The aim of this research was to evaluate the effects of postpartum day and parity season on the lactoferrin (LF), immunoglobulin G (IgG), and chemical composition of Murciano–Granadina goat colostrum during the first 96 h after kidding, and the use of the Brix refractometer to estimate IgG content. A herd of 3500 intensively managed Murciano–Granadina dairy goats (45–50 kg body weight) was used. Colostrum samples were collected from days 1 to 4 postpartum in the winter, spring, summer, and autumn. The colostrum composition was assessed using an automated infrared method; the LF and IgG concentrations were measured using an ELISA, and for the Brix percentage, we used a digital refractometer. Colostrum taken on the first postpartum day showed the highest concentrations of LF, IgG, proteins and non-fat solids (NFSs). As the postpartum days progressed, a rapid decrease in the LF, IgG, protein, and NFS contents and the Brix value was observed. In contrast, the lactose content increased steadily until the fourth postpartum day (p < 0.001). The season influenced milk yield, LF, IgG, protein, fat, and somatic cell content (p < 0.05). LF contents were significantly higher in the spring season, IgG contents were higher in autumn colostrum, and fat components were higher in the winter season. The colostrum Brix value showed a positive correlation with the ELISA colostrum LF (r = 0.716, p < 0.001) and IgG (r = 0.894, p < 0.001) determination; a 20 mg IgG/mL colostrum concentration corresponded to 18 °Brix. Our results corroborate the importance of feeding colostrum to newborns on the first day after birth, not only because of its high level of IgG but also because of its greater presence of the other bioactive protein compounds such as lactoferrin.

Pig weighing is an essential procedure for monitoring growth and animal health; however, conventional methods are often labor-intensive, costly, and potentially stressful. In this context, this study proposes a non-invasive approach for estimating the body weight of pigs during the growing stage based on computer vision and the YOLOv11 algorithm, enabling automatic segmentation and individual identification in multi-animal environments. The study used RGB images of 10 group-housed pigs captured throughout the growing phase, in which automatic dorsal segmentation was combined with individual identification through numerical markings. From the generated binary masks, the segmented dorsal area was extracted and used as a predictor variable in Linear Regression and a Multilayer Perceptron (MLP) Artificial Neural Network. The YOLOv11 model showed consistent performance in the segmentation task, achieving test-set metrics of Precision = 0.849, Recall = 0.886, mAP@0.50 = 0.936, and mAP@0.50–0.95 = 0.819, demonstrating good generalization capability in scenarios with intense animal interaction. In the weight prediction stage, Linear Regression and the MLP achieved high coefficients of determination (R² = 0.96 and 0.95, respectively) with low errors (RMSE = 1.52 kg and 1.63 kg; MAE = 1.20 kg and 1.25 kg), indicating a strong correlation between segmented dorsal area and actual body weight. Class-wise analysis revealed superior performance for classes 7 and 9, with R² values up to 0.98 and RMSE below 1.1 kg, whereas class 8 showed greater error dispersion, associated with higher morphological variability and a smaller number of available samples. These results demonstrate that the direct use of morphometric information extracted from segmented masks in 2D images constitutes a robust, accurate, and low-cost approach for automatic pig body-weight estimation. Moreover, this study is among the few addressing this task specifically during the growing stage, highlighting its potential for future deployment in embedded systems and intelligent monitoring platforms for precision pig farming, although further evaluation of computational efficiency and real-time performance is still required.

Comfort index and environmental variables are indicators of thermal stress conditions inside a livestock facility. The environmental conditions of ten different constructive typologies of swine-production facilities with natural ventilation were characterized in a tropical country (Antioquia, Colombia). Temperature and humidity index (THI), enthalpy (H), animal surface temperature (ST), light intensity, and noise level were measured and computed for each typology, which were located at heights above sea levels between 8:00-23:00. Data was analyzed as a function of each typology, geographical altitude, and time of the day. It was employed descriptive statistics, analysis of variance, and contour maps to analyze the data. It was found that more than 80% of the typologies presented moderate or critical stress conditions associated with the construction typology, not suitable THI and light intensity values, especially in warm and mild-mild climates. Showing high special variability inside the facilities. New typological designs and bioclimatic conditioning for swine facilities need to be studied To be implemented in these climatic conditions.

The increasing use of hyperprolific sows has led to greater litter heterogeneity, highlighting the need for effective nutritional support for low-birth-weight piglets. This study explores the potential of using surplus goat transitional milk as a nutritional supplement for piglets, especially for those facing increased survival and developmental challenges during the early life stages. To this end, two experiments were carried out as follows: in the first, goat transitional milk was administered via an oro-esophageal feeding tube to all piglets in the litter; in the second, concentrated transitional milk was administered via an oral dispenser to whole litters composed of low-birth-weight piglets. Performance parameters, mortality, and serum IgG levels were measured. In Experiment 1, supplementation with goat colostrum showed a tendency to improve weight in piglets ≤ 1100 g, with no significant effect on temperature, serum IgG level, or mortality. In Experiment 2, supplementation with goat colostrum did not affect live weight, rectal temperature, or serum IgG levels at 10 and 21 days. However, there was a trend towards lower mortality at 21 days in the supplemented piglets. These results suggest that goat transitional milk may provide context-dependent benefits, with a potentially greater impact on vulnerable piglets in more difficult conditions. Furthermore, its use represents a sustainable strategy to valorize surplus milk from goat farms.

The aim of this study was to verify the effect of precocity on economically important traits in Brahman cows from a herd in the low tropics of Colombia. Records from 84 cows and their calves were used during four consecutive calving seasons. Weaning weight (WW), 270-day adjusted weaning weight (270WW), lactation length (LL), age at calving (AC), and calving interval (CI) were evaluated. Cows were assigned to three categories (CAT1 to CAT3) based on their age at first calving (Early: ≤30 months; Slightly early: 30-33 months; Late: ≥34 months). Five approaches were used: 1) descriptive statistics; 2) a linear model including, as sources of variation depending on the trait, calving season (CS), calving year (CY), CAT, calf sex (CS), age at weaning (AW), length of lactation in the previous calving (LLD), and weaning weight in the previous calving (WW); 3) conditional probability analysis to verify the probability of cows in the different CAT categories; 4) multivariate multiple correspondence analysis (MCA); 5) based on the MCA results, the number of cows with acceptable and good performance for each category was verified. In all the cows, early maturing cows had a lower average lifetime performance (ALP). CAT was only influential (p=0.045) on ALP. CAT1 cows in their first two calvings showed poor to acceptable performance for the evaluated traits, but over the course of their productive life, they achieved better performance for these traits compared to cows in the other CAT categories.

Individual recognition of animals on modern farms is critical for their management. Identification of pigs is the first step to individualizing the information of each animal for decision-makers. Therefore, the objective of this study was the detection of pigs in the weaning phase employing deep learning techniques. The weaning phase was selected due to issues related to piglet’s adaptation after nursing, presenting social, environmental, physiological and management transitions, challenges, where the piglets tend to cluster together, representing an image processing problem. The YOLOv7 algorithm and VGG Image Annotator were used to detect individual pigs in two pens separated by gender. Frames taken from videos recorded in production conditions of a small farm, in tropical conditions in Colombia, were used for training purposes. Animal postures, clustering and lighting conditions were considered. The Precision, Recall and mAP were used to quantify model performance. A precision of 98.3% was reached with a threshold of 0.9 and a Recall of 98.5% was achieved with a threshold of 0.85. Data augmentation techniques were employed to increase the dataset. The trained algorithm is suitable to detect weaning pig bodies under different conditions, being the first step for implementing precision farming techniques in this pig phase.