Digital Agriculture, Smart Farming and Crop Monitoring

Weed segmentation is a fundamental task in precision agriculture, essential for targeted intervention and sustainable farming. However, achieving accurate segmentation remains challenging due to the high visual similarity between weeds and crops, as well as the ambiguous, fine-grained boundaries often present in complex field environments. To address this, we present WS-DINO, a novel weed segmentation network built upon the DINOv2 vision foundation model. Our framework introduces two key innovations: (1) a Feature Prior Module that leverages a Canny-guided refinement process to extract and inject fine-grained cues related to weed texture, morphology, and boundaries into specific blocks of the Vision Transformer; and (2) a Spatial Feature Fusion Module that leverages convolutional layers to generate multi-scale spatial features, which are then fused with the semantically rich token features from DINOv2, effectively compensating for the Transformer’s limitations in capturing local spatial details. Comprehensive evaluation on the public PhenoBench dataset shows that WS-DINO achieves an mIoU of 88.67% and outperforms the evaluated benchmark methods. Moreover, on the challenging MotionBlurred dataset, WS-DINO reaches 88.75% mIoU, showing stable performance under motion blur and degraded visual conditions. Full article

Accurate tomato ripeness detection is crucial for automated harvesting; however, complex greenhouse environments—characterized by dynamic light interference, foliage occlusion, and dense fruit overlapping—severely hinder detection performance and lead to frequent misdetections. This study aims to develop a high-precision, lightweight detection model that simultaneously addresses these three core challenges, thereby providing a technically deployable algorithmic foundation for resource-constrained agricultural edge devices. To this end, we propose CFD-DETR, a lightweight tomato ripeness detection model based on the RT-DETR architecture. The model incorporates a CAEfficientViT backbone for the lightweight extraction of multi-scale color and texture features. Furthermore, a Focused Efficient Additive Attention (FEAA) mechanism is integrated to capture fine-grained local ripening traits with minimal computational overhead. During feature reconstruction, a Deep Dynamic Upsampling (DwDySample) operator is utilized to preserve semantic integrity. Additionally, we designed the Wise-SIoU loss function, which dynamically penalizes low-quality samples to enhance boundary fitting and robustness against background noise. Experimental evaluations demonstrate that CFD-DETR achieves 90.2% mAP@0.5, outperforming the baseline model by 2.1 percentage points while significantly reducing the parameter count and computational complexity by 47.2% and 52.5%, respectively. Cross-dataset validation on the publicly available Laboro Tomato and RaUTD datasets confirms the model’s superior generalization capabilities. Overall, CFD-DETR provides a highly efficient and robust solution for real-time agricultural robotics. Full article

Modern agriculture must balance productivity with sustainability. In this context, unmanned aerial vehicles (UAVs) offer flexible, cost-effective tools for crop and soil monitoring in precision agriculture. This study aimed to evaluate the potential of UAV-borne RGB imagery, combined with vegetation indices and machine learning, to estimate surface soil properties and crop physiological traits in peanut (Arachis hypogaea) cultivation. A factorial field experiment with four varieties, two planting densities, and two tillage systems was monitored using high-resolution RGB orthomosaics acquired at key phenological stages. From these images, 17 RGB-based indices were computed and related to soil variables and crop traits using Spearman correlation and two regression algorithms: Random Forest (RF) and k-Nearest Neighbors (KNN). RF models outperformed KNN, with the Red Chromatic Coordinate (RCC) index achieving an R² of 0.87 for predicting soil organic matter content. Indices such as visible NDVI and the Green Vegetation Index also provided robust estimates of canopy condition and leaf chlorophyll. Overall, the results demonstrate that UAV RGB imagery, processed through simple vegetation indices and RF models, constitutes an effective, low-cost approach for monitoring key agronomic parameters in peanut farming. Full article

Soybean rust is a widespread and rapidly spreading fungal disease that poses a serious threat to both the yield and quality of soybeans. Traditional vegetation indices struggle to effectively assess disease severity across different infection stages, particularly during early or mild stages, due to weak spectral responses. In this study, we propose a soybean rust resistance identification model, RustNet-3D (Soybean Rust Disease Diagnosis Network-3D), which integrates a 3D deformable convolution module and a spectral dilated convolution module to achieve accurate classification of different disease severity levels. We further introduce a spectral feature band extraction module, iBSAM (improved Band Selection and Attention Module), which employs a modified depthwise separable convolution architecture. iBSAM incorporates bandwise independent convolution to enable individualized modeling of each spectral band. It also applies a hard thresholding strategy to remove redundant information, and integrates a channel attention mechanism to reinforce the model’s sensitivity to discriminative wavelengths. By modeling the temporal hyperspectral data of soybean rust, five highly sensitive spectral bands—581 nm, 605 nm, 596 nm, 609 nm, and 628 nm—are identified and subsequently used to construct the Soybean Rust Spectral Index (SRSI). Experimental results demonstrate that the RustNet-3D model achieves an overall accuracy (OA) of 92.74%, and the correlation coefficient between SRSI and disease severity reaches 0.89, validating the effectiveness of the selected spectral features. This study provides a rapid and accurate solution for soybean rust severity evaluation, offering a high-efficiency and automated approach for resistance identification and intelligent breeding. Full article

Reliable real-time detection and counting of tuna during distant-water deck operations is critical for automated catch monitoring but remains challenging due to strong illumination variation, background clutter, and frequent occlusion. This study proposes YOLOv10n-EMCNet, an improved lightweight detector based on YOLOv10n, integrating an ESC-based C2f enhancement in the backbone, a Multi-Branch and Scale Modulation-Fusion Feature Pyramid Network (SMFPN) in the neck, and a Convolutional Attention Fusion Module (CAFM) in the head for fine-grained representation and multi-scale feature fusion. An end-to-end detection–tracking–counting pipeline is further constructed by combining the detector with DeepSORT and an ROI-based de-duplication strategy. On the tuna dataset, YOLOv10n-EMCNet achieved 94.84% mAP@0.5, 65.29% mAP@0.5:0.95, and 91.77% recall with 6.5 GFLOPs. In addition, a controlled comparison among DeepSORT, ByteTrack, and OC-SORT on challenging videos showed that DeepSORT provided the best overall balance between counting accuracy, identity stability, and runtime efficiency. In shipboard video validation on four representative videos covering daytime high glare, nighttime low light, dense occlusion, and dense multi-target, the proposed pipeline achieved an average counting accuracy of 91.4%, with an average relative error of 8.62% and an average absolute error of 1.25 fish per video, while operating at approximately 30 FPS on an RTX 4090D platform. These results provide encouraging preliminary evidence that the proposed method can support automated tuna monitoring under representative shipboard conditions. Full article

