Sustainable Computing for Digital Livestock: Reconciling Artificial Intelligence with Planetary Boundaries

Artificial intelligence is transforming digital livestock farming, yet the same systems that improve welfare, efficiency, and emissions monitoring can impose large carbon costs from training, continuous inference, and hardware manufacture. This PRISMA-guided systematic review examines how Green AI can realign performance with environmental responsibility. We searched IEEE Xplore, Scopus, Web of Science, and the ACM Digital Library (January 2019–October 2025), screening 1,847 records and including 89 studies (61 with quantitative data). We address three questions: (RQ1) How do energy-efficient model designs reduce computational footprints while preserving accuracy? (RQ2) Which low-carbon machine-learning frameworks minimize training and inference emissions? (RQ3) How do sustainable infrastructures enable climate-positive deployments? Meta-analysis shows strong decoupling of performance from impact. Compression (pruning, quantization, distillation) achieves 70–95% parameter reductions with <5% accuracy loss. Lightweight architectures (e.g., MobileNet, EfficientNet) deliver 10–50× energy savings versus conventional CNNs, while neuromorphic systems achieve 200–1000× power reductions. Carbon-aware scheduling cuts emissions by ~70% via temporal and spatial workload placement; federated learning reduces communication energy by ~85% while preserving privacy; edge–fog–cloud hierarchies lower inference energy by ~87% by localizing computation. Six representative deployments report mean energy savings of 90.3% (85.9–99.96%) and cumulative CO₂ reductions of 2,175 kg with >91% accuracy retained. Key gaps remain: no ISO-aligned carbon metrics for agricultural AI; embodied emissions are rarely counted (17% of studies); accessibility for smallholders is limited; rebound effects are unquantified. We propose a roadmap prioritizing ISO-compliant accounting, low-cost solar or neuromorphic edge devices, rebound analysis, field validation, and multi-stakeholder Pareto optimization.