The present study aimed to evaluate the accuracy of a numerical model, quantifying real-time ultrasonographic (RTU) images of pregnant sows, to predict litter size. The time of the test with the least error was also considered. A number of 4165 pregnancies in Farm 1 and 438 in Farm 2 were diagnosed twice, with the quality of the RTU images translated into rated-scale values (RSV1 and RSV2). When a deep neural network (DNN) was trained, the evaluation of the method showed that the prediction of litter size can be performed with little error. Root square mean error (RMSE) for training, validation with data from Farm 1, and testing on the data from Farm 2 were 0.91, 0.97, and 1.05, respectively. Corresponding mean absolute errors (MAE) were 2.27, 2.41, and 2.58. Time appeared to be a critical factor for the accuracy of the model. The smallest MAE was achieved when the RTU was performed at days 20–22. It is concluded that a numerical, RTU imaging model is a prominent predictor of litter size, when a DNN is used. Therefore, early routinely evaluated RTU images of pregnant sows can predict litter size, with machine learning, in an automated manner and provide a useful tool for the efficient management of pregnant sows.

This paper aims to provide pig farmers with the necessary information to guide strategic decisions through the development of a tool that allows them to calculate and control their production costs. A financial ratio analysis can be used as a starting point when assessing and improving a farm’s economic sustainability. The objective of the present article is to (1) provide insight into the financial ratios commonly used for pig farm assessments and (2) how they may be applied through an advisory tool to assess farm economic sustainability. Moreover, in this study, different financial ratios were examined to uncover trade-offs and synergies between them. Using the Farm Accountancy Data Network (FADN), we analyzed Spearman correlations between financial ratios. The correlation between these sets of indicators suggested that they could be used to estimate dairy farm economic sustainability. Our results showed that pig farms face a financial situation that can be improved. Pig farmers can benefit from this tool in multiple ways, by gaining an understanding of the costs and revenues leading to investment decisions, managing the risks, planning for potential growth, and having greater access to funding opportunities.

Heat stress (HS) suppresses voluntary feed intake in lactating sows, yet individual-level characterization of indoor and outdoor Temperature–Humidity Index (THI) linked to feed intake is rare in Mediterranean commercial settings. This prospective observational study enrolled 272 F1-crossbred sows (parities 1–7) farrowing from May–October 2025 at a commercial Greek farm. Outdoor THI was computed from 8760 hourly records and indoor THI from calibrated dataloggers; individual daily lactation feed intake (days 1–30) was recorded via RFID transponder-feeders. Building cooling (ΔTHI = 3.7–14.3) attenuated but did not eliminate mild-to-moderate indoor stress from June–September. Only parity and stillbirth count were Bonferroni-significant correlates of feed intake (parity: β = +0.142, p = 0.002). A sow-day Gradient Boosting model, evaluated by grouped cross-validation to prevent within-sow leakage, achieved CV-R² = 0.406 ± 0.045, providing a validated, herd-tested framework for parity-stratified feeding management, pending external validation across farms, genetics, and climates.

Climate change and increasing thermal pressure represent major long-term challenges for sheep production, particularly in climate-vulnerable regions and production systems. Heat stress can alter thermoregulatory, metabolic, endocrine, reproductive, oxidative, and immune responses, with consequences for animal health, welfare, and productive performance. This review critically evaluates current evidence on the biological and production-related consequences of heat stress in sheep and examines nutritional, genetic, environmental, health-management, and precision-monitoring approaches within a climate-resilience framework. The evidence indicates substantial variation in the magnitude and persistence of heat-stress responses according to breed or genotype, physiological and nutritional status, production system, and the intensity, duration, and timing of thermal exposure. Controlled studies provide important mechanistic insight, whereas field studies capture commercial complexity but are more strongly influenced by concurrent nutritional, climatic, health, and management factors. Nutritional, genetic, environmental, and precision-monitoring interventions offer opportunities to support adaptation, but their effectiveness and transferability across production systems require further validation. Improving climate resilience will therefore require context-specific combinations of complementary strategies rather than uniform solutions. Major research priorities include long-term field evaluation, improved comparability of heat-stress assessment, investigation of concurrent stressors, and evaluation of the practical and economic feasibility of adaptation and mitigation measures under commercial conditions.