Wang Yuxuan, Zhou Jianzhao, Wang Xinjie, Yu Qingyuan, Sun Yukun, Li Yang, Zhang Yonggen, Shen Weizheng, Wei Xiaoli
College of Electric and Information, Northeast Agricultural University, Harbin 150030, China.
College of Animal Sciences and Technology, Northeast Agricultural University, Harbin 150030, China.
Animals (Basel). 2023 Feb 15;13(4):678. doi: 10.3390/ani13040678.
Volatile fatty acids (VFAs) and methane are the main products of rumen fermentation. Quantitative studies of rumen fermentation parameters can be performed using in vitro techniques and machine learning methods. The currently proposed models suffer from poor generalization ability due to the small number of samples. In this study, a prediction model for rumen fermentation parameters (methane, acetic acid (AA), and propionic acid (PA)) of dairy cows is established using the stacking ensemble learning method and in vitro techniques. Four factors related to the nutrient level of total mixed rations (TMRs) are selected as inputs to the model: neutral detergent fiber (NDF), acid detergent fiber (ADF), crude protein (CP), and dry matter (DM). The comparison of the prediction results of the stacking model and base learners shows that the stacking ensemble learning method has better prediction results for rumen methane (coefficient of determination (R2) = 0.928, root mean square error (RMSE) = 0.968 mL/g), AA (R2 = 0.888, RMSE = 1.975 mmol/L) and PA (R2 = 0.924, RMSE = 0.74 mmol/L). And the stacking model simulates the variation of methane and VFAs in relation to the dietary fiber content. To demonstrate the robustness of the model in the case of small samples, an independent validation experiment was conducted. The stacking model successfully simulated the transition of rumen fermentation type and the change of methane content under different concentrate-to-forage (C:F) ratios of TMR. These results suggest that the rumen fermentation parameter prediction model can be used as a decision-making basis for the optimization of dairy cow diet compositions, rapid screening of methane emission reduction, feed beneficial to dairy cow health, and improvement of feed utilization.
挥发性脂肪酸（VFAs）和甲烷是瘤胃发酵的主要产物。瘤胃发酵参数的定量研究可以使用体外技术和机器学习方法来进行。由于样本数量少，目前提出的模型泛化能力较差。在本研究中，使用堆叠集成学习方法和体外技术建立了奶牛瘤胃发酵参数（甲烷、乙酸（AA）和丙酸（PA））的预测模型。选择与全混合日粮（TMRs）营养水平相关的四个因素作为模型的输入：中性洗涤纤维（NDF）、酸性洗涤纤维（ADF）、粗蛋白（CP）和干物质（DM）。堆叠模型与基础学习器预测结果的比较表明，堆叠集成学习方法对瘤胃甲烷（决定系数（R2）=0.928，均方根误差（RMSE）=0.968 mL/g）、AA（R2 = 0.888，RMSE = 1.975 mmol/L）和PA（R2 = 0.924，RMSE = 0.74 mmol/L）具有更好的预测结果。并且堆叠模型模拟了甲烷和挥发性脂肪酸相对于膳食纤维含量的变化。为了证明该模型在小样本情况下的稳健性，进行了独立验证实验。堆叠模型成功模拟了不同TMR精粗比（C:F）下瘤胃发酵类型的转变和甲烷含量的变化。这些结果表明，瘤胃发酵参数预测模型可作为优化奶牛日粮组成、快速筛选甲烷减排、筛选有利于奶牛健康的饲料以及提高饲料利用率的决策依据。
