Search

The light-trap attraction rate (LTARI) constitutes a critical parameter for delineating diel activity profiles and underpins work in insect behavioral ecology and pest suppression. Nevertheless, mainstream automated light-trap apparatuses commonly employ destructive methods (e.g., electrified meshes or thermal irradiation), resulting in substantial losses of non-target organisms and markedly impairing image quality due to carcass accumulation. These shortcomings disturb indigenous assemblages and thwart attempts to measure LTARI. Our central objective is to engineer and appraise a non-lethal recording framework to serve as a technical substrate for subsequent LTARI inquiry, rather than to conduct direct quantitative benchmarking against orthodox traps. To remedy the shortcomings outlined above, we present a live-specimen recording instrument that merges a wind-aspiration collector with a Water-Flow Dispersion and Transport Structure (WF-DTS). The harmless trap–disperse–release pipeline curbs body layering, enables the return of captured creatures to the wild, and yields a community-scale post-collection survival fraction of 94% under the tested regime. Empirical data demonstrate that the prototype safeguards picture coherence featuring unambiguously separated single organisms and realizes a recognition score of 95.6% ([email protected]) employing the YOLOv8s architecture. During inference, only the built-in resizing and standardization routines of YOLOv8s are invoked, without supplementary noise filtering, background removal, or synthetic sample inflation. These findings indicate that the WF-DTS yields snapshots that are inherently more amenable to partitioning and identification than those from legacy equipment. The elevated recognition fidelity is predominantly ascribed to the mechanical splaying of individuals and the homogeneous, pale-matte arena provided by the hardware blueprint. Taken as a whole, the ensemble embodies a harmless hardware–software apparatus apt to trim downstream analytical burdens and provide methodological groundwork for enhanced LTARI calculation in prospective, purpose-built field exercises.

Swarm-based unmanned aerial vehicle (UAV) systems are increasingly recognized for their capabilities in extensive IoT and precision agriculture operations, notably in collaborative surveillance and the tracking of multiple moving objects across outdoor terrains. Nevertheless, prevailing coordination mechanisms tend to assume flawless communication channels, disregarding practical network disturbances including congestion, dropped packets, and transmission delays. Such disruptions hinder the prompt relay of data among UAVs and the terrestrial control station, causing control instructions to arrive late or not at all. The outcome is a breakdown in coordination fidelity and a steep decline in tracking effectiveness when these systems are fielded. To remedy this shortcoming, we put forward CSOOC (Communication-State Driven Online–Offline Coordination with Congestion Control), a hybrid governance scheme that fuses centralized learning-powered decision processes with decentralized rule-governed behaviors, enabling UAVs to tailor their actions to instantaneous network status. The CSOOC framework is built around three core elements: (1) an online component providing centralized orchestration while communication remains dependable, (2) an offline, profit-guided movement policy relying on localized Gaussian maps to sustain autonomous target pursuit when connectivity drops, and (3) congestion mitigation rooted in STAR (Stratified Transmission and RTS/CTS), which couples staggered transmission timing with RTS/CTS handshake protocols to bolster uplink robustness. A cohesive co-simulation infrastructure is constructed, linking network-layer communication with swarm-level control and coordination dynamics. Trials reveal that CSOOC delivers a mean observation ratio of 39.7%, outperforming reference algorithms by margins of 4.4%–11.13%, while also boosting network dependability through markedly improved packet delivery success under saturated channel conditions. These outcomes confirm that CSOOC successfully spans the disconnect between algorithm performance within simulators and the operational realities of UAV collectives in communication-challenged settings.

