G. Andre

Applicability of day-to-day variation in behavior for the automated detection of lameness in dairy cows

Lameness is a major problem in modern dairy husbandry and has welfare implications and other negative consequences. The behavior of dairy cows is influenced by lameness. Automated lameness detection can, among other methods, be based on day-to-day variation in animal behavior. Activity sensors that measure lying time, number of lying bouts, and other parameters were used to record behavior per cow per day. The objective of this research was to develop and validate a lameness detection model based on daily activity data. Besides the activity data, milking data and data from the computerized concentrate feeders were available as input data. Locomotion scores were available as reference data. Data from up to 100 cows collected at an experimental farm during 23 mo in 2010 and 2011 were available for model development. Behavior is cow-dependent, and therefore quadratic trend models were fitted with a dynamic linear model on-line per cow for 7 activity variables and 2 other variables (milk yield per day and concentrate leftovers per day). It is assumed that lameness develops gradually; therefore, a lameness alert was given when the linear trend in 2 or more of the 9 models differed significantly from zero in a direction that corresponded with lameness symptoms. The developed model was validated during the first 4 mo of 2012 with almost 100 cows on the same farm by generating lameness alerts each week. Performance on the model validation data set was comparable with performance on the model development data set. The overall sensitivity (percentage of detected lameness cases) was 85.5% combined with specificity (percentage of nonlame cow-days that were not alerted) of 88.8%. All variables contributed to this performance. These results indicate that automated lameness detection based on day-to-day variation in behavior is a useful tool for dairy management.

Quantifying the effect of heat stress on daily milk yield and monitoring dynamic changes using an adaptive dynamic model

Automation and use of robots are increasingly being used within dairy farming and result in large amounts of real time data. This information provides a base for the new management concept of precision livestock farming. From 2003 to 2006, time series of herd mean daily milk yield were collected on 6 experimental research farms in the Netherlands. These time series were analyzed with an adaptive dynamic model following a Bayesian method to quantify the effect of heat stress. The effect of heat stress was quantified in terms of critical temperature above which heat stress occurred, duration of heat stress periods, and resulting loss in milk yield. In addition, dynamic changes in level and trend were monitored, including the estimation of a weekly pattern. Monitoring comprised detection of potential outliers and other deteriorations. The adaptive dynamic model fitted the data well; the root mean squared error of the forecasts ranged from 0.55 to 0.99 kg of milk/d. The percentages of potential outliers and signals for deteriorations ranged from 5.5 to 9.7%. The Bayesian procedure for time series analysis and monitoring provided a useful tool for process control. Online estimates (based on past and present only) and retrospective estimates (determined afterward from all data) of level and trend in daily milk yield showed an almost yearly cycle that was in agreement with the calving pattern: most cows calved in winter and early spring versus summer and autumn. Estimated weekly patterns in terms of weekday effects could be related to specific management actions, such as change of pasture during grazing. For the effect of heat stress, the mean estimated critical temperature above which heat stress was expected was 17.8±0.56°C. The estimated duration of the heat stress periods was 5.5±1.03 d, and the estimated loss was 31.4±12.2 kg of milk/cow per year. Farm-specific estimates are helpful to identify management factors like grazing, housing and feeding, that affect the impact of heat stress. The effect of heat stress can be decreased by modifying these factors.