Search

A shortage of calcium and the resulting physiological problems, like tip burn, create serious difficulties for indoor hydroponic lettuce growing, reducing both harvest and grade. This paper puts forward a unique strategy that merges cutting-edge image segmentation and classification methods to spot calcium insufficiency in lettuce during its growth phases under colored LED light. Recognizing nutrient shortfalls at an early stage is key for prompt correction and efficient nutrient control. The trial cultivated butterhead lettuce in a Deep-Water Culture (DWC) arrangement with managed calcium doses. Image preparation steps, involving Contrast Limited Adaptive Histogram Equalization (CLAHE) and Red Color Correction (RCC), were used to boost picture quality and uniformity, and augmentation was performed to increase model resilience. Our method adopted a two-step workflow that enabled us to exploit the advantages of dedicated models. First, lettuce foliage was separated from the backdrop through state-of-the-art architectures, including U-Net, U-Net++, Recurrent U-Net, and Inception U-Net. U-Net++ showed the top segmentation performance (98.56%) with strong generalization compared to its counterparts. Segmentation extracts the target zone and discards background clutter, permitting the classifier to focus more productively on disease-indicating traits. Deep learning classification networks, namely ResNet and EfficientNet, were used in the second step to identify calcium insufficiency from the segmented pictures. EfficientNetB2 stood out as the most dependable classifier, securing an accuracy of 91.51% on the RCC dataset, while Resnet50 attained a closely matching accuracy of 91.18% on that same dataset. This work emphasizes the promise of weaving deep learning models into automated hydroponic setups for live nutrient tracking, supplying a workable answer to improve output and sustainability in indoor hydroponic operations.

Health surveillance depends fundamentally on the reliable tracking of individual calves. Yet, prevailing multi-object tracking frameworks are prone to recurrent identification anomalies, particularly ID switches arising under occluded conditions. To overcome this limitation, we introduce YSD-BPTrack in this work, a novel multi-object tracking framework tailored for calves within occlusion-prone farm environments. The architecture is divided into two principal stages: detection and tracking. For the detection stage, DCNv4 is embedded into the YOLOv8s model to learn spatial deformations caused by occlusion, thereby strengthening detection robustness under such conditions. Meanwhile, the Star operation borrowed from StarNet is adopted to deliver high detection capability while keeping computational demands low. In the tracking stage, we first devise an original rematching mechanism (Rematching module) alongside a redesigned trajectory removal policy (Trajectory removal module). The Rematching module exploits expanded trajectory prediction boxes to re-establish correspondences with detection boxes during occlusion events, thereby cutting down on ID switch errors. The Trajectory Removal module, in turn, flexibly governs the timeout period for lost trajectories, minimizing the risk of premature trajectory deletion. Concretely, the framework we propose sets a new HOTA (Higher Order Tracking Accuracy) score of 91.6%, leading competing approaches in both tracking quality and runtime performance. Experimental evidence further demonstrates the advantage of YSD-BPTrack, with HOTA climbing by 17.6%, MOTA (Multiple Object Tracking Accuracy) by 13.9%, MOTP (Multiple Object Tracking Precision) by 1.8%, IDF1 (Identification F1 Score) by 15.4%, accompanied by reductions of 49.1% in parameters, 88.9% in IDSw (Identification Switches), and 39.2% in computational overhead relative to the other frameworks. Collectively, the presented multi-object tracking framework carries strong potential to redefine calf tracking practice.

