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.