Bibliometric Analysis Of The Integrated Use Of Artificial Intelligence In Precision Livestock Farming

Abstract

Objetive. Conduct a bibliometric study on the main artificial intelligence (AI) tools applied to livestock production systems, especially ruminants and non-ruminants, in the period 2019-2024.

Methodology. A retrospective descriptive cross-sectional study was developed based on the analysis of scientific sources, analytical tools, and content analysis techniques. The corpus was constructed using the Scopus database, selected for its multidisciplinary coverage in areas such as veterinary medicine, animal husbandry and related fields. The search strategy included original articles, systematic reviews, data analyses and brief reports, delimiting the subject matter to title, abstract and keywords. The bibliometric analysis was performed with the statistical software R using the Biblioshiny interface.

Results. A total of 726 documents from 208 sources were evaluated. The research showed a growing trend with a confidence level of 97.73% and an annual growth rate of 34.46%. The year 2024 reached a peak with 211 publications. There was a high level of international collaboration, with Italy (499), China (427) and Brazil in Latin America (230) standing out. The most frequent keywords were ‘precision livestock farming’ (387), “livestock” (195) and ‘animals’ (180), highlighting topics in machine learning (ML) technologies applied to animal welfare and grazing management.

 Conclusion. The analysis confirms the strong emphasis on AI and machine learning in precision livestock farming, consolidating it as a key approach to improving efficiency and sustainability. However, adoption faces resistance due to high costs and operational complexity. Some authors recommend inclusion in academia with more accessible commercial approaches for the livestock sector.