Driven by the worldwide surge in fish maw commerce, authenticity verification has emerged as an urgent concern due to mounting adulteration incidents. Conventional approaches to verification—whether sensory-based, chemically oriented, or molecular—suffer from practical deployment constraints. The present study reframes fish maw genuineness assessment as a detection task within the object recognition paradigm and introduces RDT-YOLO, a streamlined detection model grounded in YOLO11n architecture. Addressing the twin difficulties of insufficient nuanced texture representation and processing overhead in this domain, we engineer hierarchically structured reparameterized modules for feature extraction that deploy reparameterization tactics to amplify multi-resolution texture discrimination. To counteract degradation of information arising during cross-scale feature merging, a Dynamic Adaptive Multi-Scale Pyramid Processing (DAMSPP) component is devised, integrating adaptive convolution dynamics that facilitate responsive feature synthesis. Concurrently, an Adaptive Task-Aligned Detection Head (ATADH) is formulated, fusing interactive task mechanisms with weight-shared convolutions to achieve parameter economy alongside precision gains. Moreover, Wise-ShapeIoU, a novel loss formulation, is constructed by injecting Wise-IoU's focusing coefficient into the Shape-IoU framework, thereby sharpening detection fidelity through refined contour alignment. Benchmark experiments confirm that RDT-YOLO delivers precision of 91.9%, recall of 89.6%, and [email protected] of 94% while slashing parameter count, storage footprint, and FLOPs by 75.6%, 73.8%, and 63.8%, respectively, against YOLO11s. Comparative trials versus YOLOv10s and YOLOv12s reveal [email protected] elevations of 0.8 and 0.5 percentage points. This investigation furnishes an automated pipeline for verifying fish maw genuineness, bearing implications extending across food integrity applications.

Crop diseases constitute a danger to worldwide food stability, diminishing harvest yield, grade, and total farming efficiency. Conventionally, the identification of plant ailments has depended on lengthy visual assessments by specialists, a method that frequently results in mistakes. Machine learning (ML) and artificial intelligence (AI), in particular Vision Transformers (ViTs) and Convolutional Neural Networks, deliver a swifter, automated substitute for recognizing plant illnesses through leaf image analysis. However, these frameworks are regularly faulted for their "black box" character, which curbs confidence in their outputs due to a lack of clarity. Our outcomes indicate that integrating Explainable AI (XAI) approaches like Grad-CAM, Integrated Gradients, and LIME notably boosts model explainability, rendering it simpler for users to detect the fundamental indicators of plant sicknesses. This investigation not only adds to the area of plant disease recognition but also supplies an original viewpoint on advancing AI openness in actual farming settings through the application of XAI methods. With training accuracy rates of 100.00% for ViT, 96.88% for EfficientNetB7, 93.75% for EfficientNetB0, and 87.50% for ResNet50, and equivalent validation accuracy rates of 96.39% for ViT, 86.98% for EfficientNetB7, and 82.00% for EfficientNetB0, our suggested architectures exceed earlier studies performed on the identical dataset. This illustrates a considerable leap in model capability while upholding clarity and dependability by way of explainable and trustworthy decision procedures.

Food waste is a critical concern for both developing and advanced economies alike. Digital technologies hold promise for helping to alleviate this problem, and our investigation sets out to deliver a workable prototype employing cloud-based image classification alongside tailored OCR techniques. The product of our work is an economical yet high-performing mobile app prototype that establishes a foundation for future inquiry. We drew on sophisticated principles of application integration—encompassing mobile frameworks, Firebase machine learning modules, and OCR procedures—to signal how near food items are to spoiling. Where no printed date exists, the system generates an indicative shelf-life projection built on prudent category-based assumptions. These projections do not constitute safety determinations and are not a substitute for manufacturer date markings or national food-safety regulations. The outcomes lend our paper unmistakable originality and scholarly value, boosting the operational efficiency of storage facilities and retail food outlets. The ramifications of our work are technical, economic, and societal in nature.

The increasing menace of climate change constitutes a profound obstacle for contemporary farming, carrying grave implications for worldwide food availability. The effect of altering climatic parameters on agricultural output, particularly for essential staple commodities, fuels worry regarding prospective harvests. This investigation explores the likely repercussions of climate change on cotton cultivation by merging archival climate records, Global Climate Model (GCMs, CMIP3) forecasts, and cotton production statistics. A broad spectrum of machine learning (ML) methodologies is applied, including multiple regression, k-nearest neighbors (KNN), boosted tree techniques, and several variants of artificial neural networks (ANNs), to delve into the intricate linkage between climatic drivers and cotton productivity. The models are built and verified using climatic and crop output data obtained from three districts within Punjab, Pakistan, across the timeframe 1991 to 2020. To anticipate future production outcomes, climatic projections from General Circulation Models (GCMs) are refined via downscaling under the SRA1B, A2, and B1 emission trajectories, facilitating outlooks extending to 2050. The outcomes reveal that precipitation exerts a trivial influence on cotton output (R = 0.0002), while peak temperature (R = -0.183) stands out as the foremost climatic determinant shaping yield, trailed by lowest temperature (R = 0.248). Of the tested architectures, the generalized feedforward (GFF) network delivered the optimal results (R = 0.960, MSE = 0.110, NMSE = 0.187, MAE = 0.269), exceeding the performance of the probabilistic neural network (PNN), KNN, multilayer perceptron (MLP), and boosted trees. By comparison, linear regression (LR) and multiple regression formulations registered weaker predictive power. The trustworthiness of GFF and KNN for generating yield projections (R² = 0.892, 0.861) endorses their suitability for reliable forecasting. The study calculates a 4.5% contraction in cotton harvest by 2050, measured against the peak recorded yield for the locality, stressing the footprint of climate change on cotton farming and its latent hazard to food supply. Nonetheless, the flexible strength of the ANN (GFF) frameworks under varying climate storylines delivers auspicious means for weaving ML into climate-adaptive cultivation regimes, advancing durable agrarian safety and curbing the detrimental fallout of climate shifts on nutrition provision.