As urban landscaping advances, the struggle with garden pests and diseases grows more critical. Substantial interest has been drawn to large language models for their skill in interpreting what users mean and producing suitable responses. The addition of knowledge graphs has offered these models a well-organized, high-quality foundation of facts. This investigation merges knowledge graphs (KGs), large language models (LLMs), and similar tools to engineer a smart question-answering (Q&A) framework for garden pest and disease contexts. Forge a knowledge graph dedicated to garden pests and diseases by amassing dependable data through web scraping and scholarly review. Pinpoint central entities and their links to shape a conceptual schema. Employ the ERNIE-BiLSTM-CRF architecture to pull facts from unstructured text. Testing reveals the fact-extraction system advanced in this work scores above 92% on precision, recall, and F1 metrics, beating competing designs. Put forward a Q&A strategy that fuses the garden pest and disease KG with the ERNIE-Bot-turbo engine. Knowledge is turned into vectors, and the closest matches are located via similarity search; these top hits are then bundled with the query into cues fed to the language engine for natural language output. Trials stacking our technique against ERNIE-Bot-turbo and ChatGLM-6B showed strong results across easy, mid-level, and tough problems, sidestepping off-base replies to out-of-scope questions. It exceeded both baselines in correctness, hitting a 90% exact-answer mark for straightforward queries.

Precise categorization of avocado ripeness plays a vital role in strengthening post-harvest operations and curbing waste throughout agricultural supply networks. The present study centers on constructing a resilient ensemble classification framework employing spectral readings from 120 kilograms of Buccaneer avocados procured from the Royal Project in Chiang Mai, Thailand. The specimens were assessed via near-infrared (NIR) spectroscopy at 18 wavelengths. Five distinct machine learning models—Random Forest, Decision Tree, XGBoost, Gradient Boosting, and Gaussian Mixture Model—were separately trained and subsequently fused into a unified ensemble. Four distinct algorithms were deployed to fine-tune the weighting of each model: Bayesian optimisation, differential evolution, particle swarm optimisation, and grid search. Evaluation metrics covering accuracy, precision, recall, F1-score, confusion matrices, and ROC curves were applied. Grid Search yielded the strongest classification outcomes, securing an accuracy of 82.5% alongside an F1-score of 85.3%, emphasizing the value of weight-refined ensemble learning relative to standalone classifiers. This investigation delivers a scalable and transparent pipeline for non-destructive ripeness identification. The outcomes, notwithstanding constraints related to overfitting and dependency on spectral data integrity, pave the way for eventual real-time field deployment in agriculture.

Edge devices are increasingly regarded as a portable, budget-friendly alternative to conventional personal computer terminals, offering a promising route toward downsizing equipment and highly flexible robotic fruit harvesting at the field scale. The present study proposes a compact, optimized You Only Look Once version 8n (YOLOv8n) architecture tailored for Orah fruit detection and subsequent deployment on an edge computing platform. Initially, ADown modules were brought into the design to shrink the overall model footprint while safeguarding detection performance. Next, a Concentrated-Comprehensive Dual Convolution (C3_DualConv) component, built around paired convolutional bottlenecks, was devised to reinforce the network’s ability to perceive Orah fruits partly hidden behind branches and foliage; this intervention also contributed to additional model compression. Furthermore, a Bidirectional Feature Pyramid Network (BiFPN) equipped with a high-resolution layer at pyramid level 2 was adopted to facilitate more powerful multi-scale feature aggregation. In parallel, three Coordinate Attention (CA) mechanism modules were embedded to sharpen the system’s sensitivity to Orah fruit features. Finally, a more targeted minimum points distance intersection-over-union loss formulation was applied to improve detection throughput for Orah fruits experiencing dense mutual occlusion. Experimental trials confirmed that the enhanced YOLOv8n architecture reliably pinpointed Orah fruits operating inside challenging orchard scenes, delivering precision of 97.7%, Average Precision at IoU threshold 0.5 ([email protected]) of 98.8%, and an F1 score of 96.69%, all while occupying a lean 4.1 MB of storage on a Windows-based system terminal. The resulting model was then optimally transferred to an Nvidia Jetson Orin Nano via the TensorRT Python Application Programming Interface (API), achieving a mean interface throughput of over 30 fps and thereby verifying real-time detection performance. The outcomes of this work stand to offer technical foundations for Orah fruit robotic harvesting powered by edge-based computing.

