Search

Artificial intelligence is increasingly presented as a transformative force in agriculture, promising more precise decisions, better resource use, improved productivity, and more resilient farming systems. Yet much of this promise has been shaped around large-scale, capital-intensive, data-rich farms in high-income settings. This creates a structural mismatch between dominant agricultural AI imaginaries and the everyday realities of smallholder farming. Smallholder farmers operate under conditions that are often treated as barriers to technological adoption rather than as core design conditions. Limited connectivity, intermittent electricity, restricted access to smartphones, low disposable income, linguistic diversity, and uneven access to advisory support all shape how digital tools are encountered and used. When these realities are ignored, agricultural AI risks widening rather than narrowing existing inequalities. This article develops a Smallholder-Centred AI Model for agriculture. The model reorients agricultural AI around four foundational principles: low-resource design, inclusion and affordability, context-awareness, and farmer participation. It argues that these principles must not be added after technical development but must structure the design, governance, and evaluation of AI from the beginning. The article concludes that AI can serve smallholder agriculture only when smallholders are positioned as active participants in the intelligence of the system. A smallholder-centred approach requires technologies that work with limited infrastructure, respond to local agroecological and social contexts, respect farmer knowledge, and remain affordable and accountable. The future of agricultural AI must therefore be judged not only by predictive accuracy but by its capacity to support inclusive, locally grounded, and farmer-led transformation.

Food supply chains face growing pressure to reduce waste, protect product quality, and improve sustainability performance. Yet many supply chain decisions remain reactive, even though food products are perishable, demand is volatile, and quality deterioration often begins before problems become visible. This article proposes that food systems require a more integrated predictive orientation rather than isolated technological improvements. The central problem is that demand forecasting, waste analytics, cold-chain monitoring, and sustainability assessment are often developed as separate capabilities. When these tools remain disconnected, prediction does not necessarily translate into coordinated action or measurable environmental improvement. The absence of an integrated model limits the ability of food supply chains to anticipate waste, preserve quality, and learn from sustainability outcomes. The objective of this article is to propose a conceptual model of Predictive Food Systems. The model connects demand forecasting, waste reduction and inventory intelligence, cold-chain intelligence, and sustainability performance within a closed-loop architecture. It argues that predictive value emerges when data from each component continuously inform decisions across the whole system. The article is based on a conceptual synthesis of 26 peer-reviewed journal articles published between 2017 and 2025. These studies cover food logistics, artificial intelligence, demand forecasting, dynamic inventory management, cold-chain monitoring, food waste accounting, and sustainability assessment. The article does not report new empirical data but uses existing evidence to construct an original systems-oriented framework. The proposed model specifies how demand prediction can reduce overproduction, how inventory intelligence can redirect or discount perishable stock, how cold-chain intelligence can preserve shelf-life, and how sustainability metrics can feed back into predictive systems. Three tables organise the model’s forecasting approaches, cold-chain technologies, and integrated components. The article concludes that predictive food systems can become a practical pathway for reducing waste, improving quality, and advancing sustainability performance.

Food recalls remain essential instruments for protecting public health when unsafe, contaminated, mislabelled, or otherwise non-compliant products enter food supply chains. Yet many recall systems still operate primarily as downstream corrective mechanisms after hazards have already moved through production, distribution, retail, food service, or household channels. This reactive orientation can delay containment, increase exposure, and weaken public confidence in food safety governance. Conventional recall management is increasingly challenged by globalised sourcing, rapid distribution, e-commerce, multi-ingredient products, outsourced processing, fragmented traceability records, and uneven information sharing among actors. Weak risk signals may appear in laboratory data, consumer complaints, inspection findings, supplier records, online reports, or public health surveillance before they are recognised as recall-relevant evidence. When these signals remain disconnected, recall decisions may occur only after risk propagation has already widened. This article proposes a conceptual model for intelligent food recall systems that integrates early detection, risk signal fusion, network propagation mapping, coordinated response, accountability, and communication feedback. The model reframes recall management as a system intelligence problem rather than a narrow compliance, logistics, or product-removal task. It explains how anticipatory analytics and network-aware decision support can strengthen recall scope definition, actor alignment, and public communication. The contribution of the article is a structured conceptual framework for designing recall systems that are more anticipatory, traceable, coordinated, accountable, and adaptive. The model does not report new empirical data; rather, it synthesises food safety, artificial intelligence, supply-chain traceability, risk communication, and crisis-response perspectives into an integrated recall intelligence architecture. It offers a foundation for future empirical testing, digital system design, regulatory innovation, and food-industry implementation.

Smart agriculture increasingly combines artificial intelligence, sensor networks, automation, remote sensing, robotics, and decision-support systems to guide agricultural production and resource management. These technologies promise more precise monitoring, faster diagnosis, improved input targeting, and better coordination of farm operations. Their sustainability value, however, depends on how optimisation goals are defined and how decisions interact with ecological, technical, and social systems. A central problem is that algorithmic systems are often evaluated through yield gains, input efficiency, prediction accuracy, or operational performance. These metrics are important, but they do not necessarily reveal whether an improvement in one sustainability domain shifts pressure onto another. A farm system may become more productive while increasing water demand, energy dependence, biodiversity risk, or unequal exposure to technological burdens. This article develops a conceptual model of algorithmic sustainability trade-offs in smart agriculture. The model explains how yield, water, energy, biodiversity, and equity operate as connected outcome domains rather than isolated evaluation categories. It treats trade-offs as system-level tensions that emerge through optimisation objectives, data availability, decision rules, platform design, governance arrangements, and implementation contexts. The article contributes a systems-oriented framework for analysing when smart agriculture supports sustainability and when it redistributes environmental or social costs. It argues that algorithmic optimisation should not be treated as automatically sustainable simply because it improves efficiency or prediction. Instead, smart agriculture should be assessed by how its decisions balance productivity, resource use, ecological resilience, and distributional fairness.