Reliable estimation of crop yield is vital for refining farming operations and guaranteeing food supply. This investigation tested the capacity of machine learning techniques to estimate tomato yield using meteorological measurements, spectral reflectance bands, and vegetation indices subjected to different nitrogen levels and bio-stimulant applications to generate variation in crop development. UAV-mounted sensors captured spectral information across seven acquisition dates spanning October 27 to December 15, 2023, matching critical developmental windows: vegetative establishment (acquisition 1), anthesis (acquisitions 2 and 3), fruit set and enlargement (acquisitions 4, 5, and 6), and initial maturation (acquisition 7). Discriminating explanatory variables were selected via the Pearson correlation metric (r > 0.65, P < 0.05), incorporating Near Infrared (NIR), Red Edge, and Red wavebands, together with vegetation indices comprising NDVI, GNDVI, NDRE, and SAVI. Remotely sensed canopy signatures gathered throughout the fruit set and enlargement window (acquisitions 5 and 6) displayed the tightest association with harvested yield (r = 0.66–0.74), reinforcing the necessity of spectral intelligence from the middle to latter parts of the cycle. When comparing predictive algorithms, both linear regression (LR) and XGBoost yielded the strongest predictive skill, producing root mean squared error (RMSE) figures of 16.13 kg and 16.15 kg, respectively, matched with R² values reaching 0.63. Support vector machine (SVM) and decision tree (DT) implementations also delivered competent outcomes, achieving RMSE scores of 17.15 kg and 17.18 kg, respectively. By comparison, the deep learning architecture lagged notably (RMSE = 23.49 kg, R² = 0.23), plausibly attributable to data scarcity. This research spotlights the prognostic capability inherent in spectral wavebands and underscores the centrality of growth-stage-aligned spectral acquisition for yield forecasting.

Real-time tracking of soybean seedling development demands an efficient approach for correctly recognizing seedlings and eliminating weeds. Difficulties stem from the tiny scale and shape-based likeness between seedlings and weeds, which makes standard detection techniques more complex. In response to these issues, a real-time detection framework termed YOLOv9-GSSA is introduced. A refined Mosaic-Dense algorithm boosts object concentration at the input stage of the model, improving its power to capture subtle features. Additionally, a neck optimization component called GSSA, integrating GSConv with Gated Self-Attention, aids essential information extraction and the exchange of features across scales. The Swin-GSSA prediction head further draws on spatial positioning cues, enabling better small object recognition and resolution of overlapping occlusion. Tests reveal that our model secures a mAP of 47.5% with a per-image detection speed of 23.42 ms, making it viable for real-time surveillance. The upgraded model notably strengthens the recognition of soybean seedlings and weeds, functioning as a useful asset for efficient farmland oversight. This ultimately contributes to precise yield forecasting and informed choices in precision agriculture.

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.