Within the densely structured environment of an orchard, pinpointing the exact harvesting location is fundamental to the autonomous operation of fruit-picking robotic systems. Despite this, current techniques are prone to miscalculations in positioning under intricate conditions such as abbreviated stalks, partial concealment, or instances where the target is entirely misread, any of which can compromise the robot's operational efficiency in the field. To address complex vineyard harvesting scenarios, this paper presents an advanced method for picking-point determination that relies on semantic-level inference. The approach introduces three novel components: the semantic reasoning module (SRM), the ROI threshold adjustment strategy (RTAS), and the picking point location optimization module (PPOM). The SRM is deployed to resolve cases where obstructions mask grape stalks, suffer from partial recognition errors, or undergo total recognition failure. The RTAS is designed to overcome difficulties associated with stalks that are positioned low and are notably short during the picking sequence. In the final stage, the PPOM adjusts the calculated picking point coordinates to their optimum, granting the manipulator greater maneuverability as it executes the harvest action. Empirical validation demonstrates that SegFormer produces an mIoU (mean Intersection over Union) of 84.54%, accompanied by B_IoU and P_IoU scores of 73.90% and 75.63%, respectively. In addition, the refined fruit-picking point localization method achieved a success rate of 94.96%, representing an improvement of 8.12% over the baseline technique. The average computation time stands at 0.5428 ± 0.0063 s per instance, which is adequate for real-time harvesting demands.

The choice of methodologies is a pivotal factor in disease identification, particularly when computer vision intersects with agricultural innovation. Safeguarding global food supplies depends on the timely and accurate identification of crop diseases. Deep learning offers a feasible pathway to satisfy this demand. To move this research forward, we engineered and tested a disease identification framework grounded in a novel ensemble strategy. Our contribution includes the presentation of DenseNetMini, a more compact iteration of the DenseNet architecture. We advocate merging DenseNetMini with a learning resizer via an ensemble approach to improve training fidelity and accelerate knowledge acquisition. A further innovative element involves deploying Gradient Product (GP) as the optimization mechanism, efficiently reducing the training time while simultaneously improving model performance. Investigating imagery at varying magnifications reveals remarkable improvements in diagnostic consensus and precision. Accuracy figures on test data reach 99.65%, 98.96%, and 98.11% for the Plantvillage, Tomato leaf, and Appleleaf9 collections, respectively. A core triumph of this investigation is the substantial reduction in computational time, suggesting that GP adoption could make agricultural disease screening more accessible and operationally efficient. Beyond numerical gains, the work foregrounds Explainable Artificial Intelligence (XAI) approaches as indispensable for enhancing the interpretability and clarity of the disease detection framework. By visually pinpointing diagnostically relevant zones on foliage, XAI enhances the model’s comprehensibility, thereby nurturing user confidence and insight into how it arrives at its conclusions.

Assessing the extent of plant injury is a vital element of crop safeguarding. Currently, domain experts evaluate the plots by hand. This labor-intensive activity can be mechanized utilizing cutting-edge computer vision (CV) technology. Image-reliant systems, and lately those grounded in deep learning, have demonstrated strong performance across multiple agricultural use cases. These image-based applications surpass specialist appraisals in regulated conditions and are now progressively being incorporated into uncontrolled, in-field deployments. A new solution, rooted in deep learning techniques and image processing, is proposed to estimate crop damage under field conditions. The recommended solution operates through a two-stage pipeline. The first stage identifies individual plants within the plots using a YOLO-based object detection model. After that, a regression model is applied to gauge the damage per isolated plant. The system was designed and corroborated on oilseed rape plants to measure the damage inflicted by the flea beetle. The plant detection model achieves an overall mean average precision of 91%, with [email protected] of 0.99 and [email protected] of 0.91 for the oilseed rape category. The regression model, built to predict damage severity up to 60% in single plants, yields an MAE of 7.11 and an R² of 0.46 when evaluated against plant-by-plant assessments conducted by human experts. Both models are packaged in a Docker container and can be directly queried via a REST API using images captured in the field from a mobile device.