As one of the world’s leading cotton-producing countries, China frequently experiences severe yield reductions due to crop diseases and pest infestations, with losses often exceeding 20%. Although computer vision models can identify diseased plants, they currently fail to connect visual symptoms to the diagnostic reasoning process used by agronomists. This leads to text descriptions that ignore the biological causes of the damage. To fix this, we built Multimodal Knowledge Graph-Enhanced Cross Vision Transformer-18-Dagger-408 and Text-to-Text Transfer Transformer for Cotton Disease and Pest Image Captioning (MKG-CottonCapT6), a model that uses a local knowledge database to generate professional diagnostic reports from field images. The technical core consists of a Multimodal Knowledge Graph (MMKG) containing 14 types of entities (such as Pathogens and Control Agents) and 12 types of relations. We use a Cross Vision-Transformer-18-Dagger-408 (CrossViT) encoder to capture both the overall leaf shape and microscopic details of pests. Through a Visual Entity Grounding (VEG) module, the model maps visual features directly to specific triplets in the graph. These triplets are then turned into text sequences and fused with image data in a Text-to-Text-Transfer-Transformer (T5) decoder. To train the model, we collected a dataset of cotton images paired with expert descriptions of lesions, colors, and affected plant parts. Tests show that MKG-CottonCapT6 performs better than standard models, reaching an Information-based Metric for Image Captioning (InfoMetIC) score of 72.6%. Results prove that by using a specific alignment loss (${\mathcal{L}}_{align}$), the model generates reports that correctly name the disease stage and recommend specific chemicals, such as Carbendazim or Triadimefon. This framework provides a practical tool for farmers to record and treat cotton diseases with high precision. Full article

Precise timing of rice harvesting is critical for ensuring grain yield and quality. Traditional manual evaluation methods are highly subjective and time-consuming, highlighting the critical demand for rapid, non-destructive approaches to estimate rice maturity. This study focused on cold-region japonica rice grown in Heilongjiang Province, aiming to develop and validate dual-scale (pot and field) maturity estimation models. For model development, canopy spectral data were collected using two complementary acquisition tools: a ground-based active sensor (CGMD402) and UAV-borne multispectral imagery. Four modeling algorithms—Linear Regression (LR), Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM)—were utilized, with input variables comprising single spectral indices (Normalized Difference Vegetation Index, NDVI; Ratio Vegetation Index, RVI) and composite spectral indices (Normalized Difference Maturity Ratio Vegetation Index, NDMRVI; Normalized Difference Pigment Ratio Vegetation Index, NDPRVI). At the pot scale, composite spectral indices showed stronger correlations with rice maturity than single indices. Among the four algorithms, the DT model with combined NDVI + RVI input yielded the optimal comprehensive performance, with a coefficient of determination (R²) of 0.957, a root mean square error (RMSE) of 0.064, and a relative error (RE) of 4.8% in the test set. At the field scale, NDVI and RVI both exhibited strong negative correlations with maturity (Spearman’s correlation coefficients of −0.76 and −0.79, respectively). While the RF model performed best in the training set (R² = 0.752), it was prone to overfitting; in contrast, Multiple Linear Regression (MLR, Ridge Regression) with NDVI + RVI combination demonstrated greater stability in the test set (R² = 0.515, RMSE = 0.116). Notably, composite spectral indices consistently outperformed single indices across all modeling algorithms, but their accuracy was comparable to the optimal single index combination model. To tackle the challenge of scaling models from pot to field conditions, this research developed a “modeling–validation–evaluation–scaling” framework and a four-indicator combined judgment criterion (ΔR²–ΔRMSE–ΔRE–SF). Quantitative analysis showed that the optimal pot-scale model suffered significant accuracy loss during cross-scale transfer: ΔR² = 0.447, ΔRMSE = 0.120, ΔRE = 22.84%, and Scale Transfer Factor (SF) = 2.875. A “regional calibration + residual correction” scheme was proposed, which is expected to reduce the transferred RMSE to below 0.12 and SF to 1.8–2.0. Overall, this research offers a reliable technical method for large-scale, non-destructive monitoring of rice maturity, which can facilitate data-driven precision harvesting decisions. Full article

Vertical farming requires precise environmental control, yet long-term multivariable analyses linking environmental dynamics and crop growth remain limited. This study analyzes a two-year operational dataset from a commercial vertical farm in South Korea to evaluate the suitability of advanced artificial intelligence models for harvest yield prediction. Conventional machine learning models and recent deep learning architectures were systematically benchmarked under identical conditions. Among them, the patch-based Transformer model achieved the highest predictive accuracy (R² = 0.942; RMSE = 5.81 g per plant). The variable-importance analysis revealed that daily light integral and CO₂ concentration were the dominant drivers of harvest yield variability, jointly accounting for more than 76% of total contribution. These findings demonstrate the effectiveness of Transformer-based architectures for long-term multivariate time series modeling and provide actionable insights for the data-driven optimization of vertical farming systems. Full article

Analyzing three-dimensional (3D) phenotypic parameters of maize seedlings is of significant importance for maize cultivation and selection. However, existing methods often struggle to balance cost, efficiency, and accuracy, particularly when capturing the complex morphology of seedlings characterized by slender stems. To address these issues, this study proposes a novel end-to-end automated framework for extracting phenotypes using only consumer-grade RGB cameras. The pipeline initiates with Instant-NGP to rapidly reconstruct dense point clouds, establishing the 3D data foundation for phenotypic extraction. Subsequently, we formulate a directed topological graph-based mechanism. By mathematically defining bifurcation constraints via vector analysis, this mechanism guides a depth-first traversal strategy to explicitly disentangle stem and leaf skeletons. Building upon these decoupled skeletons, organ-level point cloud segmentation is achieved through constraint-based expansion, followed by density-based spatial clustering (DBSCAN) to detect individual leaves. Algorithms combining point cloud geometry with 3D Euclidean distance are also implemented to calculate key phenotypes including plant height and stem width. Finally, single-leaf skeleton fitting is used to estimate leaf length, and principal component analysis (PCA) is adopted to determine the stem–leaf angle, realizing the comprehensive automatic extraction of maize seedling phenotypes. Experiments show that the proposed method achieves high accuracy in extracting key phenotypic parameters. The mean relative errors for plant height, stem width, leaf length, stem-leaf angle, and leaf area are 0.76%, 2.93%, 1.26%, 2.13%, and 3.33%, respectively. Compared with existing methods as far as we know, the proposed method significantly improves extraction efficiency by reducing the processing time per plant to within 5 min while maintaining such high accuracy. Full article