Grass carp hemorrhagic disease (GCHD), which is induced by grass carp reovirus (GCRV), stands as one of the most severe communicable diseases jeopardizing freshwater aquaculture, creating a demand for innovative, effective, and affordable surveillance tools. Machine vision can serve as a powerful inspection method, enabling early alerts for GCHD epidemic spread. Yet, experimental dataset tests indicate that the detection precision of existing deep learning algorithms remains unsatisfactory. In the present study, image datasets of the model organism Chinese rare minnow (Gobiocypris rarus) manifesting GCHD signs were gathered, and a self-attention-based convolutional neural network (SA-CNN) deep learning architecture was designed. This SA-CNN framework is capable of reliably pinpointing Chinese rare minnow individuals displaying GCHD symptoms. Through pre-processing the extracted imagery using refined k-means and improved watershed algorithms, tightly clustered or superimposed fish can be adaptively disentangled within populations, thereby elevating recognition accuracy. With an optimized loss function, the SA-CNN model delivers an accuracy of 99.1%, a recall of 97.7%, and an F1 score of 96.6% on the collected datasets of symptomatic fish. Its precision outperforms current state-of-the-art you only look once (YOLO) network families by margins between 4.9% and 25.6%, varying across different model variants. Image identification demands a mere 95ms per frame, highlighting considerable operational efficiency. Ablation studies confirmed that incorporating the self-attention module yielded accuracy gains of 3.8% and recall improvements of 3.0%. Accordingly, this refined SA-CNN framework furnishes an efficacious solution for the essential large-scale deployment of GCHD surveillance initiatives tracking GCRV transmission, paving the way toward intelligent, health-oriented, and precision aquaculture.

Guaranteeing end-to-end visibility, certified conformity, and uninterrupted temperature control in frozen food logistics remains an enduring obstacle, compounded by siloed oversight tools, hands-on inspection routines, and exposure to information falsification. This paper puts forward a blueprint for a blockchain-anchored conformity framework that resolves these difficulties by fusing continuous Internet of Things (IoT) sensing, authorized blockchain-based recordkeeping, and automated conformance enforcement via smart contracts. Adopting a Design Science Research (DSR) approach, the inquiry zeroes in on the formative stages (challenge scoping, goal setting, and artefact blueprinting) to deliver a methodical grounding for subsequent testing and appraisal. The envisioned construct is arranged across three mutually reliant strata: (1) a data acquisition layer that secures uninterrupted and safeguarded sensor-fed tracking; (2) a data storage layer that harnesses blockchain for indelible logs and open verifiability; and (3) an application layer that weaves in smart contracts for hands-off compliance activation along with dashboards for actor engagement. By reinterpreting statutory conformity mandates into a compartmentalized, blockchain-centric blueprint, this investigation fortifies the conceptual basis of decentralized governance apparatuses within agri-food networks. The formulated framework codifies design maxims capable of shaping parallel provenance systems in other heavily audited supply networks. While practical corroboration is yet to come, the architectural outline supplies a platform for later DSR rounds and enriches design intelligence in the arena of digital conformity infrastructures.

Reliable, hands-off measurement of bovine body dimensions and weight is vital to increasing output and accelerating genetic gains in tropical beef enterprises. Traditional techniques are time-consuming, demand heavy machinery, require handling livestock, induce animal stress, and are frequently unworkable for resource-constrained smallholders lacking adequate infrastructure. This paper introduces an original, smartphone-operated platform for instantaneous body dimension capture and weight forecasting in Brahman cattle, driven by a cloud-based artificial intelligence (AI) engine. A corpus of 12,660 lateral photographs was assembled and tagged for hip depth (HD) and body length (BL), with YOLOv11 convolutional neural network variants undergoing training and evaluation. The YOLOv11m configuration achieved the highest metrics (precision: 99.85%, recall: 100%, F1-score: 99.92%, IoU: 97.68% ± 1.31%), and the automatic extractions displayed tight concordance with manual ImageJ-derived figures (MAPE < 0.4%). HD and BL were strongly intercorrelated in both sexes (r = 0.98–0.99) and moderately indicative of body weight (r = 0.57–0.59). A multiple regression formula incorporating HD and BL delivered the most precise body weight predictions (MAE = 43.44 kg; MAPE = 8.91%). The system was fielded via a LINE messaging chatbot interface, allowing users to upload cattle photos and receive immediate dimensional outputs and weight approximations straight to their smartphone—doing away with any need for bespoke hardware. This inexpensive, easy-to-operate AI instrument supplies a scalable avenue for digital phenotyping, herd oversight, and evidence-based selection in smallholder environments. The concept exhibits substantial capacity to enable data-informed management and enduring productivity improvements in tropical beef networks.