Artificial intelligence is increasingly promoted as a tool for improving agricultural productivity, food-system coordination, sustainability monitoring, risk prediction, quality control, and decision support. Across agri-food systems, AI is expected to support more timely decisions, more efficient resource use, and more adaptive responses to climatic, market, and production uncertainty. These expectations have encouraged investment in digital tools, analytics platforms, automated monitoring systems, and predictive applications. Yet the availability of AI tools does not mean that agri-food systems are prepared to use them effectively or responsibly. Readiness depends on the quality of data infrastructure, the strength of institutions, the capabilities of farmers and other users, and the maturity of governance arrangements. When these conditions are weak, AI implementation can deepen inequality, create dependence on opaque platforms, reduce trust, or generate risks that are difficult to identify and manage. This article develops an agri-food AI readiness framework that explains the conditions required for responsible and effective AI implementation. The framework conceptualises readiness as a socio-technical condition produced through the interaction of data infrastructure and digital capacity, institutional capacity and policy support, farmer capability and adoption readiness, and governance maturity and risk management. It emphasises that AI readiness is not a single technical threshold but a combined maturity condition across interconnected system dimensions. The framework contributes a structured way to assess whether agri-food systems are prepared to adopt, adapt, govern, and benefit from AI. It identifies how weaknesses in one dimension can reduce the effectiveness of the others, even where advanced technologies are available. By linking implementation capacity with governance responsibility, the framework supports more inclusive, trustworthy, and context-sensitive pathways for agri-food AI.

Artificial intelligence is increasingly embedded in agricultural decision support, farm platforms, automation, sensing, advisory systems, and data-driven management. These systems influence how farms interpret risk, allocate inputs, monitor environments, plan production, and respond to market and ecological uncertainty. As agricultural AI becomes more consequential, its governance must address not only technical performance but also the social conditions under which digital decisions are made, trusted, challenged, and revised. Agricultural AI governance is often framed around technical accuracy, transparency, regulatory compliance, or institutional oversight. While these are necessary, they are insufficient when farmers have limited influence over system design, data practices, model assumptions, recommendation logic, or dispute pathways. Governance weaknesses can produce exclusion, loss of autonomy, data misuse, algorithmic opacity, dependency on platforms, and digital decisions that affected users cannot meaningfully challenge. This article develops a participatory AI governance framework for agriculture centred on farmer voice, local knowledge integration, contestable digital decisions, and accountability safeguards. The framework treats governance as a socio-technical practice that connects design, deployment, monitoring, revision, and redress. It argues that responsible agricultural AI requires institutional mechanisms through which farmers and other affected actors can shape, interpret, evaluate, contest, and improve digital systems. The framework contributes to agricultural AI governance by showing how participation can strengthen legitimacy, trust, accountability, and contextual fit. It positions farmer voice as a condition of decision legitimacy, local knowledge as a condition of contextual accuracy, contestability as a condition of procedural fairness, and accountability safeguards as a condition of responsible institutional performance. Participatory governance is therefore presented as a practical foundation for agricultural AI that is more locally grounded, explainable, responsive, and accountable.

Agri-food systems increasingly rely on analytics, artificial intelligence, machine learning, environmental monitoring, and decision-support tools to evaluate sustainability performance. These systems can estimate resource use, model environmental impacts, detect risks, and inform actions across farms, supply chains, markets, and governance settings. As analytics become embedded in sustainability decisions, their outputs increasingly shape how environmental problems are recognised and acted upon. Yet sustainability analytics does not become useful or responsible simply because it produces indicators, predictions, rankings, or dashboards. Environmental metrics may be technically sophisticated while remaining difficult for farmers, firms, auditors, regulators, and communities to interpret or challenge. This creates an explainability problem in which users need to understand not only what an analytic system reports, but also how the result was produced, what assumptions it contains, and what consequences may follow from acting on it. This article develops a conceptual framework for explainable sustainability analytics in agri-food systems. The framework treats explainability as a system-level requirement for linking environmental impact interpretation, risk explanation, responsibility attribution, human review, and accountability safeguards. It argues that sustainability analytics should be evaluated not only by predictive performance or measurement coverage, but also by whether it supports transparent, contestable, and context-sensitive decision-making. The article contributes a structured framework for interpreting environmental impact, explaining risk, attributing responsibility, and supporting accountable review in agri-food decision contexts. It positions explainable sustainability analytics as an approach that connects data, models, indicators, explanation mechanisms, human judgement, and governance safeguards. In doing so, it provides a foundation for sustainability analytics that is more interpretable, trustworthy, and actionable.

