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.

Accurate identification of rice diseases in precision agriculture using imagery remains difficult due to substantial misclassification rates, a wide range of influencing factors, and fluctuating conditions. While machine learning together with convolutional neural networks has yielded encouraging results for detecting rice diseases, these approaches have struggled to elucidate the interconnections among disease characteristics. In this work, we introduce an enhanced classification framework for rice diseases that combines a convolutional neural network (CNN) with a bidirectional gated recurrent unit (BiGRU). Concretely, a residual connection was embedded into the Inception module, its depth was enlarged, and a refined Convolutional Block Attention Module (CBAM) was incorporated. The upgraded CNN and the BiGRU were trained and evaluated separately; their outputs were then concatenated and forwarded to the classification layer for final prediction. Trials confirm that this strategy achieves 98.21% classification accuracy across four rice disease categories, delivering a robust solution for rice disease detection research.

The contemporary food system generates data at nearly every point where biological production, industrial processing, logistics, retail exchange, and consumer behaviour intersect. Farms produce sensor, satellite, machinery, weather, input, yield, and management data, while processing plants generate quality, safety, traceability, energy, water, and waste records. Downstream actors produce further streams of information through cold-chain monitoring, inventory systems, point-of-sale records, household consumption patterns, and nutrition-related choices. Despite this expanding data environment, the food system remains poor in system-wide intelligence because most data are captured, governed, and analysed within isolated organisational and technical domains. Production analytics, manufacturing intelligence, supply chain visibility, and consumer analytics have developed unevenly and are rarely connected into a coherent information architecture. As a result, decisions continue to be optimised locally rather than across the whole food system. This article proposes a conceptual framework for integrating production, processing, distribution, and consumption analytics into a unified food system intelligence capability. Food system intelligence is defined as the capacity to connect data across food system stages, convert them into actionable knowledge, and support decisions that improve productivity, sustainability, resilience, quality, and consumer value simultaneously. The article does not present new empirical data but synthesises existing literature to construct an integrative framework. The framework identifies four core data layers corresponding to production, processing, distribution, and consumption, joined through an integration layer based on standards, shared semantics, interoperable platforms, data-sharing agreements, and governance mechanisms. It also emphasises feedback flows, especially the use of downstream consumption, waste, and demand data to inform upstream production and processing decisions. Conversely, upstream sustainability, provenance, and production-practice data can enrich downstream retail, labelling, and consumer choice. The central argument is that food system intelligence is not primarily constrained by the absence of data but by the absence of integration and governance. Building this capability requires technical interoperability, institutional trust, reciprocal value creation, and a shift from stage-specific analytics to whole-system reasoning. The proposed framework offers a roadmap for connecting food system data to decisions from farm to fork and from fork back to farm.

Artificial intelligence is increasingly being embedded in agri-food supply chains through applications such as automated quality grading, risk scoring, demand forecasting, logistics optimisation, pricing analytics, and food safety alerts. These systems promise efficiency, resilience, and improved decision support, but they also reshape how decisions are made and who is affected by them. In food systems, AI governance is not only a technical issue but also a matter of safety, fairness, market access, and public trust. Existing responsible AI principles provide important normative foundations, including fairness, transparency, accountability, human oversight, and social benefit. However, these principles are often framed at a general level and do not fully address the distinctive structure of agri-food supply chains. Food chains are fragmented across farms, processors, logistics providers, retailers, technology platforms, regulators, and consumers, which makes governance more complex than in single-organisation AI deployment. This article develops a domain-specific Responsible AI Governance Framework for agri-food supply chains. The framework integrates four pillars: transparency, accountability, traceability, and human oversight. It argues that responsible AI in food must make algorithmic decisions visible, assign responsibility across distributed actors, preserve auditable records, and ensure meaningful human safeguards for high-risk decisions. The proposed framework specifies transparency requirements for different AI applications, maps accountability responsibilities across supply chain actors, connects traceability systems to auditability, and defines human oversight mechanisms for safety-critical and livelihood-sensitive decisions. Three tables operationalise the framework through transparency requirements, accountability allocation, and integrated governance mechanisms. The article concludes that responsible AI in food requires governance that is as distributed, interconnected, and safety-conscious as the supply chains it seeks to guide.

