Search

Crop production around the globe is increasingly at risk from invasive organisms, particularly the Fall Armyworm (FAW, Spodoptera frugiperda), which has caused severe deterioration of maize harvests across both Africa and Asia starting in 2016. To enable targeted pest control, an adaptive Echo State Network (ESN) was constructed that projects yearly maize output while factoring in FAW burden. A 15-year (2010–2024) monthly repository was built, integrating vegetation indicators from satellites, field-level meteorological measurements, soil nutrient readings, and FAW observation tallies. The intensity of FAW infestation is represented on a continuum from 0 to 100, derived by fusing monthly trap catch figures (40%) with larval concentration (60%). The ESN is initially calibrated on the entire body of environmental features to estimate crop performance. Next, isotonic regression is deployed to link infestation intensity with the ESN's positive residual errors, yielding a monotonic penalty mapping. This mapping captures the magnitude of output depression at varying infestation levels. When generating estimates, the inferred penalty is applied to the unadjusted ESN projection, modifying harvest forecasts to incorporate pest-driven losses without changing the foundational ESN configuration. In testing across held-out folds, the FAW-sensitive ESN yields an R² near 0.55 and cuts forecast discrepancies by as much as 67% compared to unadjusted reference models, faithfully reproducing documented harvest declines beyond 20% during major infestation episodes. The approach beats standard regression and deep neural architectures by comparable margins. It supports agriculturalists in directing countermeasures toward high-threat areas, lowering both chemical input volumes and operational expenditures. These outcomes emphasize its promise as a forward-looking alert mechanism for pinpointed actions that curtail agrochemical usage and improve input distribution. Ongoing field assessments will gauge its capacity to scale and its tangible efficacy within maize-growing zones affected by FAW.

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.

Precise forecasting of watermelon harvest volumes is vital within the agricultural supply chain, since it informs the deployment of farming inputs and streamlines stock and logistical scheduling. Conventional harvest assessment depends predominantly on human effort, rendering it both labour-intensive and slow. To tackle this issue, the present study proposes an algorithmic workflow that leverages unmanned aerial vehicle (UAV) video to identify and count watermelons. The workflow combines You Only Look Once version 8s (YOLOv8s) with image mosaicking and overlapping region division, which supports whole-field watermelon quantity estimation. The detection model, built on YOLOv8s and refined via transfer learning, achieved 99.20% detection accuracy, underscoring its suitability for crop forecasting. The counting strategy, which employs image mosaicking and overlapping region division, accepts stitched panoramas as input and significantly reduces double counting compared to the video-tracking-based detection and counting method. Counting accuracy exceeded 96.61%, indicating strong promise for yield forecasting applications. This elevated accuracy attests to the practicability of deploying the proposed approach for total harvest estimation across expansive watermelon cultivations.

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.

Generative artificial intelligence is emerging as a potentially important component of precision agriculture through its capacity to create synthetic data, generate agricultural imagery, retrieve and reformulate knowledge, support conversational advisory interfaces, and assist decision-support workflows. However, evidence of technical feasibility is developing faster than evidence of agronomic validity, reliability, farmer-centred usefulness, and responsible deployment. This critical review evaluates generative AI as a distinct agricultural technology class, with particular attention to generative adversarial networks, diffusion models, variational autoencoders, large language models, vision-language models, foundation models, fine-tuning, prompting, domain adaptation, and retrieval-augmented generation. It critically examines the proposed use of synthetic crop, disease, weed, pest, and remote-sensing data for augmentation, class-imbalance mitigation, and label-scarcity support, while emphasizing image realism, biological plausibility, source-data quality, and synthetic-real domain gaps. The review also assesses generative decision support and advisory systems, distinguishing accessible language generation and knowledge retrieval from agronomically validated recommendations. Reliability concerns include hallucination, factual inaccuracy, uncertainty underreporting, poor local adaptation, robustness limitations, benchmark insufficiency, and failures of human oversight. Responsible deployment further requires data governance, privacy protection, accountability, transparency, explainability, farmer trust, digital inclusion, risk monitoring, and assessment of computational and sustainability costs. The review contributes an integrated opportunity-risk interpretation and identifies priorities for domain-specific benchmarks, synthetic-data validation, hallucination measurement, uncertainty-aware assistance, human-in-the-loop evaluation, farmer-centred design, governance documentation, and cautious field-readiness assessment.