Detecting rice leaf diseases in real-world field environments remains challenging due to varying lesion sizes, diverse lesion morphologies, complex backgrounds, and the limited availability of high-quality annotated datasets. Existing detection models often suffer from performance degradation under these conditions, particularly when training data lack sufficient diversity and structural realism. To address these challenges, this paper proposes a Latent Diffusion Inpainting (LDI) data augmentation method and an improved lightweight detection model, LGH-YOLOv12n. Unlike conventional diffusion-based augmentation methods that generate full images or random patches, LDI performs category-aware latent inpainting, synthesizing realistic lesion patterns by jointly conditioning on background context and disease categories, thereby enhancing data diversity while preserving scene consistency. Furthermore, LGH-YOLOv12n improves upon the YOLOv12n baseline by introducing GSConv in the backbone to reduce channel redundancy and enhance lesion localization, and integrating Hierarchical Multi-head Attention (HMHA) into the neck network to better distinguish disease features from complex field backgrounds. Experimental results demonstrate that LGH-YOLOv12n achieves an F1 of 86.1% and an mAP@50 of 88.3%, outperforming the YOLOv12n model trained without data augmentation by 3.3% and 5.0%, respectively. Moreover, when trained on the LDI-augmented dataset, LGH-YOLOv12n consistently outperforms YOLOv8n, YOLOv10n, YOLOv11n, and YOLOv12n, with mAP@50 improvements of 4.6%, 5.2%, 1.9%, and 2.1%, respectively. These results indicate that the proposed LDI augmentation and LGH-YOLOv12n model provide an effective and robust solution for rice leaf disease detection in complex field environments. Full article

The non-destructive and chemical-free determination of anthocyanin content in single maize kernels is of great importance for plant-breeding programs. Previous studies have mainly relied on Near-Infrared Reflectance (NIR) spectroscopy and color-based approaches, often using conventional or randomly selected modeling techniques. In this study, an Automated Machine Learning (AutoML) framework was employed to predict anthocyanin content using spectral and digital image data obtained from individual maize kernels measured in two orientations (embryo-up and embryo-down). Forty colored maize genotypes representing diverse phenotypic characteristics were analyzed. Digital images were acquired in RGB, HSV, and LAB color spaces, together with NIR spectral data, from a total of 200 kernels. Reference anthocyanin content was determined using a colorimetric method. Ten datasets were constructed by combining different color space and spectral features and were grouped according to kernel orientation. AutoML was used to evaluate nine machine learning algorithms, while Partial Least Squares Regression (PLSR) served as a classical benchmark method, resulting in the development of 1918 predictive models. Kernel orientation had a notable effect on model performance and outlier detection. The best predictions were obtained from the RGB dataset for embryo-up kernels and from the combined RGB+HSV+LAB+NIR dataset for embryo-down kernels. Overall, AutoML outperformed conventional modeling by automatically identifying optimal algorithms for specific data structures, demonstrating its potential as an efficient screening tool for anthocyanin content at the single-kernel level. Full article

Accurate measurement of plant height in leafy vegetables is challenging due to their short stature, high planting density, and severe canopy occlusion during later growth stages. These factors often limit the reliability of single-plant monitoring across the full growth cycle in open-field environments. To address this, we propose a multi-temporal point cloud alignment method for accurate plant height measurement, focusing on Choy Sum (Brassica rapa var. parachinensis). The method estimates plant height by calculating the vertical distance between the canopy and the ground. Multi-temporal point cloud maps are reconstructed using an enhanced Oriented FAST and Rotated BRIEF–Simultaneous Localization and Mapping (ORB-SLAM3) algorithm. A fixed checkerboard calibration board, leveled using a spirit level, ensures proper vertical alignment of the Z-axis and unifies coordinate systems across growth stages. Ground and plant points are separated using the Excess Green (ExG) index. During early growth stages, when the soil is minimally occluded, ground point clouds are extracted and used to construct a high-precision reference ground model through Cloth Simulation Filtering (CSF) and Kriging interpolation, compensating for canopy occlusion and noise. In later growth stages, plant point cloud data are spatially aligned with this reconstructed ground surface. Individual plants are identified using an improved Euclidean clustering algorithm, and consistent measurement regions are defined. Within each region, a ground plane is fitted using the Random Sample Consensus (RANSAC) algorithm to ensure alignment with the X–Y plane. Plant height is then determined by the elevation difference between the canopy and the interpolated ground surface. Experimental results show mean absolute errors (MAEs) of 7.19 mm and 18.45 mm for early and late growth stages, respectively, with coefficients of determination (R²) exceeding 0.85. These findings demonstrate that the proposed method provides reliable and continuous plant height monitoring across the full growth cycle, offering a robust solution for high-throughput phenotyping of leafy vegetables in field environments. Full article

Timely and accurate prediction of crop traits is critical for precision breeding and regional agricultural production. Previous studies have primarily focused on single crop yield traits, neglecting other crop traits and variety-specific analyses. To address this issue, we employed a Meta-Hybrid Regression Ensemble (MHRE) approach by using multiple machine learning (ML) approaches as base learners, integrating regional multi-year, multi-variety crop field trials with satellite remote sensing indices, meteorological and phenological data to predict major crop traits. Results demonstrated MHRE’s optimal performance for rice and cotton, significantly outperforming individual models (RF, XGBoost, CatBoost, and LightGBM). Specifically, for rice crop, MHRE achieved highest accuracy for yield trait (R² = 0.78, RMSE = 0.59 t ha⁻¹) compared to the best individual model (XGBoost: R² = 0.76, RMSE = 0.61 t ha⁻¹); traits like effective spike also showed strong predictability (R² = 0.64, RMSE = 27.81 10,000·spike ha⁻¹). Similarly, for cotton, MHRE substantially improved yield trait prediction (R² = 0.82, RMSE = 0.33 t ha⁻¹) compared to the best individual model (RF: R² = 0.77, RMSE = 0.36 t ha⁻¹); bolls per plant accuracy was highest (R² = 0.93, RMSE = 2.27 bolls plant⁻¹). Moreover, rigorous validation confirmed that crop-specific MHRE models are robust across five rice and three cotton varietal groups and are applicable across six distinct regions in China. Furthermore, we applied the SHAP (SHapley Additive exPlanations) method to analyze the growth stages and key environmental factors affecting major traits. Our study illustrates a practical framework for regional-scale crop traits prediction by fusing multi-source data and ensemble machine learning, offering new insights for precision agriculture and crop management. Full article

