AI-Driven Welfare Assessment and Decision-Support Systems for Sustainable Small Ruminant Production in Challenging Climates

Small ruminants, particularly sheep and goats, play a crucial role in food security and rural livelihoods in regions characterized by extreme climatic conditions, including hot-arid and semi-arid environments. These production systems present welfare challenges that conventional assessment frameworks, largely developed under temperate conditions and for other species, are ill-equipped to address. The physiological and behavioral complexity of sheep and goats under climate stress calls for species-specific welfare indicators that reflect their distinct responses to environmental pressure, rather than relying on generalized environmental measures. Recent advances in Precision Livestock Farming (PLF) and Artificial Intelligence (AI) offer transformative opportunities for continuous, objective, and scalable monitoring of animal welfare, with the animal itself, rather than its surroundings, at the center of assessment. Technologies such as wearable sensors, automated behavior recognition, computer vision, and machine-learning-based decision-support systems enable real-time capture of animal-based physiological and behavioral welfare signals in small ruminants. This Research Topic aims to gather cutting-edge research applying PLF and AI to animal-centered welfare assessment and management in sheep and goat production systems exposed to extreme climatic stress. Contributions focusing on species-specific welfare indicators, behavioral and physiological responses, early detection of welfare compromise, and AI-driven decision-support tools are particularly encouraged. The Research Topic also welcomes studies addressing the development and validation of animal-based digital welfare indicators and the translation of data outputs into actionable, on-farm decisions. By bringing together animal scientists, engineers, data scientists, and educators, this Research Topic seeks to advance innovative, species-sensitive welfare solutions that enhance resilience, sustainability, and ethical livestock production in small ruminant systems worldwide.The goal of this Research Topic is to advance the application of Precision Livestock Farming and Artificial Intelligence for the assessment and enhancement of welfare in sheep and goats raised under extreme climatic conditions, with a primary focus on animal-based welfare indicators and species-specific methodologies. Small ruminants possess unique physiological and behavioral adaptations to harsh environments, and effective welfare monitoring must be grounded in these species-specific traits rather than broad environmental parameters. This Research Topic aims to identify and promote innovative digital approaches that prioritize animal-based indicators such as behavioral, postural, and physiological signals and leverage AI-driven decision-support systems to enable early detection of welfare risks and informed management decisions. By centering the animal rather than the environment, the Research Topic seeks to generate practical, scalable, and species-appropriate solutions that improve welfare outcomes while supporting productivity and sustainability in climate-challenged livestock systems.This Research Topic welcomes original research articles, reviews, and methodological papers focusing on PLF and AI-based welfare assessment in sheep and goats raised under extreme climatic conditions, with particular emphasis on animal-based and species-specific approaches. Topics of interest include automated behavior and posture analysis, physiological welfare indicators (e.g., body temperature, respiration rate, and ocular or nasal discharge scoring), thermal imaging for animal-level welfare assessment, machine-learning models for welfare state prediction, and AI-driven decision-support tools for on-farm management. Studies addressing the development, validation, and reliability of species-specific digital welfare indicators for small ruminants are especially encouraged, as are contributions that demonstrate the translation of animal-based data outputs into practical welfare interventions and that examine the practical implementation and economic feasibility of these technologies at the farm level. Contributions may include experimental, field-based, or applied research from arid, semi-arid, and other extreme climate regions. Topic editors: Claire Morgan-Davies, Ebru Emsen Source: https://www.frontiersin.org/research-topics/79488/ai-driven-welfare-assessment-and-decision-support-systems-for-sustainable-small-ruminant-production-in-challenging-climates