Agri-food systems increasingly rely on artificial intelligence for farm decision support, automation, quality control, sustainability monitoring, logistics, supply-chain coordination, risk prediction, and resource management. These applications promise productivity gains and improved responsiveness to environmental and market pressures. Yet their growing influence also creates new governance demands because AI systems can shape decisions that affect farms, firms, workers, consumers, ecosystems, and public institutions. Trustworthy AI in agri-food systems cannot be established through technical performance claims alone. A model may be accurate in a narrow test environment while remaining opaque, unsafe under changing field conditions, unfair across producer groups, or unable to substantiate sustainability claims. Certification therefore needs to move beyond reputational signalling and provide credible assurance that AI systems can be examined, challenged, monitored, and held accountable. This article develops a trustworthy AI certification framework for agri-food systems centred on auditability, safety, fairness, and sustainability-claim verification. The framework treats certification as a governance mechanism rather than a simple label or checklist. It identifies the evidence, assurance procedures, monitoring expectations, and institutional safeguards needed to make certification credible in technically complex and socially consequential agri-food settings. The article contributes a structured approach for regulators, certification bodies, technology providers, agri-food firms, farmer organisations, sustainability auditors, and public institutions. It argues that trustworthy AI certification should depend on verifiable evidence, independent auditability, lifecycle risk assurance, distributional accountability, environmental claim verification, and clear responsibilities across the AI value chain. Certification becomes meaningful only when it supports systems that are auditable, safe, fair, environmentally credible, and publicly accountable.

Intelligent agriculture increasingly uses artificial intelligence, sensors, remote sensing, automation, modelling, and decision-support systems to monitor and manage agricultural production. These tools can strengthen observation, prediction, and coordination across farms and landscapes. Yet their contribution to agricultural transformation depends on the ecological aims toward which they are designed and governed. Regenerative agriculture requires more than improved efficiency or narrower optimisation of inputs. It calls for soil restoration, biodiversity protection, ecological feedback, and long-term system health. Intelligent systems therefore need to be evaluated not only by productivity gains, but also by their capacity to support ecological recovery. This article develops a conceptual framework for regenerative intelligence in agriculture. Regenerative intelligence is defined as the AI-supported capacity of agricultural systems to monitor, interpret, and support soil restoration, biodiversity protection, and long-term system health through adaptive and ecologically accountable decision pathways. The framework explains how sensing, ecological analytics, modelling, decision support, monitoring, feedback, and governance can contribute to regenerative agricultural transformation. It also clarifies that AI-supported agriculture is not automatically regenerative. Its regenerative value depends on ecological indicators, farmer participation, responsible governance, biodiversity sensitivity, soil-health interpretation, and sustained learning from ecological outcomes.

Edge Artificial Intelligence and Tiny Machine Learning are increasingly discussed as approaches for moving selected analytical functions from remote cloud infrastructure to low-power devices located closer to agricultural data sources. Their potential relevance to precision agriculture lies in supporting local sensing, classification, monitoring, and decision-assistance functions where continuous connectivity, high-performance computing, or extensive data transmission may be impractical. This framework-oriented review examines Edge AI and TinyML through four connected dimensions: low-power intelligence, embedded farm systems, agricultural deployment constraints, and farm-scale applications and implementation barriers. The review distinguishes on-device inference and near-sensor intelligence from conventional agricultural Internet of Things sensing, generic wireless sensor networks, cloud-based artificial intelligence, and non-embedded machine-learning applications. It organizes the reviewed evidence around embedded hardware, model compression, memory, latency, energy use, sensor quality, connectivity, environmental exposure, calibration, maintenance, usability, affordability, local validation, cybersecurity, privacy, and human oversight. The synthesis indicates that compact inference can reduce reliance on continuous cloud access in appropriately designed systems, but miniaturized models alone do not establish accuracy, robustness, affordability, usability, sustainability, or deployment readiness. Farm-scale usefulness remains conditional on the quality of sensing systems, hardware-aware model design, environmental testing, lifecycle maintenance, locally relevant validation, and clear responsibility for system oversight. The main contribution is a framework that connects technical design choices with deployment conditions, implementation boundaries, and a research and practice agenda for evaluating low-power agricultural intelligence without converting prototype feasibility into unsupported operational claims.