This study presents a hybrid recurrent neural network (RNN) approach for greenhouse microclimate prediction, combining a mechanistic model with an Elman network. The research addresses the gap in systematic comparisons between hybrid RNN and feedforward neural network (FFNN) architectures for greenhouse climate forecasting. Different network structures with 1, 2, 3, 5, and 7 hidden layers were evaluated using mean absolute percentage error (MAPE), mean square error (MSE), and coefficient of determination (R²). Results demonstrate that hybrid RNNs significantly outperform FFNNs in predicting indoor temperature, with the 2-hidden-layer configuration achieving the best performance (R² = 0.897). For relative humidity prediction, both networks showed comparable results. The hybrid RNN with 3 hidden layers exhibited optimal performance during training, while simpler configurations proved more effective during testing. The integration of mechanistic knowledge with neural networks enhances prediction accuracy, providing a reliable tool for greenhouse climate control systems. These findings contribute to smart agriculture by offering an efficient computational approach for microclimate management. Full article

Digital agriculture and smart farming require crop health monitoring methods that balance detection accuracy with computational cost. Rice leaf diseases threaten yield, while field images often contain small multi-scale lesions, variable illumination and cluttered backgrounds. This paper investigates SCD-YOLOv11n, a lightweight detector designed with these constraints in mind. The model replaces the YOLOv11n backbone with a StarNet backbone and integrates a C3k2-Star module to enhance fine-grained, multi-scale feature extraction. A Detail-Strengthened Cross-scale Detection (DSCD) head is further introduced to improve localization of small lesions. On this architecture, we design a DepGraph-based mixed group-normalization pruning rule and apply channel-wise feature distillation to recover performance after pruning. Experiments on a public rice leaf disease dataset show that the compressed model requires 1.9 MB of storage, achieves 97.4% mAP@50 and 76.2% mAP@50:95, and attains a measured speed of 184 FPS under the tested settings. These results provide a quantitative reference for designing lightweight object detectors for rice disease monitoring in digital agriculture scenarios. Full article

Agriculture faces growing pressure to optimize water use, particularly in woody perennial crops where irrigation systems are installed once and seldom redesigned despite changes in canopy structure, soil conditions, or plant mortality. Such static layouts may accumulate inefficiencies over time. This study introduces a decision support system (DSS) that evaluates the hydraulic adequacy of existing irrigation systems using two new concepts: the Resource Overutilization Ratio (ROR) and the Irrigation Ecolabel. The ROR quantifies the deviation between the actual discharge of an installed irrigation network and the theoretical discharge required from crop water needs and user-defined scheduling assumptions, while the ecolabel translates this value into an intuitive A+++–D scale inspired by EU energy labels. Crop water demand was estimated using the FAO-56 Penman–Monteith method and adjusted using canopy cover derived from UAV-based canopy height models. A vineyard case study in Galicia (Spain) serves an example to illustrate the potential of the DSS. Firstly, using a fixed canopy cover, the FAO-based workflow indicated moderate oversizing, whereas secondly, UAV-derived canopy measurements revealed substantially higher oversizing, highlighting the limitations of non-spatial or user-estimated canopy inputs. This contrast (A+ vs. D rating) illustrates the diagnostic value of integrating high-resolution geospatial information when canopy variability is present. The DSS, released as open-source software, provides a transparent and reproducible framework to help farmers, irrigation managers, and policymakers assess whether existing drip systems are hydraulically oversized and to benchmark system performance across fields or management scenarios. Rather than serving as an irrigation scheduler, the DSS functions as a standardized diagnostic tool for identifying oversizing and supporting more efficient use of water, energy, and materials in perennial cropping systems. Full article

Accurate, high-throughput estimation of Above-Ground Biomass (AGB), a key predictor of yield, is a critical goal in rapeseed breeding. However, this is constrained by two key challenges: (1) traditional measurement is destructive and laborious, and (2) modern deep learning approaches require vast, costly labeled datasets. To address these issues, we present a data-efficient deep learning framework using smartphone-captured top-down RGB images for AGB estimation (Fresh Weight, FW, and Dry Weight, DW). Our approach utilizes a two-stage strategy where a Vision Transformer (ViT) backbone is first pre-trained on a large, aggregated dataset of diverse, non-rapeseed public plant datasets using the DINOv2 self-supervised learning (SSL) method. Subsequently, this pre-trained model is fine-tuned on a small, custom-labeled rapeseed dataset (N = 833) using a Multi-Task Learning (MTL) framework to simultaneously regress both FW and DW. This MTL approach acts as a powerful regularizer, forcing the model to learn robust features related to the 3D plant structure and density. Through rigorous 5-fold cross-validation, our proposed model achieved strong predictive performance for both Fresh Weight (Coefficient of Determination, R² = 0.842) and Dry Weight (R² = 0.829). The model significantly outperformed a range of baselines, including models trained from scratch and those pre-trained on the generic ImageNet dataset. Ablation studies confirmed the critical and synergistic contributions of both domain-specific SSL (vs. ImageNet) and the MTL framework (vs. single-task training). This study demonstrates that an SSL+MTL framework can effectively learn to infer complex 3D plant attributes from 2D images, providing a robust and scalable tool for non-destructive phenotyping to accelerate the rapeseed breeding cycle. Full article

Vibration technology is a commonly used method for detaching citrus fruits, and studying the vibrational properties of citrus trees can helpfully improve the effectiveness of vibrating harvesters. The existing mechanical properties of wood have shown that tree materials in nature have transversely isotropic characteristics instead of isotropic ones. However, in the study of the vibrational characteristics of fruit trees, the material of fruit trees is still defined as isotropic. This paper presents a vibration simulation approach for transversely isotropic citrus trees using the Frenet frame to reveal the true physical characteristics of fruit trees. A comparison was carried between the vibration spectrum obtained from experiments on citrus branches and the simulated spectra from transversely isotropic and isotropic material models. The findings reveal that the simulated vibration spectra for the transversely isotropic citrus branch can closely match the experimentally measured spectra. This supports the effectiveness of simulation method for transversely isotropic citrus trees. Furthermore, simulations of the vibration frequency response characteristics for citrus trees with both transversely isotropic and isotropic materials showed notable differences in their spectra. The proposed simulation method for transversely isotropic citrus trees offers a more precise depiction of their actual vibrational properties. This simulation technique is crucial for optimizing the parameters of citrus harvesting equipment, leading to enhanced machine performance. Full article

Rice lodging is a major agricultural disaster that reduces yield and quality. Accurate lodging detection and causal analysis are essential for disaster mitigation and precision management. To overcome the limited coverage and low automation of conventional approaches, we propose MSR-LodfNet, an enhanced semantic-segmentation model driven by multi-scale remote-sensing imagery, enabling high-precision lodging mapping from regional to field scales. The study selected 13 state-owned farms in Jiansanjiang, Heilongjiang Province, and jointly used PlanetScope satellite images (3 m) and UAV images (0.2 m) to build an integrated workflow of “satellite macro-monitoring, UAV fine verification, and agronomic factor coupling analysis.” The model synergistically optimizes WFNet, DenseASPP multi-scale context enhancement, and Condensed Attention, markedly improving feature extraction and boundary recognition under multi-source imagery. Experimental results show that the model achieves mIoU 84.34% and mPA 93.31% on UAV images and mIoU 81.96% and mPA 90.63% on PlanetScope images, demonstrating excellent cross-scale adaptability and stability. Causal analysis shows that the high-EVI range is significantly positively correlated with lodging probability; its risk is about 6 times that of the low-EVI range, and the lodging probability of direct-seeded rice is about 2.56 times that of transplanted rice, indicating that it may be associated with a higher lodging risk. The results demonstrate that multi-scale remote sensing combined with agronomic parameters can effectively support the mechanism analysis of lodging disasters, providing a quantitative basis and technical reference for precision rice management and lodging-resistant breeding. Full article

