Ruminants

The present study aimed to apply machine learning algorithms to estimate respiratory rate (RR, breaths min⁻¹) and rectal temperature (RT, °C) as indicators of thermal stress in Dorper breeding rams, based on environmental and thermal variables obtained through infrared thermography. The algorithms Random Forest (RF) and Support Vector Regression (SVR) with radial kernel were employed, using ocular globe temperature (OGT), air temperature (AT), relative humidity (RH), and coat surface temperature (CST) as predictor variables, and rectal temperature (RT) and respiratory rate (RR) as response variables. Data were collected on a property located in Garanhuns, Pernambuco State, Brazil, under two environmental conditions (with and without climate control), totaling 20 monitored animals and 120 paired observations. Model performance was evaluated using the coefficient of determination (R²), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE), complemented by cross-validation (k-fold = 10), and model interpretability was assessed using SHapley Additive exPlanations (SHAP) to quantify the contribution of each predictor variable to model predictions. The results indicated that the RF model showed superior performance in predicting the physiological variables RR and RT, with higher coefficients (RR: R² = 0.858; RT: R² = 0.687) and lower error values. For RR, the RF model achieved RMSE = 16.38 and MAE = 13.33; while for RT, the errors were RMSE = 0.217 and MAE = 0.154. In contrast, the radial kernel SVR model showed lower performance, with R² values of 0.742 (RR) and 0.533 (RT), and RMSE and MAE values of 21.05 and 17.38 for RR, and 0.262 and 0.196 for RT, respectively. The application of machine learning-based models proved to be a viable and accurate alternative for estimating physiological indicators of thermal stress, contributing to the development of automated thermal management strategies for sheep in the Brazilian semi-arid region. The proposed data-driven approach demonstrates that low-cost thermal sensors combined with explainable artificial intelligence can support automatic decision-making for climate adaptation and animal welfare in semi-arid sheep production systems.

Background: Cortisol is known as the main hormone released during stress responses in cattle and has been used to assess various stressors, including heat stress. This study investigated hair cortisol concentration (HCC) in different hair coat colors in dairy cows under natural heat stress conditions (temperature humidity index = 75). Methods: Hair samples were collected from the forehead region of ten multiparous cows (Brown Swiss, Montbéliarde, and Holstein) per group color at both the beginning and end of a three-week peak summer period in 2024 in the region of Jendouba, North Tunisia. Cows were grouped according to hair coat color (black, brown, red, white, and yellow) for subsequent analysis. Hair samples were prepared using a methanol-based separation protocol and analyzed via enzyme-linked immunosorbent assay (ELISA). Results: Meteorological data confirmed that cows were sustained under heat stress, with an average temperature humidity index value of 75; results indicated that black hair had considerably more HCC than white hair (p < 0.05). The results showed that there is a significant difference between HCC under three clusters (p < 0.05) according to hair color. Conclusions: The study emphasizes that hair color, along with factors such as breed and environmental conditions, should be carefully considered when using HCC to assess stress in cattle beyond simply black or white hair color.

Studies in taurine breeds have shown that genetic selection can improve the fatty acid (FA) profile of bovine milk, but studies are scarce considering Zebu animals. In this study, genetic parameters for FA concentrations and unsaturation indexes in the milk fat of Zebu cows were estimated, with emphasis on Gir and Guzerá breeds. Milk samples from 299 Gir and 266 Guzerá cows belonging to 22 herds distributed throughout Brazil were analyzed using gas chromatography. Fourteen individual FAs, 11 FA groups, four nutritional indexes, and five unsaturation indexes were evaluated. Tri-trait Bayesian models were applied, including 305-day milk and fat yields as “anchor” traits. Systematic effects such as contemporary group, age at calving, diet, sampling age class, and days in milk were considered. Palmitic acid was the most abundant FA, followed by oleic, stearic, and myristic acids. Heritability estimates ranged from moderate to high: 0.28–0.66 in Gir cows, and 0.25–0.74 in Guzerá cows, for individual FAs and FA groups. Unsaturation indexes also showed moderate to high heritability. Genetic correlations were generally strong, with long-chain FAs negatively correlated with short- and medium-chain FAs. The results suggest that genetic selection can be applied to improve the nutritional profile of milk fat in Zebu cattle.