Foundation models are becoming relevant to precision agriculture because they can connect sensing, remote sensing interpretation, multimodal data integration, knowledge retrieval, advisory communication, and farm decision-support workflows. Their broad capability, however, does not establish agronomic validity, trustworthy performance, operational safety, or deployment readiness. This article develops an original governance and technical safeguard framework for responsible agricultural foundation models. The framework treats these models as potential components of decision infrastructure and integrates trustworthy artificial intelligence requirements with data governance, validation, human oversight, farmer participation, monitoring, and explicit claim boundaries. It identifies requirements concerning data quality, provenance, documentation, transparency, explainability, interpretability, uncertainty communication, robustness, generalization, bias, fairness, privacy, cybersecurity, accountability, auditability, and traceability. It also maps risks arising from opaque pretraining data, uncertain data control, hallucination, factual error, agronomic invalidity, platform dependency, model drift, data drift, and unclear responsibility. Technical safeguards include data screening, domain-adaptation assessment, external and local validation, robustness testing, bias and fairness review, factual and agronomic checking, human-in-the-loop review, and continuing monitoring. Responsible deployment principles add purpose limitation, context sensitivity, incident response, withdrawal planning, and non-autonomy boundaries. The contribution is a structured conceptual framework that connects governance questions with technical evidence and accountable actors without claiming legal compliance, guaranteed trustworthiness, farmer approval, or deployment readiness.

Generative artificial intelligence is expanding the conversational and interpretive functions available within precision-farming decision support, yet fluent responses may contain factual inaccuracies, unsupported claims, fabricated evidence, agronomically invalid interpretations, local-context mismatches, or understated uncertainty. This article develops a conceptual artificial-intelligence safety framework for managing these risks in generative agricultural decision-support systems. The framework treats hallucination risk as a socio-technical safety problem rather than solely as a language-model defect. It links agricultural use-case definition, advisory-output classification, farm-level consequence assessment, data and knowledge provenance, retrieval and response grounding, hallucination screening, factual verification, agronomic-validity review, uncertainty communication, human oversight, expert escalation, farmer feedback, traceability, accountability, monitoring, and controlled updating. Generative outputs are differentiated according to whether they provide information, interpretation, scenario explanation, or recommendation-like content, because the evidentiary and review requirements increase with potential consequence. Validation is similarly separated into factual checking, external evaluation, local-context assessment, agronomic review, and future field-validation planning. The framework establishes decision boundaries against unsupported agronomic advice, autonomous farm action, hallucination-elimination claims, safety guarantees, and deployment-readiness claims. It also allocates responsibilities among developers, platform providers, data stewards, knowledge-base curators, agricultural reviewers, and farmers while preserving farmer autonomy. The main contribution is an integrated safety model for structuring how hallucination-prone generative outputs may be interpreted, reviewed, restricted, escalated, recorded, and updated within precision-farming decision support. The framework is conceptual and does not independently establish advisory correctness, operational safety, legal compliance, or deployment readiness.