To address the pressing challenges facing global agriculture—including resource constraints, structural labour shortages, and climate change adaptation—exploring pathways for digital transformation is crucial for safeguarding regional food security and advancing sustainable agricultural development. Taking China’s Yangtze River Economic Belt as a case study, this research aims to dissect the interplay between the digital economy, new-quality agricultural productivity, and agricultural modernisation. Utilising panel data from 11 provinces and municipalities spanning 2013–2023, the study employs an entropy-weighted approach to construct a composite indicator system for these three core variables. Panel data analysis comprehensively employs random effects models, mediation effect tests, robustness checks, and heterogeneity analyses. Empirical results indicate that the digital economy exerts a significant positive driving effect on new-quality agricultural productivity. Mediation tests further reveal that agricultural modernisation plays a crucial mediating role in this relationship. Heterogeneity analysis finds that the promotional effect of the digital economy exhibits distinct regional gradient characteristics, being most pronounced in growth zones, followed by leading zones, and weakest in starting zones. These findings support the formulation of differentiated agricultural digitalization policies: Leading areas should focus on deep integration of AI and agricultural big data; growth zones require investments in scaling intelligent irrigation and UAV plant protection; and start-up areas should prioritize digital infrastructure and large-scale farmer digital literacy training to establish transformation foundations. Full article

Temperature is a key driver of microbial metabolism, yet non-invasive methods for quantifying microbially generated heat in complex environments remain limited. Here, we present a low-cost digital temperature sensing system integrated into an Arduino-controlled data acquisition setup to monitor microbial activity in stratified Winogradsky columns, which are self-contained sediment microcosms that reproduce natural oxygen and sulfide gradients. Localized temperature differences of up to 0.55 ± 0.04 °C were detected between aerobic and anaerobic layers, consistent with microbial heat generation in active sediment zones. Short-term insulation experiments further amplified these effects, demonstrating that microbial thermogenesis can serve as a reliable proxy for metabolic activity. Compared with infrared thermography or isothermal microcalorimetry, the proposed approach is simple, cost-effective, and compatible with aqueous and stratified systems. The method enables real-time, non-invasive observation of microbial metabolic dynamics and establishes a framework for continuous thermal monitoring in living environmental microcosms. Full article

Common vetch (Vicia sativa L.) is a cool-season annual legume cultivated for grain and forage, valued for its high nutrient content, broad edaphoclimatic adaptability, and suitability for crop rotations. Physical seed attributes are critical for variety classification, quality evaluation, and breeding selection. This study aimed to characterize the nutritional composition, mineral contents, and physical attributes of nine common vetch varieties and to assess the feasibility of binary variety classification using supervised machine learning (ML). Proximate analyses (e.g., crude protein, tannin), macro/micro minerals, and morpho-physical seed descriptors were determined. Multivariate and discriminant analyses were conducted. Binary classifiers were developed with a multilayer perceptron (MLP) and random forest (RF) under stratified 10-fold cross-validation. The highest values were observed for crude protein (22.66%, Alper), ADF (11.36%, Alınoğlu), NDF (16.47%, Alperen), and tannin (3.12%, Alınoğlu). For mineral profiles, Alper, Ankara Moru, and Doruk emerged as prominent varieties. In pairwise discrimination, Ankara Moru vs. Ayaz achieved 89% (MLP) and 90% (RF) accuracy, followed by Ankara Moru vs. Özveren with 88% (MLP) and 90.50% (RF). These results demonstrate that MLP and RF can classify common vetch varieties from physical attributes with high reliability. Integrating compositional, mineral, and morpho-physical data with supervised learning provides an objective, low-cost pathway for variety identification. The approach has direct implications for quality assessment, planting system design, and breeding. Future work should expand datasets, incorporate color-rich/hyperspectral cues, and compare feature-based models with domain-adapted deep learning on larger, multi-site collections. Full article

Most fruit classification studies rely on color-based features, but shape-based analysis provides a promising alternative for distinguishing subtle variations within the same variety. Tomato shape classification is challenging due to irregular contours, variable imaging conditions, and difficulty in extracting consistent geometric features. In this study, we propose an efficient and structured workflow to address these challenges through contour-based analysis. The process begins with the application of a Mask Region-based Convolutional Neural Network (Mask R-CNN) model to accurately isolate tomatoes from the background. Subsequently, the segmented tomatoes are extracted and encoded using Elliptic Fourier Descriptors (EFDs) to capture detailed shape characteristics. These features are used to train a range of machine learning models, including Support Vector Machine (SVM), Random Forest, One-Dimensional Convolutional Neural Network (1D-CNN), and Bidirectional Encoder Representations from Transformers (BERT). Experimental results observe that the Random Forest model achieved the highest accuracy of 79.4%. This approach offers a robust, interpretable, and quantitative framework for tomato shape classification, reducing manual labor and supporting practical agricultural applications. Full article

This article aims to improve the real-time monitoring accuracy of the loss rate for grain combine harvesters by optimizing the sensor-sensitive plate structure, thereby addressing the problem of low detection efficiency in existing equipment. Based on Kirchhoff’s thin plate theory, COMSOL 6.0 software was utilized to conduct modal analysis and single-grain impact tests on rectangular and circular sensing plates fabricated from three materials: stainless steel, aluminum alloy, and cupronickel. The circular stainless steel sensing plate was identified as the optimal structure, whose natural frequency and sensitivity significantly outperform those of traditional rectangular plates. By integrating a signal processing strategy based on FFT (Fast Fourier Transform) spectrum analysis (band-pass filtering: 1.0~3.0 kHz, voltage threshold: 3.5 V) and a high-level duration counting algorithm, the system effectively distinguishes between grains and impurities and resolves the counting errors caused by multi-grain impacts and secondary rebounds. Field experiments demonstrate that the developed sensor exhibits strong anti-interference ability and high measurement accuracy, providing reliable technical support for reducing harvesting losses. Full article

