Artificial intelligence applied to precision livestock farming: A tertiary study

Abstract

Recent advances in Artificial Intelligence (AI) are transforming the livestock sector by enabling continuous real-time data monitoring and automated decision support systems. While several secondary studies have explored the application of AI in Precision Livestock Farming (PLF), they often focus on specific AI techniques or particular PLF activities, limiting a broader understanding of the field. This study aims to provide a comprehensive overview of the state-of-the-art of AI applications in PLF, highlighting both achievements and areas that require further investigation. To this end, a tertiary systematic mapping study was conducted following recognized guidelines to ensure reliability and replicability. The research process involved formulating 10 research questions, designing a comprehensive search strategy, and performing a rigorous quality assessment of the identified studies. From an initial pool of 738 retrieved manuscripts, 14 high-quality secondary studies were selected and analyzed. The findings reveal a wide range of AI techniques applied in PLF, particularly in the learning and perception AI domains. These techniques have proven effective in tasks such as animal recognition, abnormality detection, and health and welfare monitoring. However, comparatively less attention has been given to environmental monitoring and sustainability, highlighting an area that warrants further exploration. By offering valuable insights for future research and practical applications, this study suggests directions for both researchers and livestock farmers to unlock AI's full potential in PLF.