Quantifying soil total nitrogen (TN) with high accuracy is vital for boosting crop vigor and quality. A major obstacle, however, is that soil diversity from one region to another undermines the transferability of calibration models. To confront this obstacle, this paper puts forward a framework called transfer-learning-assisted laser-induced breakdown spectroscopy for cross-regional soil analysis (TransLIBS-CRS), which is custom-built to counteract the weak cross-domain predictive capacity caused by differences in regional soil characteristics. By adapting the model with a small batch of samples from the target setting, the technique substantially elevates the cross-domain utility of LIBS measurements, easing the difficulties tied to procuring soil specimens from geographically dispersed locations. In tests where Beijing data were used to infer TN levels in Guangzhou, the TransLIBS-CRS model yielded the strongest outcomes, recording an R2V of 0.846 and an RMSEV of 0.814 g/kg. A closer look via saliency mapping and chemometric tools indicated that carbon emission wavelengths at 193.0 nm and 247.8 nm serve a decisive function in TN quantification. Crucially, these spectral markers kept their predictive power unchanged when carried over to the Guangzhou soil dataset. This tactic furnishes a workable route toward broad-scale, high-efficiency soil TN assessment.

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.

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 tracking and forecasting of dissolved oxygen (DO) concentrations in aquaculture environments are essential for sustaining ideal water quality and safeguarding fish well-being. This research introduces an improved Long Short-Term Memory (LSTM)-based framework for DO forecasting that leverages historical records of DO concentrations, water temperature, and other environmental variables. In contrast to conventional techniques that rely on static assumptions, the proposed framework dynamically adapts to changing environmental conditions, delivering immediate, high-accuracy predictions. Experimental results show that the improved LSTM framework achieves a forecasting precision of 92.28%, surpassing current models, including IFP (81.97%), DOE (63.81%), and DOP (86.79%). The framework's exceptional precision and flexibility make it a reliable tool for aquaculture oversight, helping optimize DO levels and reduce the risk of fish deaths. By incorporating artificial intelligence into aquaculture surveillance, this method enhances system performance and long-term viability.

The capacity to detect rapeseed with precision and to track the enlargement of its canopy coverage stands among the most telling phenotypic signals of how the crop is developing. When both the individual rapeseed plant and the zone it occupies can be accurately recognized, the resulting data stream provides a powerful foundation for downstream phenotypic exploration and breeding programs. The difficulty, however, is that in genuine field conditions, detection performance continues to face serious obstacles because RGB data alone provides only a limited vocabulary of representable features. Seeking a way around this limitation, the work described here advances a dual-modal instance segmentation framework, MSNet, which builds on YOLOv11n-seg and combines RGB and Near-Infrared (NIR) data streams. The chief innovations embedded in this framework comprise three strategies governing where fusion occurs (at the front end, at an intermediate stage, or at the back end), together with a newly crafted Hierarchical Attention Fusion Block (HAFB) dedicated to blending multi-modal features. Experiments designed to compare these placement choices reveal that conducting fusion at the intermediate stage delivers the strongest compromise between how accurately the model detects and how economical it remains in terms of parameter count. Relative to the baseline, the improvement in mAP50:95 can reach 3.5%. Once the HAFB unit is incorporated, the MSNet-H-HAFB configuration posts a 6.5% lift in mAP50:95 over that baseline, while requiring fewer than 38% extra parameters. A point that deserves emphasis is that mid-stage fusion consistently outperformed the alternatives in every experimental run, supplying a clear blueprint for where future multi-modal architectures should position their fusion operations. In further testing, side-by-side comparisons against a suite of RGB-only instance segmentation alternatives confirmed that all MSNet-HAFB fused variants decisively beat single-modal counterparts on rapeseed count detection, reinforcing the case that multi-spectral fusion holds genuine promise for recognizing agricultural targets. As a concluding step, MSNet was applied in a practical agricultural scenario that included vegetation index analysis and grading of frost-related damage. The data pointed to ZN6–2836 and ZS11 as likely candidate elite lines, while the EVI2 vegetation index registered the strongest classification scores for frost damage in rapeseed.

