Dynamic forecasting of individual cow milk yield in automatic milking systems

Abstract

Accurate forecasting of dairy cow milk yield is useful to dairy farmers, both in relation to financial planning and for detection of deviating yield patterns, which can be an indicator of mastitis and other diseases. In this study we developed a dynamic linear model (DLM) designed to forecast milk yields of individual cows per milking, as they are milked in milking robots. The DLM implements a Wood's function to account for the expected total daily milk yield. It further implements a second-degree polynomial function to account for the effect of the time intervals between milkings on the proportion of the expected total daily milk yield. By combining these 2 functions in a dynamic framework, the DLM was able to continuously forecast the amount of milk to be produced in a given milking. Data from 169,774 milkings on 5 different farms in 2 different countries were used in this study. A separate farm-specific implementation of the DLM was made for each of the 5 farms. To determine which factors would influence the forecast accuracy, the standardized forecast errors of the DLM were described with a linear mixed effects model (lme). This lme included lactation stage (early, middle, or late), somatic cell count (SCC) level (nonelevated or elevated), and whether or not the proper farm-specific version of the DLM was used. The standardized forecast errors of the DLM were only affected by SCC level and interactions between SCC level and lactation stage. Therefore, we concluded that the implementation of Wood's function combined with a second-degree polynomial is useful for dynamic modeling of milk yield in milking robots, and that this model has potential to be used as part of a mastitis detection system.

Comparison of time-series models for monitoring temporal trends in endemic diseases sero-prevalence: lessons from porcine reproductive and respiratory syndrome in Danish swine herds

“…The same implementation of the DLM and DGLM was validated on simulated data in a previous study [6]. These models have further been validated and used in previous studies [12–15].…”

Review: Application and Prospective Discussion of Machine Learning for the Management of Dairy Farms

“…Automatic milking robots and milking parlors offer continuous animal-specific data for this use case. Dynamic linear modeling was able to forecast the cows’ individual milk yields per milking from automatically collected milking robot data [ 29 ]. The study used a large dataset ( n = 970,463 observations from 52 farms) of existing, automatically generated data to predict management relevant yields.…”

Unweaving tangled mortality and antibiotic consumption data to detect disease outbreaks – Peaks, growths, and foresight in swine production

“…Large deviations between forecasted and observed values could then be taken as an indication that the herd was deviating from the healthy state. This approach to defining the DLM has been described in previous studies ([23, 35, 36]).…”

“…However, the potential use of these data for outbreak detection and surveillance purposes at herd level remains unexplored. One possible approach is to train models on data from healthy herds, set up a monitoring system based on these model and, any deviation from the expected outcome sets a warning, as described in previous studies [21–23]. This is particularly useful for authorities to detect and monitor outbreaks and follow up changes in prevalence on the national scale.…”