Climate-smart precision agriculture is increasingly discussed as a means of connecting farm data, environmental observation, and analytical modeling with climate adaptation, mitigation-relevant assessment, and resilience planning. However, data availability and predictive capability alone do not establish climate benefit, decision reliability, or farm readiness. This article proposes a conceptual data-science framework that organizes climate-smart use-case definition, farm-context mapping, multi-source data integration, adaptation analytics, mitigation-relevant analysis, climate-risk modeling, uncertainty assessment, resilience-oriented decision support, sustainability feedback, monitoring, and governance safeguards. The framework distinguishes climate hazards, exposure, vulnerability, adaptive capacity, forecasting, scenario analysis, and operational decision support while preserving boundaries between analytical indicators and verified outcomes. Remote sensing, sensors, weather and climate records, soil and crop observations, water and resource-use data, machine learning, geospatial analysis, time-series modeling, and data fusion are positioned as conditional inputs and methods rather than automatic sources of climate benefit. The framework also requires local validation, uncertainty communication, farmer participation, human oversight, data-quality assessment, provenance, interoperability, and feedback updating. Its main contribution is an integrated architecture for interpreting how data-science functions may support climate-smart precision agriculture without presenting modeled outputs as guaranteed adaptation, verified mitigation, proven resilience, carbon accounting, or deployment readiness. The article therefore frames climate-smart precision agriculture as a governed learning system whose value depends on evidence quality, contextual interpretation, transparent limitations, and iterative assessment.

Artificial intelligence is becoming embedded in precision agriculture through data-intensive monitoring, predictive models, digital platforms, advisory systems, robotics, and automated machinery. These arrangements complicate accountability because consequential outputs may result from interactions among data providers, model developers, platform operators, advisors, machinery manufacturers, system integrators, service providers, and farm operators rather than from a single actor or technical component. This article proposes a conceptual accountability framework for examining AI liability issues across agricultural AI systems without treating accountability mapping as a substitute for legal interpretation. The framework begins with agricultural use-case definition and stakeholder-role mapping, then examines data-level duties concerning quality, provenance, access, control, privacy, cybersecurity, and governance. It further maps model-level responsibilities for documentation, validation, robustness, bias assessment, explainability, uncertainty communication, and drift monitoring. Platform and advisory layers are addressed through governance, interface design, monitoring, escalation, human review, professional interpretation, and farmer-autonomy requirements. Machinery, automation, and operational risks are incorporated through control-system responsibilities, sensor-to-actuator traceability, supervisory control, fail-safe design, maintenance, incident reporting, and operational boundaries. The framework also identifies liability gaps created by fragmented evidence, unclear validation ownership, platform ambiguity, ineffective human oversight, and incomplete traceability. Its contribution is a structured method for clarifying responsibility pathways, evidence needs, decision boundaries, and governance gaps across interconnected agricultural AI layers. The framework is conceptual and does not determine legal liability, establish compliance, certify safety, allocate blame, or demonstrate deployment readiness.

Smart farming platforms are frequently conceived around persistent connectivity, modern devices, scalable cloud services, specialized technical support, and the financial capacity to adopt integrated digital systems. These assumptions may not hold in smallholder and connectivity-constrained agricultural settings, where infrastructure gaps, uneven digital skills, limited advisory access, maintenance difficulties, data costs, language diversity, and uncertain platform governance shape whether digital services are usable or sustainable. This article develops a conceptual design science framework for low-resource smart farming platforms. The framework links problem relevance, contextual requirement definition, design principles, platform artifact logic, implementation conditions, evaluation needs, feedback, and framework updating. It focuses on affordability, transparent costs, incremental adoption, modular architecture, interoperability, offline-first operation, low-bandwidth communication, local usability, accessible interaction, advisory integration, maintenance capacity, farmer data control, and trust. The proposed approach treats smallholders as heterogeneous users operating within diverse production systems, infrastructures, institutions, and knowledge networks. Platform functions are therefore organized as configurable responses to identified conditions rather than as a universal technology package. The principal contribution is a structured design science logic for translating low-resource agricultural problems into bounded platform requirements and evaluable conceptual artifacts. The framework can guide platform design and research planning, but it does not independently demonstrate affordability, inclusion, adoption, scalability, sustainability, operational safety, or deployment readiness. These outcomes require local usability assessment, affordability analysis, governance review, maintenance evaluation, implementation research, and field validation involving intended users and supporting institutions.

