Fostering artificial intelligence in the livestock sector: Adoption factors and policy insights from the case of Spain

CONTEXT AND PURPOSE The integration of Artificial Intelligence (AI) and Precision Livestock Farming (PLF) offers significant opportunities to improve the productivity, animal welfare and sustainability of the livestock sector. However, the adoption of these technologies remains highly uneven. Moving beyond descriptive statistics, this study investigates the complex, interacting factors associated with AI adoption in the Spanish livestock sector. METHODOLOGY Utilising a survey-based sample of 666 Spanish livestock holdings, drawn from a national survey whose sampling was designed to be proportional to the 2020 Agricultural Census by subsector and region, a Partial Least Squares Structural Equation Modelling (PLS-SEM) approach was employed to evaluate a comprehensive adoption framework across different farming systems and operational scales. AI adoption was modelled as a formative composite of five self-reported AI system categories, and the framework was tested through mediation, moderation, subgroup and out-of-sample predictive analyses with a 10,000-resample bootstrap. MAIN FINDINGS The empirical results indicate that AI adoption is most strongly associated with a holding's baseline technological infrastructure (β = 0.6464, p < 0.001); advanced predictive tools appear to presuppose a pre-existing ecosystem of digital farm books, automated feeding systems and interoperable sensors. A ‘perception-capability gap’ is formally supported: perceived benefits are associated with adoption only indirectly, through the infrastructure baseline (indirect-only mediation), and their association strengthens as infrastructure increases (positive interaction). Recognition of AI's theoretical benefits or awareness of public subsidies is thus not independently associated with adoption in the absence of foundational digital capability. Furthermore, the study identifies a stark structural divide: adoption reaches 56.3% in intensive and semi-intensive holdings but only 24.4% in extensive ones (χ2 = 57.61, p < 0.001), as traditional extensive systems face severe physical and connectivity barriers that leave them systematically disadvantaged. Results are robust across reflective, count, reduced-indicator and logistic specifications, and the model shows substantial out-of-sample predictive power (Q 2 predict ≈ 0.53). CONCLUSIONS To facilitate a more inclusive digital transformation, the findings suggest that policymakers should adopt a ‘readiness-conditional’ model, ensuring farms meet baseline digital prerequisites and have access to robust extension services before subsidising advanced AI tools.