Remote sensing and machine learning have become prominent components of smart farming research, generating an expanding body of review literature across agricultural monitoring and prediction applications. This umbrella review synthesises review-level evidence concerning crop monitoring, disease detection, yield forecasting, and decision support while examining the methodological conditions that shape evidence strength and transferability. Peer-reviewed systematic reviews, scoping reviews, structured reviews, surveys, meta-reviews, and other eligible review-level articles were identified through searches of major academic databases and publisher platforms. Evidence was organised by application domain, sensing modality, analytical method, validation design, generalisation, uncertainty, reproducibility, and decision-support relevance. Crop-monitoring reviews describe extensive use of satellite, unmanned aerial vehicle, multispectral, hyperspectral, thermal, and multimodal data for crop mapping, growth assessment, phenotyping, stress monitoring, and related applications. Disease-detection reviews report rapid expansion of image-based machine learning and deep learning, but repeatedly identify data scarcity, class imbalance, curated-image dependence, and limited cross-context validation. Yield-forecasting reviews identify recurring integration of remote sensing, weather, soil, crop-model, and management information, although forecast horizons, spatial and temporal validation, uncertainty communication, and decision relevance remain inconsistent. Across domains, reported technical promise is moderated by heterogeneous datasets, benchmark inconsistency, review overlap, incomplete reproducibility, and limited evidence of transfer across crops, regions, seasons, and acquisition conditions. Review-level evidence supports a substantial research opportunity for remote sensing and machine learning in smart farming, but it does not independently establish field readiness, diagnostic reliability, operational forecasting performance, or deployment readiness. Stronger review reporting, external validation, transparent benchmarking, uncertainty assessment, reproducible workflows, and responsible decision-support evaluation are required.

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.

Smart farming technologies are often presented as innovations whose adoption depends mainly on technical availability, economic advantage, or farmer willingness. Such interpretations do not adequately explain why similar technologies are adopted and sustained in some settings but resisted, selectively used, discontinued, or abandoned in others. This realist review develops an explanatory synthesis of smart farming adoption through context–mechanism–outcome reasoning. It examines how farm structure, farmer capability, financial resources, infrastructure, connectivity, advisory support, institutional conditions, social legitimacy, platform relations, and data governance influence farmers’ interpretations of technological opportunities and risks. Adoption is distinguished from technology acceptance, partial adoption, sustained use, discontinuance, abandonment, and implementation failure. Enabling mechanisms include perceived usefulness, compatibility, trust, decision confidence, credible value, and experiential learning. Constraining mechanisms include affordability concern, return uncertainty, complexity, privacy concern, autonomy concern, platform dependency, and maintenance burden. The synthesis indicates that no contextual factor or mechanism independently guarantees adoption or implementation success. Similar technologies may generate different outcomes because farmers encounter different resources, constraints, relationships, and implementation experiences. The review proposes a recursive programme theory in which appraisal, trial, implementation experience, feedback, and changing farm conditions continually reshape perceived value, trust, capability, and willingness to continue. Responsible implementation therefore requires context-sensitive evaluation, farmer-centered usability assessment, reliable infrastructure, credible advisory and technical support, interoperability, transparent data governance, and attention to exclusion. The proposed configurations support explanatory synthesis and empirical testing rather than universal prediction or implementation prescription.

