This study highlights the importance of monitoring cattle feeding behavior using the YOLO algorithm for object detection. Videos of six Charolais bulls were recorded on a French farm, and three feeding behaviors (biting, chewing, visiting) were identified and labeled using Roboflow. YOLOv8 and YOLOv10 were compared for their performance in detecting these behaviors. YOLOv10 outperformed YOLOv8 with slightly higher precision, recall, mAP50, and mAP50-95 scores. Although both algorithms demonstrated similar overall accuracy (around 90%), YOLOv8 reached optimal training faster and exhibited less overfitting. Confusion matrices indicated similar patterns of prediction errors for both versions, but YOLOv10 showed better consistency. This study concludes that while both YOLOv8 and YOLOv10 are effective in detecting cattle feeding behaviors, YOLOv10 exhibited superior average performance, learning rate, and speed, making it more suitable for practical field applications.

In recent years, machine learning (ML) algorithms have emerged as powerful tools for predicting and modeling complex data. Therefore, the aim of this study was to evaluate the prediction ability of different ML algorithms and a traditional empirical model to estimate the parameters of lactation curves. A total of 1186 monthly records from 156 sheep lactations were used. The model development process involved training and testing models using ML algorithms. In addition to these algorithms, lactation curves were also fitted using the Wood model. The goodness of fit was assessed using correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE), relative absolute error (RAE), and relative root mean square error (RRSE). SMOreg was the algorithm with the best estimates of the characteristics of the sheep lactation curve, with higher values of r compared to the Wood model (0.96 vs. 0.68) for the total milk yield. The results of the current study showed that ML algorithms are able to adequately predict the characteristics of the lactation curve, using a relatively small number of input data. Some ML algorithms provide an interpretable architecture, which is useful for decision-making at the farm level to maximize the use of available information.

The aim of the present research was to evaluate the effect of Pithecellobium dulce, Tagetes erecta and Cosmos bipinnatus on methane emission, milk yield and dry matter intake in dairy cattle. A 4×4 Latin square experimental design was employed, using four multiparous Holstein cows of 553±72.4kg body weight, at mid lactation and average milk yield of 17.3±3kg/day. The experiment lasted 92 days, divided into four experimental periods of 23 days each. All cows had free access to maize and alfalfa silage in a 50:50 proportion, 4kg of concentrate/day and ad libitum access to water. Treatments consisted in supplementation of 0.5kg/day of the experimental plants, with one control treatment without supplementation. Each cow received one of each treatment in turn during one of the four periods. The C. bipinnatus reduced methane production by 16% (P0 0.05) by the use of C. bipinnatus or any other plant species. Supplementation at low doses of C. bipinnatus showed a reduction in ruminal methane production in dairy cows.

The objective of this study was to evaluate the level of concentrate supplementation on the production and chemical composition of milk from 12 crossbred F1 dual-purpose cows (½ Bos taurus – ½ Bos indicus) and estimate the emission of CH4, N2O, and CO2 gases. The study included 12 crossbred F1 dual-purpose cows over 60 days of lactation. The cows grazed on 28% tropical native grassland and 72% Brachiaria spp. and Cynodon neumfluensis, supplemented with 0, 150, 300, and 450g of concentrate per kg daily milk production, during three experimental periods of 15 days each in a crossover design. Pasture and concentrate samples were collected and were analyzed for dry matter, crude protein, neutral detergent fiber, and acid detergent fiber. Milk production (kg d-1) was recorded daily, nitrous oxide (N2O), and emissions from excreta and daily CH4 production were calculated. Results were analyzed with the SAS MIXED procedure. Concentrate supplementation in tropical crossbred dairy cows did not improve milk yield but increased CH4 and N2O production (P < 0.0001) per cow as the concentrate increased in the diet; the Ym factor from the tropical region yielded less CH4 than the IPCC Ym model (P < 0.0001). In conclusion, the calculation of CH4 using specific emission factors for the tropical climate region is better than the IPCC default emission factors in order not to overestimate the CH4 emissions.

Beef industry needs alternative feeding strategies to enhance both economic and environmental sustainability. Among these strategies, adjusting the diet dynamically according to the change of nutritional requirements (multiphase diet) has demonstrated its economic and environmental benefits in pig production systems. Therefore, this retrospective study aims to assess, through simulation, the theoretical economic and environmental benefits of introducing a multiphase diet for crossbreed bulls feeding (one or more diet changes). For this, individual data of BW, BW gain, and daily intake were recorded from 342 bulls during the last fattening period (112 days). These data were used to estimate individual trajectory of energy and protein requirements, which were subsequently divided by individual intake to calculate the required dietary energy and protein concentrations. The area between two functions (i.e., ƒ1: constant protein concentration in the original diet during fattening and ƒ2: estimated protein concentration requirements) was minimised to identify the optimal moments to adjust the dietary concentration of energy and protein. The results indicated that both energy and protein intake exceeded requirements on average (+16% and +28% respectively, P < 0.001), justifying the adoption of a multiphase diet. Modelling the individual trajectories of required metabolisable protein (MP, g/kg DM) during the fattening period resulted in exponential decay model in relation to BW [32120 × exp(-0.026 × BW) + 59.9], while the dietary net energy concentration followed a slightly quadratic model [2.26-0.0026 × BW + 0.000003 × BW²]. Minimisation of the area between curves showed two optimal moments to adjust the diet: at 312 kg and 385 kg of BW, indicating three diet phases: (a) <312 kg, (b) 312-385 kg, and (c) 385-600 kg. For the second and third phases, the dietary energy and protein concentration should be 70 g MP/kg DM and 1.70 Mcal/kg DM and 61 g MP/kg DM and 1.65 Mcal/kg DM, respectively. These diet adjustments might improve economic profitability by 29 €/animal, reduce estimated nitrogen excretions by 16% (P < 0.001), and maintain similar weight gain (P > 0.16) compared to the commercial diet. However, the decrease in dietary energy concentration led to increased fibre concentration, which in turn increased the estimated CH₄ emissions of animals with the multiphase diet (+44%, P < 0.001). Hence, multiphase diet could theoretically reduce feeding cost and nitrogen excretion from fattening cattle. Further in vivo studies should confirm these results and find optimal nutritional strategies to improve economic profitability and environmental impact.

Dairy cows are the highest daily and annual methane (CH₄) producers among all cattle categories. So, the present study aimed to evaluate the effect of increasing supplementation levels of a low-quality forage on dry matter intake (DMI), DM digestibility (DMD), milk production, enteric CH₄ emission, gross energy, and protein partitioning in Holstein cows. In total, eight cows (112 ± 38 days postpartum; mean ± s.d.) were randomly assigned to 4 treatments composed of 4 dietary neutral detergent fibre (NDF) inclusion levels (40.2% (control), 43.3%, 46.5%, and 50.5%) in a 4 × 4 repeated Latin square experimental design. The cows were fed corn + alfalfa silage and a concentrate (60:40 forage:concentrate ratio). To increase the contents of low-quality NDF, part of the silage was replaced with maize stover (MSTV). The CH₄ production was measured in an open-circuit respiration chamber. The DMI increased significantly and linearly (p < 0.05) with increasing levels of MSTV. However, the CH₄ yield decreased (p < 0.0001) as the NDF level increased (32.1, 28.1, 23.1, and 21.3 CH₄ L/kg DMI, respectively). DMD decreased as NDF levels in the diet increased (p < 0.0001). The NDF digestibility (DNDF) explained the better (p < 0.0001) CH₄ production response than DMD. It was concluded that low-quality forages can be used to regulate CH₄ production in subtropical and tropical climate regions.