The transition period is one of the most challenging periods in the lactation cycle of high-yielding dairy cows. It is commonly known to be associated with diminished animal welfare and economic performance of dairy farms. The development of data-driven health monitoring tools based on on-farm available milk yield development has shown potential in identifying health-perturbing events. As proof of principle, we explored the association of these milk yield residuals with the metabolic status of cows during the transition period. Over 2 yr, 117 transition periods from 99 multiparous Holstein-Friesian cows were monitored intensively. Pre- and postpartum dry matter intake was measured and blood samples were taken at regular intervals to determine β-hydroxybutyrate, nonesterified fatty acids (NEFA), insulin, glucose, fructosamine, and IGF1 concentrations. The expected milk yield in the current transition period was predicted with 2 previously developed models (nextMILK and SLMYP) using low-frequency test-day (TD) data and high-frequency milk meter (MM) data from the animal's previous lactation, respectively. The expected milk yield was subtracted from the actual production to calculate the milk yield residuals in the transition period (MRT) for both TD and MM data, yielding MRTTD and MRTMM. When the MRT is negative, the realized milk yield is lower than the predicted milk yield, in contrast, when positive, the realized milk yield exceeded the predicted milk yield. First, blood plasma analytes, dry matter intake, and MRT were compared between clinically diseased and nonclinically diseased transitions. MRTTD and MRTMM, postpartum dry matter intake and IGF1 were significantly lower for clinically diseased versus nonclinically diseased transitions, whereas β-hydroxybutyrate and NEFA concentrations were significantly higher. Next, linear models were used to link the MRTTD and MRTMM of the nonclinically diseased cows with the dry matter intake measurements and blood plasma analytes. After variable selection, a final model was constructed for MRTTD and MRTMM, resulting in an adjusted R2 of 0.47 and 0.73, respectively. While both final models were not identical the retained variables were similar and yielded comparable importance and direction. In summary, the most informative variables in these linear models were the dry matter intake postpartum and the lactation number. Moreover, in both models, lower and thus also more negative MRT were linked with lower dry matter intake and increasing lactation number. In the case of an increasing dry matter intake, MRTTD was positively associated with NEFA concentrations. Furthermore, IGF1, glucose, and insulin explained a significant part of the MRT. Results of the present study suggest that milk yield residuals at the start of a new lactation are indicative of the health and metabolic status of transitioning dairy cows in support of the development of a health monitoring tool. Future field studies including a higher number of cows from multiple herds are needed to validate these findings.

(Sub)clinical hypocalcaemia occurs frequently in the dairy industry, and is one of the earliest symptoms of an impaired transition period. Calcium deficiency is accompanied by changes in cows’ daily behavioural variables, which can be measured by sensors. The goal of this study was to construct a predictive model to identify cows at risk of hypocalcaemia in dairy cows using behavioural sensor data. For this study 133 primiparous and 476 multiparous cows from 8 commercial Dutch dairy farms were equipped with neck and leg sensors measuring daily behavioural parameters, including eating, ruminating, standing, lying, and walking behaviour of the 21 days before calving. From each cow, a blood sample was taken within 48 h after calving to measure their blood calcium concentration. Cows with a blood calcium concentration ≤2.0 mmol/L were defined as hypocalcemic. In order to create a more context based cut-off, a second way of dividing the calcium concentrations into two categories was proposed, using a linear mixed-effects model with a k-Means clustering. Three possible binary predictive models were tested; a logistic regression model, a XgBoost model and a LSTM deep learning model. The models were expanded by adding the following static features as input variables; parity (1, 2 or 3＋), calving season (summer, autumn, winter, spring), day of calcium sampling relative to calving (0, 1 or 2), body condition score and locomotion score. Of the three models, the deep learning model performed best with an area under the receiver operating characteristic curve (AUC) of 0.71 and an average precision of 0.47. This final model was constructed with the addition of the static features, since they improved the model’s tuning AUC with 0.11. The calcium label based on the cut-off categorization method proved to be easier to predict for the models compared to the categorization method with the k-means clustering. This study provides a novel approach for the prediction of hypocalcaemia, and an ameliorated version of the deep learning model proposed in this study could serve as a tool to help monitor herd calcium status and to identify animals at risk for associated transition diseases.

Calving is one of the most critical moments during the life of a cow and their calves. Timely supervision is therefore crucial for animal welfare as well as the farm economics. In this study, we propose a framework to predict calving within 24 h, 12 h, 6 h, 3 h and 1 h of dairy cows using sequential sensor data. In particular, data were extracted from 2363 cows coming from 8 commercial farms between August 2016 and November 2020. Two sensors attached to the neck and leg of each cow measured rumination, eating, lying, standup, walking and inactive behavior on a minute basis. A novel methodology was used to impute the missing values in the sensor sequences by leveraging the observed values of all the behavioral activities recorded by the sensors. A deep learning model was then used to predict the moment of calving on an hourly basis using the imputed sensor sequences. Results show that 65% of the calvings within 24 h can be detected with a precision of 77%, while 57% of calvings occurring within 3 h can be identified with a precision equal to 49%. Moreover, we find that using the missing value imputations significantly improves the predictive performance for observations containing up to 60% of missing values. The framework proposed in this study can be used by farmers to optimize their calving management and hence improve animal monitoring.

Existing lactation models predict milk yields based on a fixed amount of observed milk production in early lactation. In contrast, this study proposes a model to predict the entire lactation curve of dairy cows by leveraging historical milk yield information observed in the preceding cycle. More specifically, we present a deep learning framework to encode the model inputs, predict the latent representation of the milk yield sequences and generate the corresponding lactation curves. Results show that the proposed framework outperforms the baseline models and that during the first 26 days of lactation, the model’s predictions are more accurate than those of a state-of-the-art lactation model which is able to leverage the observed milk yields. As a result, the framework presented in this study allows farmers to increase their forecast horizon with respect to predicting its herd’s total production and hence facilitates optimal herd management. Additionally, the model can be used to compare a cow’s actual and expected milk yield over the entire course of the lactation cycle. This in turn can help to accelerate disease detection and enhance current animal monitoring systems. Finally, as the model incorporates the impact of health and reproduction events as well as herd management on the cow’s productivity, future earnings and costs can be estimated more accurately.

In this study, we propose a lactation model that estimates the daily milk yield by using autoencoders to generate a latent representation of all milk yields observed during the entire lactation cycle, irrespective of the length of the time interval between the different measurements. More specifically, we propose a sequential autoencoder (SAE) to process the sequential data, extract and decode the low-dimensional representations and generate the milk yield sequences. The SAE is compared with a more traditional multilayer perceptron model (MLP) which uses herd and parity information and lagged milk yields as input. Results show that incorporating the recorded daily milk yields, lactation number, herd statistics as well as reproduction and health events the cow encountered during the lactation cycle results in the most qualitative latent representations. Moreover, by leveraging these low-dimensional encodings, the SAE reconstructed the entire milk yield curve with a higher accuracy than the MLP. Hence, we present a framework that is able to infer missing milk yields along the entire lactation curve which facilitates selection and culling decisions as well as the estimation of future earnings and costs. Furthermore, the model allows farmers to enhance their animal monitoring systems as it incorporates the sequence of health and reproduction events to forecast the cow’s future productivity.