A precision spray perception system using LiDAR was designed, algorithmically developed, and experimentally verified to address the problem of low navigation line extraction accuracy in self-propelled sprayers, which causes wheel encroachment on ridges and pesticide overuse. For this perception system, a data processing framework was built encompassing preprocessing, adaptive segmentation separating crops from ditches, and the derivation of navigation lines and crop positioning, all originating from raw LiDAR point cloud species. To validate the system’s stability, field data on cabbages at different growth stages were collected and analyzed. A controllable, constant-speed experimental configuration was set up to benchmark LiDAR against a depth camera within the same field conditions. The trial outcomes reveal that at sprayer speeds of 0.5 and 1 ms⁻¹, the peak lateral deviation reaches 0.112 m within cabbage ridge settings containing inter-row weeds. In comparison, the mean absolute lateral error stands at 0.059 m. Each frame is processed in no more than 43 ms. Compared with the machine vision approach, the proposed technique reduces the mean processing time by 122 ms. In terms of identification accuracy, computational speed, and overall robustness for crop detection and navigation line derivation, the system introduced here outperforms its machine vision counterpart.

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.

Cotton growth is severely threatened by Verticillium wilt, which has a considerable negative effect on yield. For this reason, prompt identification of stress-related disease is critically important. The current work explored how Verticillium wilt stress influences leaf microstructure and physiological metrics (SOD, POD, CAT, MDA, Chla, Chlb, Chlab, Car) in cotton and tested whether hyperspectral imaging could be used to estimate those leaf physiological metrics. Results revealed that disease-induced stress altered the cellular architecture of cotton leaves, leading to the breakdown and disintegration of chloroplasts and mitochondria. Moreover, infected leaves showed significantly higher SOD and POD activities, as well as elevated MDA levels, relative to their healthy counterparts, while chlorophyll and carotenoid concentrations dropped markedly. Furthermore, rapid-assessment models for cotton physiological metrics were built, with the strongest models attaining Rp values spanning 0.809 to 0.975. These models were then employed to generate visual maps of the distribution of physiological signatures over cotton leaf surfaces. The outcomes indicate that the physiological phenotype of cotton leaves can be reliably captured using hyperspectral imaging, providing a solid theoretical foundation for rapid identification of Verticillium wilt stress.

The root system is essential not only for nutrient uptake and anchoring the plant but also for shaping crop development and responses to environmental stress. Rhizobox setups permit in situ, non-invasive root observation in soil, representing an economical imaging strategy. Nevertheless, soil’s non-transparent nature frequently produces discontinuous root images with intermittent gaps, diminishing the precision of derived root phenotypic metrics. We propose a root inpainting methodology grounded in a Generative Adversarial Network (GAN) framework. Furthermore, a hybrid root inpainting dataset (HRID) was assembled, containing 1206 cotton root images with genuine gaps and 7716 rice root images with synthetically introduced gaps. Compared with computationally simulated root depictions, our dataset provides authentic root system architecture (RSA) and textural characteristics. Rather than cropping during training, our technique uses downsampled versions of the full image to convey the complete root morphology. Training the model uses binary cross-entropy loss to differentiate between root and background pixels.Additionally, Dice loss is incorporated to counteract the effects of uneven class representation. Skip connections typical of U-Net are removed, and an edge attention module (EAM) is introduced to retain more granular structural details. Compared with competing approaches, our technique substantially increases recall from 17.35% to 35.75% on a cotton root test collection of 122 images, indicating marked gains in inpainting fidelity. For root area, root length, convex hull area, and root depth, the trait error reduction rates (TERRs) reach 76.07%, 68.63%, 48.64%, and 88.28%, respectively, delivering significantly more accurate root phenotyping outcomes. Both the EU-GAN source code and the 8922 annotated images are openly accessible, offering potential reuse in other AI-driven investigations. This work provides a resilient solution for root phenotyping, thereby accelerating breeding workflows and expanding knowledge of root system behavior.