With the aim of tuning the complexity of traditional image processing parameters, the automated extraction of spike phenotypes based on the fusion of YOLOv11 and image processing was proposed, with winter wheat in Lingcheng District, Dezhou City, Shandong Province as the research object. The keypoint detection of spikes was studied, and the integration of FocalModulation and TADDH modules improved the feature extraction ability, solved the problems of light interference and spike awn occlusion under the complex environment in the field, and the detection accuracy of the improved model reached 96.00%, and the mAP50 reached 98.70%, which were 6.6% and 2.8% higher than that of the original model, respectively. On this basis, this paper integrated morphological processing and a watershed algorithm, and innovatively constructed an integrated extraction method for spike length, spike width, and number of grains in the spike to realize the automated extraction of phenotypic parameters in the spike. The experimental results show that the extraction accuracy of spike length, spike width, and number of grains reached 98.08%, 96.21%, and 93.66%, respectively, which provides accurate data support for wheat yield prediction and genetic breeding research, and promotes the development of intelligent agricultural phenomic technology innovation. Full article

As global agriculture shifts to intelligence and precision, crop attribute detection has become foundational for intelligent systems (harvesters, UAVs, sorters). It enables real-time monitoring of key indicators (maturity, moisture, disease) to optimize operations—reducing crop losses by 10–15% via precise cutting height adjustment—and boosts resource-use efficiency. This review targets harvesting-stage and in-field monitoring for grains, fruits, and vegetables, highlighting practical technologies: near-infrared/Raman spectroscopy (non-destructive internal attribute detection), 3D vision/LiDAR (high-precision plant height/density/fruit location measurement), and deep learning (YOLO for counting, U-Net for disease segmentation). It addresses universal field challenges (lighting variation, target occlusion, real-time demands) and actionable fixes (illumination compensation, sensor fusion, lightweight AI) to enhance stability across scenarios. Future trends prioritize real-world deployment: multi-sensor fusion (e.g., RGB + thermal imaging) for comprehensive perception, edge computing (inference delay < 100 ms) to solve rural network latency, and low-cost solutions (mobile/embedded device compatibility) to lower smallholder barriers—directly supporting scalable precision agriculture and global sustainable food production. Full article

Rice leaf diseases are critical factors affecting rice yield and quality, and their effective detection is crucial for ensuring stable production. However, existing detection models exhibit limitations in capturing irregular and fine-grained lesion features and are susceptible to interference from complex backgrounds. To address these challenges, this study proposes an Efficient Attention-Guided Network (EAG-YOLOv11n) for rice leaf disease detection. Specifically, an EMA-C3K2 module is proposed to enhance the network’s feature extraction capability. It integrates Efficient Multi-Scale Attention (EMA) into the shallow C3K2 layers, enabling the network to extract richer low-level feature representations. In addition, a Global Local Complementary Attention module (GLC-PSA) is proposed, which integrates a Local Importance Attention (LIA) branch to enhance the local feature representation of the original C2PSA. This design strengthens the perception of lesion regions while effectively suppressing background interference. Furthermore, an Adaptive Threshold Focal Loss (ATFL) is employed to guide the optimization of model parameters during training, alleviating sample imbalance and adaptively emphasizing the learning of challenging samples. Experimental results demonstrate that EAG-YOLOv11n achieves a mean Average Precision (mAP) of 87.3%, representing a 2.7% improvement over the baseline. Furthermore, compared with existing mainstream detection methods, including RT-DETR-L, YOLOv7tiny, YOLOv8n, YOLOv9tiny, YOLOv10n, and YOLOv12n, EAG-YOLOv11n improves mAP by 4.2%, 4.3%, 1.9%, 1.1%, 8.7%, and 2.9%, respectively. Overall, these results highlight its superior effectiveness in rice leaf disease detection, providing reliable technical support for stable yield and sustainable agricultural development. Full article

In the context of global agricultural modernization, the early and accurate detection of sugarcane leaf diseases is critical for ensuring stable sugar production. However, existing deep learning models still face significant challenges in complex field environments, such as blurred lesion edges, scale variation, and limited generalization capability. To address these issues, this study constructs an efficient recognition model for sugarcane disease detection, named CaneFocus-Net, specifically designed for precise identification of sugarcane leaf diseases. Based on a single-stage detection architecture, the model introduces a lightweight cross-stage feature fusion module (CP) to optimize feature transfer efficiency. It also designs a module combining a channel-spatial adaptive calibration mechanism with multi-scale pooling aggregation to enhance the backbone network’s ability to extract multi-scale lesion features. Furthermore, by expanding the high-resolution shallow feature layer to enhance sensitivity toward small-sized targets and adopting a phased adaptive nonlinear optimization strategy, detection and localization accuracy along with convergence efficiency have been further improved. Test results on public datasets demonstrate that this method significantly enhances recognition performance for fuzzy lesions and multi-scale targets while maintaining high inference speed. Compared to the baseline model, precision, recall, and mean average precision (mAP50 and mAP50-95) improved by 1.9%, 4.6%, 1.5%, and 1.4%, respectively, demonstrating strong generalization capabilities and practical application potential. This provides reliable technical support for intelligent monitoring of sugarcane diseases in the field. Full article

To address the issues of signal loss and insufficient accuracy of traditional GNSS (Global Navigation Satellite System) navigation in agricultural machinery sheds and farm access road environments, this paper proposes a high-precision mapping method for such complex environments and a real-time localization system for agricultural vehicles. First, an autonomous navigation system was developed by integrating multi-sensor data from LiDAR (Light Laser Detection and Ranging), GNSS, and IMU (Inertial Measurement Unit), with functional modules for mapping, localization, planning, and control implemented within the ROS (Robot Operating System) framework. Second, an improved LeGO-LOAM algorithm is introduced for constructing maps of machinery sheds and farm access roads. The mapping accuracy is enhanced through reflectivity filtering, ground constraint optimization, and ScanContext-based loop closure detection. Finally, a localization method combining NDT (Normal Distribution Transform), IMU, and a UKF (Unscented Kalman Filter) is proposed for tracked grain transport vehicles. The UKF and IMU measurements are used to predict the vehicle state, while the NDT algorithm provides pose estimates for state update, yielding a fused and more accurate pose estimate. Experimental results demonstrate that the proposed mapping method reduces APE (absolute pose error) by 79.99% and 49.04% in the machinery sheds and farm access roads environments, respectively, indicating a significant improvement over conventional methods. The real-time localization module achieves an average processing time of 26.49 ms with an average error of 3.97 cm, enhancing localization accuracy without compromising output frequency. This study provides technical support for fully autonomous operation of agricultural machinery. Full article

