Reproductive efficiency is a critical determinant of productivity and profitability in sheep farming. Traditional selection methods have largely relied on phenotypic traits and historical reproductive records, which are often limited by subjectivity and delayed feedback. Recent advancements in artificial intelligence (AI), including video tracking, wearable sensors, and machine learning (ML) algorithms, offer new opportunities to identify behavior-based indicators linked to key reproductive traits such as estrus, lambing, and maternal behavior. This review synthesizes the current research on AI-powered behavioral monitoring tools and proposes a conceptual model, ReproBehaviorNet, that maps age- and sex-specific behaviors to biological processes and AI applications, supporting real-time decision-making in both intensive and semi-intensive systems. The integration of accelerometers, GPS systems, and computer vision models enables continuous, non-invasive monitoring, leading to earlier detection of reproductive events and greater breeding precision. However, the implementation of such technologies also presents challenges, including the need for high-quality data, a costly infrastructure, and technical expertise that may limit access for small-scale producers. Despite these barriers, AI-assisted behavioral phenotyping has the potential to improve genetic progress, animal welfare, and sustainability. Interdisciplinary collaboration and responsible innovation are essential to ensure the equitable and effective adoption of these technologies in diverse farming contexts.

This study investigates key physiological, genetic, and environmental factors influencing maternal success in sheep to enhance lamb survival and maternal quality. Using data from native and crossbred prolific ewes in a high-altitude, cold-climate region, we applied machine learning models to predict mothering scores based on dam characteristics, birth conditions, and lamb attributes. Pregnant ewes were monitored 24 hours per day, beginning three days before parturition, with minimal human intervention. Predictor variables included dam breed, body weight, age, litter size, lamb genotype, lambing season, time of lambing, parturition duration, and lambing assistance. Several machine learning algorithms, including Random Forest, Decision Trees, Logistic Regression, and Support Vector Machines (SVM), were evaluated for predictive accuracy. The Random Forest model achieved the highest accuracy (67.2%) and demonstrated the best overall performance with a 0.41 Kappa statistic and the lowest mean absolute error (0.59). Feature importance analysis identified dam weight at birth, parturition duration, and lamb birth weight as the strongest predictors of maternal success. The Decision Tree model highlighted time of lambing, lamb genotype, and lambing assistance as key decision points for classifying mothering ability. Further analysis revealed that shorter parturition durations (≤ 38 min), unassisted lambing, and smaller litter sizes were associated with higher mothering scores. Breed-specific maternal differences were also observed, with crossbred prolific ewes exhibiting stronger maternal instincts. These findings provide actionable insights for precision livestock farming, emphasizing the importance of genetic selection, birthing management, and environmental monitoring to enhance maternal efficiency and lamb survival.

Reproductive efficiency is a critical determinant of productivity and profitability in sheep farming. Traditional selection methods have largely relied on phenotypic traits and historical reproductive records, which are often limited by subjectivity and delayed feedback. Recent advancements in artificial intelligence (AI), including video tracking, wearable sensors, and machine learning algorithms, provide new opportunities to identify behavior-based indicators linked to key reproductive traits such as estrus, lambing, and maternal behavior. This review synthesizes current research on the use of AI-powered behavioral monitoring tools to enhance selection accuracy and breeding outcomes. The integration of accelerometers, GPS systems, and computer vision models enables continuous, non-invasive monitoring of individual animals, allowing for the early detection of reproductive events and maternal performance. We also present a conceptual model, ReproBehaviorNet, that maps age and sex specific behaviors to bio-logical processes and AI applications, supporting real-time decision-making in both intensive and semi-intensive systems. This approach not only improves breeding pre-cision and genetic progress but also contributes to better animal welfare and sustainable management. Our findings underscore the importance of interdisciplinary collaboration and data-driven tools in the evolution of livestock selection strategies.

Intensive sheep and goat farming in hot-arid regions faces unique welfare challenges that differ substantially from those encountered in cooler climates; however, few practical and validated assessment tools are specifically designed to assess welfare under such extreme conditions. In this study, the term practical refers to field feasibility under routine farm conditions, limited assessment time, and suitability for reliability-based application, rather than comprehensive validation of welfare outcomes. This study aimed to develop and pilot-test a simplified welfare assessment protocol, based on a reduced set of clearly defined, field-applicable indicators supported by explicit operational definitions and standardized scoring criteria, tailored for the United Arab Emirates, with a specific focus on extreme heat and intensive husbandry conditions. Candidate indicators were identified from validated international sources and screened for applicability to arid climates, meat-oriented production, and intensive systems. The refined indicator set was converted into operational scoring sheets and applied by trained undergraduate animal science students as assessors to 100 animals at an intensive research farm. Inter-observer reliability was calculated using Fleiss’ Kappa to evaluate consistency across assessors. Most behavioural and health indicators demonstrated substantial to almost perfect inter-observer agreement (κ-based), while environmental and some tactile indicators, such as body condition and hydration tests, showed moderate reliability. Based on the most reliable indicators, a climate-sensitive Arid-Hot Small Ruminant Welfare Index (ASR-WI) was developed by weighting four welfare domains—Behaviour and Mental State, Environment, Nutrition, and Health. The findings confirm that a simplified welfare assessment protocol can be reliably implemented under intensive hot-arid conditions when clear scoring criteria and structured assessor training are provided. The resulting protocol and index offer a practical foundation for routine welfare monitoring under intensive hot-arid conditions, as well as for policymaking and future longitudinal research.