The present study aimed to apply machine learning algorithms to estimate respiratory rate (RR, breaths min-1) and rectal temperature (RT, degrees 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.