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 creating new possibilities for conversational access to agricultural information, farm data, and decision-support resources. However, fluent interaction does not establish factual accuracy, agronomic validity, farmer trust, or operational safety. This article proposes an original conceptual architecture for generative AI-enabled farm advisory systems in precision agriculture. The architecture treats conversational decision support as a governed socio-technical process rather than a standalone chatbot function. It connects farm advisory use-case definition, farmer query interpretation, heterogeneous agricultural data inputs, curated knowledge retrieval, generative model layers, response grounding, advisory-output controls, uncertainty communication, human oversight, expert escalation, farmer feedback, monitoring, and controlled system updating. Sensor observations, remote-sensing products, weather information, soil and crop data, farm-management records, and textual agricultural knowledge are positioned behind data-quality, provenance, documentation, and access-control requirements. Foundation models, large language models, vision-language models, multimodal models, prompting, domain adaptation, and retrieval-augmented generation are treated as optional architectural components whose appropriateness depends on the bounded advisory task. The architecture further distinguishes factual checking from agronomic validity review and separates farmer-facing explanations from advisor-facing evidence assessment. Safety and trust requirements include risk classification, hallucination monitoring, privacy, cybersecurity, auditability, farmer autonomy, explicit advisory boundaries, and escalation pathways. The principal contribution is a structured framework for designing and evaluating conversational farm advisory systems without implying autonomous decision authority, validated agronomic advice, guaranteed trust, operational safety, 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 increasingly embedded in smart farming systems, yet explanation requirements are often treated as a single technical attribute rather than as stakeholder-dependent needs. This article develops a conceptual taxonomy of explainability requirements across agricultural decision contexts. The taxonomy approach distinguishes stakeholders by their roles, decision consequences, explanation purposes, required explanation objects, usability expectations, accountability needs, trust risks, and implementation boundaries. Farmers may require accessible, locally relevant, actionable, and uncertainty-aware explanations that preserve autonomy. Agronomists and advisors may require model logic, input relevance, data-quality information, output rationale, limitations, and evidence supporting professional validation. Regulatory stakeholders may require traceability, documentation, auditability, risk justification, and clear responsibility allocation. Platform providers, technology providers, data intermediaries, system operators, and data stewards may require lifecycle transparency, monitoring information, provenance records, version histories, and incident reconstruction. Supply-chain and sustainability actors may require interpretable provenance and decision boundaries without treating explanation as proof of quality, sustainability, or compliance. The taxonomy also identifies failures including under-explanation, over-explanation, misleading explanations, uncertainty omission, explanation overload, false confidence, provenance opacity, accountability gaps, and trust miscalibration. Its main contribution is a structured account of how explanation requirements change across stakeholders and decision settings. The taxonomy is conceptual and requires stakeholder validation, usability testing, governance assessment, and domain-specific evaluation before operational application.

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.

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.

Precision agriculture depends on distributed data from sensors, remote sensing, machinery, crop and livestock monitoring, weather services, and farm-management systems. Collaborative model development can use these resources, yet central collection may intensify privacy, ownership, access, control, cybersecurity, participation, and secondary-use concerns. This article proposes a conceptual federated learning architecture in which farms retain raw data locally while contributing model updates to coordinated cross-farm learning. The architecture integrates use-case definition, stakeholder and governance mapping, farm-data sensitivity assessment, provenance and quality review, local node configuration, local model training, protected update exchange, secure aggregation, global and local evaluation, cross-farm validation, heterogeneity assessment, privacy safeguards, security controls, drift monitoring, auditability, and farmer feedback. It distinguishes horizontal federated learning from conditional vertical and transfer configurations and connects these principles to bounded agricultural use cases, including crop monitoring, disease detection, yield prediction, remote-sensing interpretation, livestock monitoring, and human-reviewed decision support. Secure aggregation, differential privacy, homomorphic encryption, and trusted execution environments are treated as context-dependent safeguards rather than guarantees. The contribution links decentralized model development with governance, accountability, communication constraints, non-identically distributed data, validation, monitoring, and claim boundaries. It supports research and design but does not establish certification, legal compliance, superiority, farmer approval, operational safety, or deployment readiness.