Animal Breeding and Genomics Group, Wageningen University, PO Box 338, 6700 AH, Wageningen, the Netherlands.
Animal Breeding and Genomics Group, Wageningen University, PO Box 338, 6700 AH, Wageningen, the Netherlands.
J Dairy Sci. 2019 Jul;102(7):6288-6295. doi: 10.3168/jds.2018-15684. Epub 2019 May 2.
Because of the environmental impact of methane (CH), it is of great interest to reduce CH emission of dairy cattle and selective breeding might contribute to this. However, this approach requires a rapid and inexpensive measurement technique that can be used to quantify CH emission for a large number of individual dairy cows. Milk infrared (IR) spectroscopy has been proposed as a predictor for CH emission. In this study, we investigated the feasibility of milk IR spectra to predict breath sensor-measured CH of 801 dairy cows on 10 commercial farms. To evaluate the prediction equation, we used random and block cross validation. Using random cross validation, we found a validation coefficient of determination (Rval) of 0.49, which suggests that milk IR spectra are informative in predicting CH emission. However, based on block cross validation, with farms as blocks, a negligible Rval of 0.01 was obtained, indicating that milk IR spectra cannot be used to predict CH emission. Random cross validation thus results in an overoptimistic view of the ability of milk IR spectra to predict CH emission of dairy cows. The difference between the validation strategies could be due to the confounding of farm and date of milk IR analysis, which introduces a correlation between batch effects on the IR analyses and farm-average CH. Breath sensor-measured CH is strongly influenced by farm-specific conditions, which magnifies the problem. Milk IR wavenumbers from water absorption regions, which are generally considered uninformative, showed moderate accuracy (Rval = 0.25) when based on random cross validation, but not when based on block cross validation (Rval = 0.03). These results indicate, therefore, that in the current study, random cross validation results in an overoptimistic view on the ability of milk IR spectra to predict CH emission. We suggest prediction based on wavenumbers from water absorption regions as a negative control to identify potential dependence structures in the data.
由于甲烷（CH）的环境影响，减少奶牛的 CH 排放具有重要意义，而选择性育种可能对此有贡献。然而，这种方法需要一种快速且廉价的测量技术，以便能够对大量个体奶牛的 CH 排放进行量化。牛奶红外（IR）光谱已被提出作为 CH 排放的预测因子。在这项研究中，我们研究了牛奶 IR 光谱预测 10 个商业奶牛场 801 头奶牛呼吸传感器测量的 CH 排放的可行性。为了评估预测方程，我们使用了随机和分组交叉验证。使用随机交叉验证，我们发现验证系数的确定（Rval）为 0.49，这表明牛奶 IR 光谱在预测 CH 排放方面具有信息性。然而，基于分组交叉验证，以农场为分组，得到一个可以忽略不计的 Rval 为 0.01，这表明牛奶 IR 光谱不能用于预测 CH 排放。因此，随机交叉验证导致对牛奶 IR 光谱预测奶牛 CH 排放能力的过度乐观的看法。验证策略之间的差异可能是由于农场和牛奶 IR 分析日期的混淆造成的，这会导致 IR 分析批次效应与农场平均 CH 之间产生相关性。呼吸传感器测量的 CH 强烈受到特定于农场的条件的影响，这放大了这个问题。基于随机交叉验证，水吸收区域的牛奶 IR 波数（通常被认为是无信息的）显示出中等的准确性（Rval = 0.25），但基于分组交叉验证时则不准确（Rval = 0.03）。因此，这些结果表明，在当前研究中，随机交叉验证导致对牛奶 IR 光谱预测 CH 排放能力的过度乐观的看法。我们建议基于水吸收区域的波数进行预测作为识别数据中潜在依赖结构的阴性对照。