Agri-food systems increasingly operate under compound crises in which climate shocks, supply disruptions, market instability, ecological stress, and social vulnerability interact. These crises do not affect production, distribution, livelihoods, and food access in isolation. They move through connected risk pathways that can destabilise farms, supply chains, public institutions, and households at the same time. Artificial intelligence can support prediction, monitoring, early warning, and decision support in these contexts. However, technical forecasting alone does not constitute resilience when risks cascade across multiple domains. Agri-food resilience requires that predictive information be translated into adaptive decisions, coordinated response, and food security protection. This article develops a conceptual model of AI-supported agri-food resilience under compound crises. The model links climate shocks, supply disruptions, farmer adaptation, and food security governance as interacting domains. It treats AI as a decision-support function embedded within social, institutional, ecological, and market systems rather than as a stand-alone technological solution. The model identifies resilience mechanisms that connect risk detection, signal integration, uncertainty communication, adaptive decision support, institutional coordination, feedback learning, and accountability. It also clarifies boundary conditions that determine whether AI strengthens or weakens resilience. These include data quality, interpretability, local relevance, farmer participation, institutional response capacity, equity, and governance accountability. The article contributes a structured conceptual model for understanding how AI can support agri-food resilience when analytics are aligned with adaptation needs and food security objectives. It argues that resilient agri-food AI systems must connect prediction with human judgement, local knowledge, public action, and accountable coordination. The proposed model offers a basis for future empirical testing, policy design, and responsible innovation in crisis-sensitive food systems.

Smart farming increasingly operates through digital platforms that connect farm machinery, sensors, remote-sensing services, advisory systems, agricultural inputs, data analytics, and decision-support applications. Although these arrangements may improve coordination and service integration, their governance implications cannot be evaluated through technological functionality or productivity expectations alone. This article develops an original conceptual model for examining platform governance in smart farming as a socio-technical problem involving data power, platform dependency, value creation, value capture, farmer autonomy, and accountability. The model begins with platform ecosystem mapping, actor identification, and agricultural data-flow analysis. It then assesses how data access, control, portability, interoperability, asymmetry, algorithmic influence, switching costs, and service bundling may shape dependency relationships. A parallel value pathway distinguishes ecosystem value creation from value capture and distribution among farmers, platform operators, technology providers, advisers, suppliers, complementors, cooperatives, and public institutions. Farmer autonomy is examined through decision rights, informed participation, practical agency, human oversight, trust, digital inclusion, and access to contestation and remedy. The model further links identified risks to governance mechanisms such as data stewardship, transparency, auditability, interoperability requirements, participatory governance, farmer representation, accountability structures, and dispute resolution. Its main contribution is a structured framework for evaluating smart farming platforms through power, dependency, distribution, and agency rather than platform performance alone. The model supports conceptual analysis and research design but requires contextual implementation and empirical validation.

Smart farming increasingly operates through interconnected socio-technical ecosystems rather than through isolated technologies deployed at farm level. These ecosystems involve farmers, advisors, technology and platform providers, data intermediaries, equipment and input suppliers, cooperatives, public institutions, research and extension organizations, and agri-food supply-chain actors. This article develops a conceptual ecosystem model for examining how these stakeholders contribute to data-driven agricultural innovation and how value may be created, captured, and distributed through their interactions. The model-building approach integrates stakeholder roles, multidirectional data and knowledge flows, analytics and advisory services, platform coordination, institutional support, co-production, and co-innovation. It distinguishes farmer value, platform value, supply-chain value, public value, knowledge value, and sustainability value while treating value capture and distribution as separate analytical questions. Governance dimensions include data access, control, sharing, interoperability, portability, stewardship, transparency, accountability, trust, participation, digital inclusion, dependency, and power imbalance. The principal contribution is a structured framework that connects innovation processes with governance and distributional boundaries rather than assuming that technological deployment automatically produces shared value or farmer benefit. The model is intended to support conceptual analysis, stakeholder dialogue, and future empirical research. It does not establish the effectiveness, fairness, policy suitability, commercial viability, or implementation readiness of any particular smart farming ecosystem.

Autonomous farming is emerging as a precision agriculture frontier in which sensing, environmental awareness, reasoning, decision logic, robotic action, and adaptive feedback are linked within increasingly integrated technical systems. Yet autonomy in agriculture cannot be reduced to unattended machine operation because field environments are variable, data quality is uneven, physical actions are consequential, and farmers and operators retain essential contextual and supervisory roles. This article develops an original conceptual model for analysing autonomous farming systems as supervised socio-technical architectures rather than self-sufficient farm managers. The model is constructed through conceptual synthesis of agricultural robotics, computer vision, machine learning, navigation, control, human–robot interaction, and responsible innovation scholarship. It organizes autonomy into connected layers: use-case definition; sensing and environmental awareness; data quality and fusion; reasoning, planning, and uncertainty interpretation; acting, control, and robotic execution; learning, feedback, and drift monitoring; and human oversight, safety, accountability, and governance. The main contribution is a closed-loop account of how farm observations may become bounded robotic actions only when perception is validated, reasoning is contextually interpreted, plans remain within operating constraints, execution is monitored, and human intervention remains available. Learning is treated as governed model updating rather than automatic self-improvement. The model therefore clarifies both enabling relationships and non-guarantee boundaries: conceptual integration alone does not establish safe autonomous operation, productivity improvement, legal sufficiency, or deployment readiness. It offers a structured basis for future research, local validation planning, supervisory design, and responsible assessment of autonomous farming within precision agriculture.