Labor shortages in seedling nurseries, particularly in manual inspection and replanting, hinder operational efficiency despite advancements in automation. This study aims to develop a cost-effective, GPU-free machine vision system to automate the detection of deficient seedlings in plug trays, specifically for small-scale nursery operations. The proposed Deficiency Detection and Replanting Positioning (DDRP) machine integrates low-cost components including an Intel RealSense Depth Camera D435, Raspberry Pi 4B, stepper motors, and a programmable logic controller (PLC). It utilizes OpenCV’s Haar cascade algorithm, HSV color space conversion, and Otsu thresholding to enable real-time image processing without GPU acceleration. The proposed Deficiency Detection and Replanting Positioning (DDRP) machine integrates low-cost components including an Intel RealSense Depth Camera D435, Raspberry Pi 4B, stepper motors, and a programmable logic controller (PLC). It utilizes OpenCV’s Haar cascade algorithm, HSV color space conversion, and Otsu thresholding to enable real-time image processing without GPU acceleration. Under controlled laboratory conditions, the DDRP-Machine achieved high detection accuracy (96.0–98.7%) and precision rates (82.14–83.78%). Benchmarking against deep-learning models such as YOLOv5x and Mask R-CNN showed comparable performance, while requiring only one-third to one-fifth of the cost and avoiding complex infrastructure. The Batch Detection (BD) mode significantly reduced processing time compared to Continuous Detection (CD), enhancing real-time applicability. The DDRP-Machine demonstrates strong potential to improve seedling inspection efficiency and reduce labor dependency in nursery operations. Its modular design and minimal hardware requirements make it a practical and scalable solution for resource-limited environments. This study offers a viable pathway for small-scale farms to adopt intelligent automation without the financial burden of high-end AI systems. Future enhancements, adaptive lighting and self-learning capabilities, will further improve field robustness and including broaden its applicability across diverse nursery conditions. Full article

Accurate and rapid acquisition of soil texture information is crucial to evaluating soil quality, formulating soil and water conservation strategies, and guiding agricultural resource management. Compared with traditional machine learning methods, convolutional neural networks (CNNs) demonstrate superior accuracy in soil texture prediction. To overcome the limitations of existing lightweight models in spectral modeling, such as insufficient single-scale feature representation, limited channel utilization, and branch redundancy, and to meet the demand for lightweight architectures, we propose a novel dynamic feature modeling approach: Multi-scale Routing Attention Network (MSRA-Net). MSRA-Net integrates grouped multi-scale convolutions with an intra-group Efficient Channel Attention (gECA) mechanism, combined with a multi-scale weighting strategy based on a Branch Routing Attention (BRA) mechanism, thereby enhancing inter-channel feature interaction and improving the model’s ability to capture complex spectral patterns. Furthermore, we introduce a multi-task learning variant, MSRA-MT, which employs uncertainty dynamic weighting to balance gradients magnitude across tasks, thereby improving both stability and predictive accuracy. Experimental results on the LUCAS and ICRAF datasets demonstrate that the MSRA-MT model consistently outperforms baseline models in terms of performance and robustness ($RMS{E}_{mean}$ = 9.190 and $RMS{E}_{mean}$ = 8.189 for ICRAF and LUCAS, respectively). Prior knowledge-based soft constraints may hinder optimization by amplifying intrinsic noise, rather than improving learning effectiveness. Full article

This study presents a robust and extensible hybrid classification framework for accurately detecting diseases in citrus leaves by integrating transfer learning-based deep learning models with classical machine learning techniques. Features were extracted using advanced pretrained architectures—DenseNet201, ResNet50, MobileNetV2, and EfficientNet-B0—and refined via the minimum redundancy maximum relevance (mRMR) method to reduce redundancy while maximizing discriminative power. These features were classified using support vector machines (SVMs), ensemble bagged trees, k-nearest neighbors (kNNs), and neural networks under stratified 10-fold cross-validation. On the lemon dataset, the best configuration (DenseNet201 + SVM) achieved 94.1 ± 4.9% accuracy, 93.2 ± 5.7% F1 score, and a balanced accuracy of 93.4 ± 6.0%, demonstrating strong and stable performance. To assess external generalization, the same pipeline was applied to mango and pomegranate leaves, achieving 100.0 ± 0.0% and 98.7 ± 1.5% accuracy, respectively—confirming the model’s robustness across citrus and non-citrus domains. Beyond accuracy, lightweight models such as EfficientNet-B0 and MobileNetV2 provided significantly higher throughput and lower latency, underscoring their suitability for real-time agricultural applications. These findings highlight the importance of combining deep representations with efficient classical classifiers for precision agriculture, offering both high diagnostic accuracy and practical deployability in field conditions. Full article

Phaeozem, which is recognized as one of the world’s most fertile soils, derives much of its productivity from soil organic matter (SOM). Because SOM strongly influences fertility, soil structure, and ecological functions, it is the SOM content that must be rapidly and accurately determined to ensure sustainable soil management. Traditional chemical methods are reliable but time-consuming and labor-intensive, which makes them inadequate for large-scale applications. Hyperspectral reflectance, which is highly sensitive to SOM variations, provides a non-destructive alternative for rapid SOM grading. This study proposes an ensemble learning strategy model based on phaeozem hyperspectral reference data for the rapid grading and detection of SOM content. First, the SOM content of the collected phaeozem samples was determined using the potassium dichromate volumetric method. Next, hyperspectral reflectance data of the phaeozem were collected using a hyperspectral imaging sensor, with a wavelength range of 400–1000 nm. Furthermore, stacking models were constructed by modifying the internal structure, with five classifiers (MLP, SVC, DTree, XGBoost, kNN) as the L1 layer. Then, global optimization was performed using the simulated annealing algorithm. Through comparative analysis, the LSVM-stacking model demonstrated the highest accuracy and generalization capabilities. The results demonstrated that the LSVM-stacking model not only achieved the highest overall accuracy (0.9488 on the independent test set) but also improved the classification accuracy of “Category 1” samples to 1.0. Compared with other models, this framework significantly improved generalization ability and robustness. It is therefore evident that combining hyperspectral reflectance with improved stacking strategies provides a novel and effective approach for the rapid grading and detection of SOM in phaeozem. Full article

Existing rice harvesting models often lack depth or extensibility and are limited in their scope across the agriculture value chain, from crop planting to postharvest handling. A multi-agent system (MAS) offers flexibility and scalability and supports the simulation and modeling of complex real-world scenarios. This paper introduces a novel approach utilizing an MAS to simulate rice harvesting operations (including additional pre- and post-harvesting operations). Initially, a generic MAS was created, and it was then subsequently adapted to the agricultural context of rice farming in Central Japan. The localized MAS consists of agents such as weather, farm, rice centers, fields, crops and multiple agriculture machinery. Additionally, the introduced MAS environment is based on a discrete event simulation that enables communication across various independent agents. The system includes different harvesting schedule policies which determine the harvesting order for multiple paddy fields on specific days. The system was evaluated through two distinct experiments: (i) ‘Model Verification Simulation’, which successfully demonstrated the replication of actual historical farming practices, and (ii) ‘Operational Efficiency Simulation’, which compared the overall farm efficiency under different scheduling policies as well as different environmental conditions (e.g., rainfall). The simulation successfully generated a dataset containing traits and performance indicators that replicate the patterns observed in real-world data, while also approximating the operational behaviors and workflows of actual rice harvesting systems. Future studies could further evaluate the model’s robustness to confirm its practical applicability. Full article

