Table_1_Causal structure search and modeling of precision dairy farm data for automated prediction of ketosis risk, and the effect of potential interventions.docx

Causal search techniques enable inference from observational data, such as that produced in Precision Livestock Farming. The Peter-Clark algorithm was used to produce four causal models, for the risk of ketosis in individual cows. The data set covered 1542 Holstein-Friesian cows on a commercial dairy farm in Slovakia, over a period of 18 months and had 483 variables, split into four samples for four-way cross validation. The cow data was sorted into quartiles by predicted postpartum blood ketone value. The observed incidences of ketosis by quartile were 3.14%, 6.35%, 6.77%, 15.1%. To test the effect of intervention on the reduction of ketosis cases on the farm, we predicted the expected effect of 20% lower dry matter in the total mixed ration over the 6 months pre-partum. Predicted reductions in incidence of ketosis for the highest risk (4th) quartile were -4.96%, -7.4%, -11.21%, and -11.07% of animals in the herd, respectively for the four models. The different predictions were due to the different causal structures estimated from the four data samples by the Peter-Clark causal model search algorithm. To accurately predict the effect of intervention for automatic optimization of herd performance it is necessary to determine the correct causal structure of the model. Collinearity of inputs due to e.g. grouping by pens, reduced the conditional independence of their effects, and therefore the ability of the Peter-Clark algorithm to determine the correct causal structure. To reduce the collinearity of variables, we recommend causal search on datasets from multiple farms or multiple years.

因果搜索技术能够从观测数据中推断结论，例如精养畜牧业所产生的数据。本研究采用 Peter-Clark 算法构建了四个因果模型，以分析个体奶牛发生酮病的风险。该数据集涵盖了斯洛伐克一家商业乳牛场1542头荷斯坦-弗里斯兰奶牛18个月内的数据，包含483个变量，分为四个样本以进行四重交叉验证。根据预测的产后血液酮体值，奶牛数据被分为四个四分位数。各四分位数中酮病发生观测率分别为3.14%、6.35%、6.77%、15.1%。为了测试干预措施对降低农场酮病病例的影响，我们预测了在产前6个月内总混合饲料中干物质降低20%的预期效果。对于风险最高的（第四）四分位数，四个模型预测的酮病发生率减少分别为-4.96%、-7.4%、-11.21%和-11.07%。不同的预测结果源于Peter-Clark 因果模型搜索算法从四个数据样本中估计的不同因果结构。为了准确预测干预措施的效果，以便自动优化群体性能，有必要确定模型的正确因果结构。由于如按栏舍分组等原因导致的输入变量共线性，降低了它们效应的条件独立性，从而影响了Peter-Clark 算法确定正确因果结构的能力。为了减少变量间的共线性，我们建议在来自多个农场或多个年份的数据集上进行因果搜索。