. All the models were fitted more accurately with 6 TD than 3 TD records. Further analysis revealed that the curves made by the Nelder, Wood and Dhanoa models were close to the actual curves. These three models can be used to predict the 305-day yield for management decisions in farms and for the genetic evaluation of Chinese Holstein cattle.

Accuracy of estimates of milk production per lactation from limited test-day and recall data collected at smallholder dairy farms

“…Accuracy of MPL-estimates based on limited records were expected to be lower than those based on CTD, because the accuracy of MPLestimates decreases with a decrease in number of records per lactation (Berry et al, 2005;Duclos et al, 2008;Flores et al, 2013;Kong et al, 2018;McGill et al, 2014;Otwinowska-Mindur et al, 2014;Zezza et al, 2016Zezza et al, , 2016. The accuracy of the LTD method was higher than that of the LRM method (Table 4).…”

“…The scarcity of frequent longitudinal milk production records has driven the search for alternative data recording methods that estimate MPL based on less records per lactation. This can be through a limited number of TD records per lactation, but it can be done also by using farmer recall data, where farmers rely on memory and recollection to give information for events in the past (Kong et al, 2018;McGill et al, 2014;Zezza et al, 2016). Ideally, farmers participating in recall surveys provide information about MP t at several distinctive days in the past from their memory.…”

Застосування Коефіцієнту Постійності Лактації Для Перерахунку Незакінченої Лактації На Повну (305 Днів)

“…Для прогнозу молочної продуктивності за умовне/фактичне контрольне доїння отриманий показник постійності (персистентності) лактації множили на розрахований або фактичний добовий надій попереднього місяця: , де М nнадій корови за n-ий місяць лактації (контрольне доїння); КПЛ nкоефіцієнт постійності лактації за n-ий місяць; nмісяць лактації. Для розрахунку молочної продуктивності за 305 днів лактації результати умовних/фактичних контрольних доїнь і результати, які отримані внаслідок прогнозування, перераховувалися за методикою інтервалів (Sargent, 1968) [13]: де M 1 , M 2 , M 3 , , M n-1 , M nдобові надої за результатами контрольних доїнь, кг; I 0 , I 1 , I 2 , …, I n-1 , I nінтервали між контрольними доїннями, днів. Прогноз молочної продуктивності за 305 днів лактації було зроблено після 3, 4, 5, 6, 7, 8 та 9 місяців лактації.…”

Evaluation of Normalization Techniques on Neural Networks for the Prediction of 305-Day Milk Yield

“…Neural networks method is one of the most popular artificial intelligence methods which are widely used in animal husbandry as well as in many applied sciences (Akıllı, 2019). Neural networks have been used for milk yield estimation studies in the field of dairy science (Salehi et al, 1998;Sanzogni and Kerr, 2001;Grzesiak et al, 2003;Grzesiak 2006;Sharma et al, 2006;Sharma et al, 2007;Hosseinia et al, 2007;Edriss et al, 2008;Njubi et al, 2009;Gandhi et al, 2010;Njubi et al, 2010;Ruhil et al, 2011;Dongre et al, 2012;Gandhi et al, 2012;Tahmoorrespur et al, 2012;Murphy et al, 2014;Kong et al, 2018) and ruminant animals (Ominakis et al, 2002;Torres et al, 2005;Ince andSofu, 2013, Karadas et al, 2017). In the 305-day milk yield estimation examined in the context of linear regression analysis, information on reproductive activities such as calving interval as well as milk yield on test day and lactation information are included in the model structures (Grzesiak et al, 2006;Sharma et al, 2007;Dongre et al, 2012;Takma et al, 2012;Görgülü, 2012).…”