Agricultural output and the assurance of food supplies depend fundamentally on plant breeding. A new chapter in this field has been opened by Genomic Selection, a technology distinguished by its power to exploit variation across the entire genome for predictive purposes. This technique makes it unnecessary to have pre-existing knowledge of the genes controlling particular characteristics. Yet, the enormous scale of genomic information, contrasted with the usually scarce set of phenotypic observations, frequently leads to the “curse of dimensionality,” in which classic statistical approaches, machine learning, and deep learning architectures tend to memorize noise rather than learn patterns, yielding poor predictive performance. To address this barrier, we propose a consolidated Variational auto-encoder-based Multi-task Genomic Prediction model (VMGP) that fuses a self-supervised process of shrinking and rebuilding genomic data with several simultaneous forecasting objectives. This method provides a durable solution, offering a powerful inferential engine that has undergone rigorous verification across publicly available datasets for wheat, rice, and maize. The model we have built displays extraordinary proficiency in forecasting across multiple phenotypes and varying environments, effectively mastering the challenges of genomic selection spanning different populations and highlighting its distinct capabilities and practical importance. In addition, by fusing VMGP with tools for model transparency, we can efficiently sift through and prioritize influential single-nucleotide polymorphisms, thereby boosting prediction accuracy and putting forward avenues for potentially more economical genotyping workflows. The VMGP framework, characterized by its clean design, strong forecasting capabilities, and publicly accessible source code, is well-suited for widespread rollout across plant breeding operations. It proves especially valuable for practitioners whose main focus is phenotypic projection, yet who might not be deeply versed in deep learning methodologies or the intricacies of hyperparameter optimization.

The push toward precision agriculture is increasingly driven by environmental considerations alongside economic pressures, fueling progress in variable-rate fertilization (VRF) technology. Although centrifugal fertilizer spreaders offer benefits such as mechanical simplicity, low cost, and high throughput, non-homogeneous spread patterns are becoming a primary obstacle to their broader use. An urgent investigation is therefore required into how particles behave and what variability patterns emerge when centrifugal VRF spreaders operate under multi-pass overlapped application, to boost both evenness of coverage and field accuracy. This paper examined and assessed the operational characteristics of a custom-built centrifugal VRF spreader that uses real-time crop status data for rice and wheat, applying the collection tray protocols detailed in ISO 5690 and ASAE S341.2 (1999). Distribution uniformity was evaluated by calculating the coefficient of variation (CV) from weighed fertilizer captured in standardized trays, thereby gauging the evenness of the applied spread profile. The obtained data indicated effective swath widths of 21.05, 22.58, and 23.67 m corresponding to target application dosages of 225, 300, and 375 kg/ha, respectively. In practice, multi-pass, overlapped spreading tended to deliver application amounts exceeding the intended rates, with within-swath CVs of 11.51, 9.25, and 11.28% for each respective dosage level. Field-based assessments of multi-pass, overlapped operations recorded a mean discrepancy of 4.54% between delivered and target rates, along with a mean lateral distribution CV of 11.94% across the implement’s working span, results that align with the performance criteria for transverse particle placement using centrifugal broadcasters. The insights generated by this work provide a conceptual reference point for the design refinement and technological evolution of centrifugal VRF equipment, carrying considerable applied and societal value in hastening their integration into everyday precision farming practice.

To address poor accuracy in identifying open-field vegetables when light is blocked, this investigation used cabbage as the subject. It established an online target identification model based on deep learning. Using YOLOv8n as the backbone network, an approach was formulated to reduce the impact of light occlusion on the precision of online cabbage identification. A sequence of cabbage image filters was engineered to remove the consequences of light occlusion. A unit for adaptive parameter acquisition tailored to the cabbage image filters was built. The image filter sequence and the adaptive acquisition unit were woven into the YOLOv8n object detection architecture. This fusion enabled precise, real-time identification of cabbage in light-occluded environments. Experimental outcomes indicated identification precisions of 97.5% with the normal lighting dataset, 93.1% with the light occlusion dataset, and 95.0% with the mixed dataset. When the degree of light occlusion exceeded 0.4, the identification precision increased by 9.9% and 13.7% compared with the YOLOv5n and YOLOv8n architectures. The model achieved identification precisions of 99.3% with the Chinese cabbage dataset and 98.3% with the broccoli dataset. The model was deployed on an Nvidia Jetson Orin NX edge device, where it processed images at 26.32 frames per second. Field assessments showed identification precisions of 96.0% in ordinary light and 91.2% when light was blocked. The presented online cabbage identification model facilitates instant recognition and spatial location of cabbage in complex open-field conditions, providing technical support for targeted spraying.