Regenerative agriculture is increasingly associated with soil improvement, ecological restoration, climate adaptation, and more resilient farming systems, yet these outcomes cannot be inferred from a management label or from digital measurement alone. This article develops a conceptual framework for data-driven regenerative agriculture that links precision farming, soil health monitoring, biodiversity monitoring, ecological feedback, climate-risk interpretation, farmer participation, and responsible decision support. The framework approach treats regeneration as a context-dependent monitoring and interpretation problem involving heterogeneous data, multiple spatial and temporal scales, uncertain ecological relationships, and explicit claim boundaries. Precision farming contributes spatially and temporally resolved observations from sensors, remote sensing, soil sampling, crop monitoring, water data, and farm-management records, while soil-health interpretation requires function-linked indicators, longitudinal baselines, local validation, and separation of monitoring from verified restoration or carbon-accounting claims. Biodiversity monitoring is organized around agrobiodiversity, functional biodiversity, habitat conditions, landscape context, ecological indicators, and field-validated observation methods. Climate resilience is framed through hazards, exposure, vulnerability, adaptive capacity, farm-system adaptation, and uncertainty rather than as a guaranteed outcome. Regenerative decision support integrates these domains through data-quality review, provenance, interoperability, ecological interpretation, farmer knowledge, human oversight, sustainability feedback, and iterative framework updating. The principal contribution is a structured conceptual architecture for connecting digital agricultural capabilities with cautious ecological reasoning. The framework supports research design and monitoring-system development but does not independently verify regenerative outcomes, environmental performance, biodiversity recovery, soil restoration, carbon sequestration, climate resilience, operational safety, or deployment readiness.

Agricultural artificial intelligence is commonly compared through benchmark datasets and technical metrics before any field experimentation occurs. Such comparisons can help identify promising models, reveal methodological weaknesses, and organize evidence for further testing, but they cannot establish field readiness, agronomic validity, operational safety, or deployment suitability. This article proposes a conceptual framework for benchmarking agricultural AI without field experiments. The framework separates five linked assessment domains: model readiness, technical validation, data quality, contextual fit, and deployment risk and decision validity. It addresses benchmark-task clarity, metric justification, dataset representativeness, provenance, label and ground-truth uncertainty, structured validation, domain shift, robustness, calibration, uncertainty, error patterns, bias, explainability, human oversight, and monitoring requirements. Non-empirical evaluation is treated as a structured screening process based on documentation, reported evidence, cross-context reasoning, and explicit claim boundaries. The framework produces a conditional benchmark-readiness statement and a field-validation gap register rather than a deployment decision. Its principal contribution is to distinguish benchmark performance from decision validity and deployment readiness while giving researchers, developers, evaluators, and agricultural stakeholders a transparent structure for comparing evidence before field testing. The framework is conceptual, does not replace field experiments, and should be updated as new data, validation evidence, user feedback, and operational observations become available.

Agricultural artificial intelligence increasingly combines sensor measurements, remote sensing, farm records, predictive modelling, and digital decision support. Yet agricultural context cannot be adequately represented through machine-readable data or model performance alone. Farming decisions are also shaped by tacit knowledge, farmer expertise, local ecological understanding, seasonal experience, farm history, cultural relationships, and institutional power. This article proposes a conceptual framework for integrating these dimensions into context-aware agricultural AI without treating local or Indigenous knowledge as extractable technical inputs. The framework begins with context-aware use-case definition and farm, agroecological, cultural, and historical context mapping. It then distinguishes tacit, experiential, situated, local, Indigenous, traditional ecological, scientific, and model-based knowledge while preserving differences in authority, representation, and validation. Participatory design, farmer-centered design, knowledge co-production, human oversight, local validation, knowledge sovereignty, Indigenous data sovereignty, access control, and ethical review are positioned as interconnected requirements rather than optional additions. The framework also addresses knowledge extraction, misappropriation, decontextualization, translation loss, contextual bias, algorithmic opacity, consent ambiguity, unequal benefit distribution, and trust overclaiming. Its principal contribution is a staged architecture that links knowledge plurality with contextual interpretation, governance safeguards, uncertainty communication, feedback, and explicit decision boundaries. The framework is intended to guide conceptual development and research design. It does not authorize knowledge use, establish community or Indigenous approval, validate Indigenous knowledge through AI, guarantee cultural appropriateness or trust, or demonstrate operational or deployment readiness.