Predictive modelling of deviation from expected milk yield in transition cows on automatic milking systems

The transition period is a pivotal time in the production cycle of the dairy cow. It is estimated that between 30% and 50% of all cows experience metabolic or infectious disease during this time. One of the most common and economically consequential effects of disease during the transition period is a reduction in early lactation milk production. This has led to the utilisation of deviation from expected milk yield in early lactation as a proxy measure for transition health. However, to date, this analysis has been used exclusively for the retrospective assessment of transition cow health. Statistical models capable of predicting deviations from expected milk yield may allow producers to proactively manage animals predicted to suffer negative deviations in early lactation milk production. The objective of this retrospective cohort study was first, to explore the accuracy with which cow-level production and behaviour data collected on automatic milking systems (AMS) from 1-3 days in milk (DIM) can predict deviation from expected 30-day cumulative milk yield in multiparous cows. And second, to assess the accuracy with which predicted yield deviations can classify cows into groups which may facilitate improved transition management. Production, rumination, and physical activity data from 31 commercial AMS were accessed. A 3-step analytical procedure was then conducted. In Step 1, expected cumulative yield for 1-30 DIM for each individual cow-lactation was calculated using a mixed effect linear model. In Step 2, 30-Day Yield Deviation (YD) was calculated as the difference between observed and expected cumulative yield. Lactations were then assigned to one of three groups based on their YD, RED Group (0% YD). In Step 3, yield, rumination, and physical activity data from days 1-3 in lactation were used to predict YD using machine learning models. Following external validation, YD was predicted across the test data set with a mean absolute error of 9%. Categorisation of animals suffering large negative deviations (RED group) was achieved with a specificity of 99%, sensitivity of 35%, and balanced accuracy of 67%. Our results suggest that milk yield, rumination and physical activity patterns expressed by dairy cows from 1-3 DIM have utility in the prediction of deviation from expected 30-day cumulative yield. However, these predictions currently lack the sensitivity required to classify cows reliably and completely into groups which may facilitate improved transition cow management.

Associations of reproductive indices with fertility outcomes, milk yield, and survival in Holstein cows

The study is part of a research effort investigating potential associations between genomic variation and fertility of Holstein cows. The objective was to compare the reproductive performance of Holstein cows in 3 categories of 2 reproductive indices (RI) that were developed for the allocation of cows in a ranking for potential fertility, based on the predicted probability of pregnancy. The associations between categories of the developed indices and multiple fertility variables in a large multistate population of Holstein cows were tested. In addition, we analyzed associations among the RI categories with milk yield and survival. Based on phenotypic information from individual cows, 2 reproductive indices (RI1 and RI2) were developed, representing a predicted probability that a cow will become pregnant at first artificial insemination postpartum, as a function of explanatory variables used in a logistic model. Data from a total of 11,733 cows calving in 16 farms located in 4 regions of the United States (Northeast, Midwest, Southeast, and Southwest) were available. Cows were enrolled at parturition and monitored weekly for reproductive events, health status, milk yield, and survival. To develop the indices, potential significant effects were initially tested by univariate analyses. Effects with P ≤ 0.05 were offered to the multivariate analysis, and the final models were determined through backward elimination, considering potentially significant interactions. The final model for RI1 included the random effect of farm and a complement of significant fixed effects as explanatory variables influencing a pregnancy outcome: (1) incidence of retained fetal membranes; (2) metritis; (3) clinical endometritis; (4) lameness at 35 days in milk (DIM); (5) resumption of postpartum ovulation by 50 DIM; (6) season of calving; and (7) parity number. The model for RI2 included (1) parity number; (2) body condition score at 40 DIM; (3) incidence of retained fetal membranes; (4) metritis; (5) resumption of postpartum ovulation by 50 DIM; (6) region; (7) subclinical ketosis; (8) mastitis; (9) clinical endometritis; and (10) milk yield at the first milk test after calving; as well as the interaction effects of postpartum resumption of ovulation by 50 DIM × region; mastitis × region; and milk yield at the first milk test after calving × parity number. Multivariate logistic regression, ANOVA, and survival analysis were used to test the correspondence between the resulting RI and individual fertility, milk yield, and survival from the population. To facilitate the analyses, the resulting RI values were categorized as low for cows in the lowest quartile, medium for cows within the interquartile range, or high for cows in the top quartile. We found consistent agreement between categories of the predicted RI and the measures of fertility and survival collected from individual cows. We conclude that the proposed RI represent a viable approach to refine the allocation of cows into potential low- and high-fertility populations.

Invited review: Big Data in precision dairy farming

Insight into current scientific applications of Big Data in the precision dairy farming area may help us to understand the inflated expectations around Big Data. The objective of this invited review paper is to give that scientific background and determine whether Big Data has overcome the peak of inflated expectations. A conceptual model was created, and a literature search in Scopus resulted in 1442 scientific peer reviewed papers. After thorough screening on relevance and classification by the authors, 142 papers remained for further analysis. The area of precision dairy farming (with classes in the primary chain (dairy farm, feed, breed, health, food, retail, consumer) and levels for object of interest (animal, farm, network)), the Big Data-V area (with categories on Volume, Velocity, Variety and other V’s) and the data analytics area (with categories in analysis methods (supervised learning, unsupervised learning, semi-supervised classification, reinforcement learning) and data characteristics (time-series, streaming, sequence, graph, spatial, multimedia)) were analysed. The animal sublevel, with 83% of the papers, exceeds the farm sublevel and network sublevel. Within the animal sublevel, topics within the dairy farm level prevailed with 58% over the health level (33%). Within the Big Data category, the Volume category was most favoured with 59% of the papers, followed by 37% of papers that included the Variety category. None of the papers included the Velocity category. Supervised learning, representing 87% of the papers, exceeds unsupervised learning (12%). Within supervised learning, 64% of the papers dealt with classification issues and exceeds the regression methods (36%). Time-series were used in 61% of the papers and were mostly dealing with animal-based farm data. Multimedia data appeared in a greater number of recent papers. Based on these results, it can be concluded that Big Data is a relevant topic of research within the precision dairy farming area, but that the full potential of Big Data in this precision dairy farming area is not utilised yet. However, the present authors expect the full potential of Big Data, within the precision dairy farming area, will be reached when multiple Big Data characteristics (Volume, Variety and other V’s) and sources (animal, groups, farms and chain parts) are used simultaneously, adding value to operational and strategic decision.