Precision livestock farming depends critically on the ability to identify individual animals. One practical route for marking individual livestock is freeze branding with liquid nitrogen. With the march of technological progress, deep learning pipelines have begun to be deployed for reading such individual markings. The present work introduces a deep-learning-based pipeline for the localization and interpretation of oriented horse brands. In the first stage, Rotational YOLOv5 (R-YOLOv5) was harnessed to pinpoint the oriented brand, after which YOLOv5 processed the extracted brand patches to read the digits. Within that first stage, R-YOLOv5 departed from standard detection frameworks by embedding orientation directly into the YOLO architecture through Circle Smooth Label (CSL). In addition, Coordinate Attention (CA) was woven into the network to sharpen its focus on spatial positioning cues. These design choices boosted the fidelity with which oriented brands were detected. The second stage reframed digit reading as an object-detection problem, given the need for precise identification. The full brand number was then assembled by ordering the detection boxes according to their spatial coordinates. Experimental comparisons revealed that R-YOLOv5 outpaced competing rotating target detection methods, achieving an AP (Average Accuracy) of 95.6%, FLOPs of 17.4 G, and an inference rate of 14.3 fps. The digit reading stage delivered an mAP (mean Average Precision) of 95.77%, a weight footprint of 13.71 MB, and an inference rate of 68.6 fps. Through this two-stage design, brand numbers can be read reliably even against cluttered backgrounds, offering a robust yet lightweight solution for individual livestock identification.

Automated phenotyping, the automated measurement of plant characteristics, supports breeders and growers in producing vigorous, resilient crops. An early-detection tool can accelerate the discovery of plant resistance and swiftly identify problematic breeding outcomes. Numerous phenotyping objectives of this kind can be met by analyzing images captured by simple, inexpensive RGB-D cameras. The present work focuses on a case study — assessing the degree of resistance that tomato hybrids exhibit against the tomato yellow leaf curl virus (TYLCV) in commercial greenhouses. This poses a tough challenge, given that discriminating between resistance classes from imagery is difficult even for seasoned breeders. A substantial image collection was assembled from a trial encompassing many tomato hybrids with different resistance ratings. Depth data served to pinpoint the highest section of the tomato plant. Subsequently, deep learning networks were deployed to categorize the distinct resistance classes. For spotting plants with visual indicators, our techniques achieved an accuracy of 0.928, a precision of 0.934, and a recall of 0.95. In the multi-class scenario, an accuracy of 0.76 was achieved in identifying the appropriate level, with an error of 0.278. Our pipelines are not exclusively tailored for this task and can be expanded to other undertakings that detect various plant diseases with outward signs, including ToBRFV, mildew, ToMV, and others.

The quantification of actual evapotranspiration (ETₐ) is fundamental to sound water resource governance, yet current estimation methods pose significant constraints. Established methodologies, among them eddy covariance and energy balance computations reliant on remote sensing, are frequently beset by prohibitive costs, patchy spatial and temporal coverage, and deteriorating forecast fidelity, particularly for older empirical constructs. Although machine learning has emerged as a viable solution, it is not without drawbacks, especially a systematic bias toward low ETₐ predictions during high-temperature episodes. We trace this deficiency to inadequate model training on the scarce but critically significant extreme ETₐ values, paired with meteorological datasets that are limited rather than massive. Within this paper, we illustrate how few-shot, meta-learning frameworks (MAML), purpose-built to deliver superior generalization when data are constrained, can eclipse elementary machine learning formulations in the upscaling of ETₐ originating from two major in-situ observation networks, namely Ameriflux and Euroflux. Working with a sparse set of remotely sensed land surface variables sourced from the METRIC-EEFlux system alongside a narrow suite of climatic drivers, we establish that the selected models yield measurable benefits when assessed under the utility-based regression philosophy, guiding meaningful real-world decisions. Our preliminary findings show that EEflux ETₐ strays markedly from in-situ tower readings from the Ameriflux and EEflux installations (R² = 39%). By comparison, MAML attains the strongest alignment with ETₐ, outperforming both elementary machine learning architectures and EEFlux (R² = 71% on the full test corpus, R² = 0.88 under the Csa climate class, R² = 0.79 under the Cfa climate class, and R² = 0.78 for the CSH vegetation category), and steadily improves without succumbing to overfitting even when trained on a comparatively modest data pool. Its elevated F2 score (96%) indicates that MAML maintains high precision and recall for atypical instances, a feature of considerable consequence for irrigation scheduling. As a noteworthy result in its own right, this investigation corroborates that even a sparse set of remotely sensed EEflux outputs contributes materially to understanding ground-referenced ETₐ and can thus serve a valuable role in environments where the procurement of abundant, high-quality data is limited.

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.