Search

Machine learning is increasingly applied across agri-food systems to support prediction, classification, optimisation, monitoring, and decision-making. These applications now extend from farm-level production to processing, logistics, consumption, and food-waste management. As data-intensive agriculture expands, machine learning is often presented as an enabling technology for sustainable agri-food transitions. Despite this promise, the sustainability evidence base remains fragmented. Many studies report improvements in model accuracy, prediction performance, or operational decision support, but they do not always specify how these technical gains translate into environmental, economic, or social outcomes. This creates uncertainty about whether machine learning contributes to sustainability transitions directly, indirectly, or only under particular implementation conditions. This systematic review examines how machine learning contributes to sustainable agri-food transitions through environmental, economic, and social impact pathways. It focuses on the relationship between machine learning methods, agri-food applications, and sustainability-relevant outcomes rather than treating model performance as an end in itself. The review asks where evidence is strongest, where it remains indirect, and how different pathways vary across production, processing, distribution, consumption, waste reduction, and governance. The review finds that environmental and economic pathways are more developed than social and equity pathways. Evidence is strongest where machine learning supports precision input management, yield forecasting, irrigation decision support, operational efficiency, supply-chain analytics, and food-waste reduction. However, stronger longitudinal evaluation, causal assessment, life-cycle integration, participatory design, and equity-sensitive governance are needed before machine learning can be judged as a reliable driver of sustainable agri-food transitions.

Foundation models are increasingly investigated as reusable architecture-level systems for agricultural sensing, remote-sensing interpretation, multimodal learning, knowledge access, phenotyping, monitoring, and decision-support assistance. However, the evidence remains dispersed across model families, data modalities, agricultural applications, and validation settings. This systematic review synthesises the technical architectures, data requirements, opportunities, risks, deployment challenges, evidence gaps, and research priorities associated with foundation models in smart farming and precision agriculture. Peer-reviewed journal literature was identified through structured database and publisher-platform searches, supplementary reference checking, predefined eligibility criteria, sequential screening, claim-specific evidence extraction, and thematic synthesis. Evidence was organised across language, vision, vision-language, multimodal, geospatial, remote-sensing, time-series, self-supervised, transfer-learning, and domain-adaptation approaches. The reviewed literature indicates that foundation-model approaches may support transferable representation learning, reduced annotation dependence, multimodal data integration, crop and livestock monitoring, remote-sensing analysis, plant phenotyping, agricultural knowledge services, and bounded decision-support workflows. Nevertheless, reported results are commonly task-, dataset-, region-, sensor-, or application-specific. Important limitations include agricultural data scarcity and heterogeneity, geographic and temporal domain shift, uncertain generalisation, bias, weak explainability, inadequate uncertainty communication, privacy and cybersecurity risks, unclear accountability, computing demands, and limited farmer-centred or operational evaluation. Priorities include agricultural benchmark suites, domain-specific pretraining resources, multimodal and spatiotemporal adaptation, low-resource representation, robustness testing, calibrated uncertainty, human-in-the-loop evaluation, privacy-preserving development, sustainable-computing assessment, and lifecycle governance. Foundation models represent a promising research direction, but benchmark performance or pretraining scale alone does not establish agronomic validity, operational safety, farmer trust, or deployment readiness.