Development of prediction model for body weight and energy balance indicators from milk traits in lactating dairy cows based on deep neural networks

To develop a body weight (BW) prediction model using milk production traits and present a useful indicator for energy balance (EB) evaluation in dairy cows. Data were collected from 30 Holstein cows using an automatic milking system. BW prediction models were developed using multiple linear regression (MLR), local regression (LOESS), and deep neural networks (DNN). Milk production traits readily available on commercial dairy farms, such as energy-corrected milk (ECM), fat-to-protein ratio, days in milk (DIM), and parity, were used as input variables for BW prediction. The EB was evaluated as the difference between energy intake and energy demand. The DNN model showed the greatest predictive accuracy for BW compared with the LOESS and MLR models. The BW predicted using the DNN model was used to calculate the energy demand. Our results revealed that the day on which the EB status transitioned from negative to positive differed among cows. The cows were assigned to one of the three EB index groups. EB index 1 indicated that the day of EB transition was within DIM <= 70. The EB indexes 2 and 3 were 70 < DIM <= 140 and 140 < DIM <= 305, respectively. EB index 3 had the lowest EB, which is the slowest to transition from a negative to a positive energy balance compared with EB indexes 1 and 2. The highest ECM and feed efficiency were observed for EB index 3. The calving interval was the shortest for EB index 1. EB of individual cows during lactation can be estimated and monitored with moderately high accuracy using EB indexes.