Artificial intelligence is increasingly used in food safety systems to support contamination detection, shelf-life prediction, quality classification, inspection prioritisation, and risk scoring. These applications promise faster, more sensitive, and more scalable decision support across complex food supply chains. However, the same predictive complexity that makes AI useful can also make its outputs difficult for food safety professionals, regulators, and operators to interpret. The central problem addressed in this framework article is that AI-supported food safety decisions may become opaque, uncontestable, and weakly aligned with existing structures of regulatory responsibility. When risk scores or alerts cannot be understood, challenged, or traced to relevant evidence, they may undermine rather than strengthen food safety governance. This problem is especially serious because food safety decisions involve direct public health consequences, market consequences, and legal accountability. The objective of this article is to develop an original Explainable AI Framework tailored to food safety decision systems. The framework integrates four interdependent dimensions: risk interpretation, regulatory confidence, operational accountability, and human review. It treats explainability not only as a technical property of models but also as a governance condition for responsible food safety decision-making. The article is based on a conceptual synthesis of 27 peer-reviewed articles published between 2017 and 2025 across food safety, explainable artificial intelligence, algorithmic accountability, risk assessment, and digital food safety systems. It does not present new empirical data. Instead, it constructs a design and governance framework that can guide the development, validation, deployment, and oversight of AI-supported food safety tools. The proposed framework defines four pillars: interpretable risk communication, transparent regulatory evidence, accountable operational responsibility, and contestable human review. Together, these pillars show how food safety AI systems can become not only predictive but also auditable, trustworthy, and practically usable. The article argues that embedding explainability into food safety AI is a governance and trust-building imperative rather than a purely technical enhancement.

Circular food systems require a shift from linear models of production, consumption, disposal, and remediation toward systems that continuously recover value from biological materials. This conceptual article argues that such a transition cannot rely on policy, behavioural change, or technological substitution alone. It also requires an intelligence layer capable of sensing waste generation, interpreting material quality, identifying recovery options, and coordinating decisions across fragmented food-system actors. Artificial intelligence offers this intelligence layer by enabling predictive, diagnostic, and decision-support capacities across the food chain. Rather than treating AI as a narrow automation tool, this article positions AI as cognitive infrastructure for circular food economies. Its role is to connect data on food loss, by-product composition, logistics, environmental impacts, recovery technologies, and stakeholder constraints. The article develops a conceptual framework for AI-enabled circular food systems. The framework integrates five functions: waste detection, valorisation pathway selection, resource recovery, sustainability-oriented decision support, and cross-actor coordination. These functions are presented as mutually reinforcing layers that allow food materials to be tracked, evaluated, redirected, and valorised before they become unmanaged waste. The article contributes to sustainability and circular economy scholarship by linking food-waste valorisation with material flow intelligence and multi-criteria decision support. It highlights how AI can support real-time evaluation of waste streams, match heterogeneous residues with suitable recovery pathways, and improve the coordination of producers, processors, retailers, consumers, waste managers, and policymakers. It also clarifies the risks of fragmented digitalisation when data systems are not aligned with circular outcomes. The proposed framework is intended for researchers, practitioners, and policymakers seeking to design circular food systems that are adaptive, evidence-based, and sustainability-oriented. It does not present new empirical data. Instead, it provides a conceptual basis for future empirical testing, digital platform development, policy design, and interdisciplinary research on AI-enabled food circularity.

Food systems increasingly generate consumer data through digital platforms, shopping records, dietary applications, wearable technologies, loyalty schemes, and personalised nutrition services. These data can reveal patterns of preference, dietary behaviour, product use, affordability constraints, and health-oriented needs. However, consumer data are often used for commercial targeting while remaining disconnected from product reformulation, nutrition improvement, and public health goals. AI-enabled food intelligence is frequently positioned as a tool for predicting consumer preferences or delivering personalised recommendations. This narrow use limits the potential of AI to support healthier food environments, more acceptable reformulated products, and more transparent consumer communication. A broader framework is needed to connect consumer insight with nutrition evidence, product innovation, ethical governance, and public trust. This article proposes a consumer-centred food intelligence framework linking AI, nutrition personalization, product reformulation, trust, transparency, and public health. The framework treats consumers not only as data sources but also as beneficiaries, participants, and evaluators of food-system innovation. It explains how individual and aggregated consumer intelligence can inform dietary advice, product design, reformulation priorities, and responsible communication. The article contributes a structured conceptual model for ethically transforming consumer data into health-oriented and trust-sensitive food-system decisions. It argues that AI should not only recommend diets or predict purchasing behaviour, but should also help translate nutritional evidence into acceptable products and transparent innovation pathways. Consumer-centred food intelligence is presented as a foundation for more responsible, healthier, and publicly trusted digital food systems.