Soil moisture prediction is a key parameter for effective irrigation scheduling and water use efficiency. However, accurate long-term prediction remains challenging, as most existing models excel in short- to medium-term prediction but struggle to capture the complex temporal dependencies and non-linear interactions of soil moisture variables over extended horizons. This study proposes a hybrid soil moisture prediction method, integrating a long short-term memory (LSTM) network and extreme gradient boosting (XGBoost) model for multistep soil moisture prediction at 24 h, 72 h, and 168 h horizons. The LSTM captures temporal dependencies and extracts high-level features from the dataset, which are then used by XGBoost for final predictions. The study uses real-world data from the D.A.T.A (Demonstrating Applied Technology in Agriculture) research farm at ABAC (Abraham Baldwin Agricultural College) Tifton, GA, USA, utilizing watermark soil moisture sensors and weather station’s data installed on the farm. Results show that the proposed method outperforms other hybrid models, achieving R² values of 98.67%, 98.54%, and 98.56% for 24, 72, and 168 h predictions, respectively. The study findings highlight that LSTM-XGBoost offers a precise long-term soil moisture prediction, making it a practical tool for real-time irrigation scheduling, enhancing water use efficiency in precision agriculture. Full article

Drones have been widely used in precision agriculture to capture high-resolution images of crops, providing farmers with advanced insights into crop health, growth patterns, nutrient deficiencies, and pest infestations. Although several machine and deep learning models have been proposed for plant stress and disease detection, their performance regarding accuracy and computational time still requires improvement, particularly under limited data. Therefore, this paper aims to address these challenges by conducting a comparative analysis of three State-of-the-Art object detection deep learning models: YOLOv8, RetinaNet, and Faster R-CNN, and their variants to identify the model with the best performance. To evaluate the models, the research uses a real-world dataset from potato farms containing images of healthy and stressed plants, with stress resulting from biotic and abiotic factors. The models are evaluated under limited conditions with original data of size 360 images and expanded conditions with augmented data of size 1560 images. The results show that YOLOv8 variants outperform the other models by achieving larger mAP@50 values and lower inference times on both the original and augmented datasets. The YOLOv8 variants achieve mAP@50 ranging from 0.798 to 0.861 and inference times ranging from 11.8 ms to 134.3 ms, while RetinaNet variants achieve mAP@50 ranging from 0.587 to 0.628 and inference times ranging from 118.7 ms to 158.8 ms, and Faster R-CNN variants achieve mAP@50 ranging from 0.587 to 0.628 and inference times ranging from 265 ms to 288 ms. These findings highlight YOLOv8’s robustness, speed, and suitability for real-time aerial crop monitoring, particularly in data-constrained environments. Full article

This study proposes CEL-DL-Bagging (Cross-Entropy Loss-optimized Deep Learning Bagging), a multi-model fusion framework that integrates cross-entropy loss-weighted voting with Bootstrap Aggregating (Bagging). First, we develop a lightweight recognition architecture by embedding a salient position attention (SPA) mechanism into four base networks (YOLOv5s-cls, EfficientNet-B0, MobileNetV3, and ShuffleNetV2), significantly enhancing discriminative feature extraction for disease patterns. Our experiments show that these SPA-enhanced models achieve consistent accuracy gains of 0.8–1.7 percentage points, peaking at 97.86%. Building on this, we introduce DB-CEWSV—an ensemble framework combining Deep Bootstrap Aggregating (DB) with adaptive Cross-Entropy Weighted Soft Voting (CEWSV). The system dynamically optimizes model weights based on their cross-entropy performance, using SPA-augmented networks as base learners. The final integrated model attains 98.33% accuracy, outperforming the strongest individual base learner by 0.48 percentage points. Compared with single models, the ensemble learning algorithm proposed in this study led to better generalization and robustness of the ensemble learning model and better identification of rice diseases in the natural background. It provides a technical reference for applying rice disease identification in practical engineering. Full article

Poultry waste composting is a necessary technique for agricultural farm sustainability. Composting is a dynamic process influenced by multiple variables. Humidity and temperature play fundamental roles in analyzing its different phases according to the environment and composting technique. Current developments for monitoring these variables include automation via intelligent Internet of Things (IoT)-based sensor networks for variable tracking. These advancements serve as efficient tools for modeling that facilitate the simulation and prediction of composting process variables to improve system efficiency. Therefore, this paper presents the dynamic modeling of composting via forced aeration processes in high-mountain climates, with the intent of estimating biomass temperature dynamics in different phases using system identification techniques. To this end, four dynamic model estimation structures are employed: transfer function (TF), state space (SS), process (P), and Hammerstein–Wiener (HW). The and model quality, fitting results, and standard error metrics of the different models found in each phase are assessed through residual analysis from each structure by validation with real system data. Our results show that the second-order underdamped multiple-input–single-output (MISO) process model with added noise demonstrates the best fit and validation performance. Full article

Indoor horticulture requires a substantial quantity of electricity to meet crops extended photoperiodic requirements for optimal photosynthetic rate. Simultaneously, global electricity costs have grown dramatically in recent years, endangering the sustainability and profitability of indoor vertical farms and/or modern greenhouses that use artificial lighting systems to accelerate crop development and growth. This study investigates the growth rate and physiological development of cherry tomato plants cultivated in a pilot indoor vertical farm at the Agricultural University of Athens’ Laboratory of Farm Structures (AUA) under continuous and disruptive lighting. The leaf physiological traits from multiple photoperiodic stress treatments were analyzed and utilized to estimate the plant’s tolerance rate under varied illumination conditions. Four different photoperiodic treatments were examined and compared, firstly plants grew under 14 h of continuous light (C-14L10D/control), secondly plants grew under a normalized photoperiod of 14 h with intermittent light intervals of 10 min of light followed by 50 min of dark (NI-14L10D/stress), the third treatment where plants grew under 14 h of a load-shifted energy demand response intermittent lighting schedule (LSI-14L10D/stress) and finally plants grew under 13 h photoperiod following of a load-shifted energy demand response intermittent lighting schedule (LSI-13L11D/stress). Plants were subjected also under two different light spectra for all the treatments, specifically WHITE and Blue/Red/Far-red light composition. The aim was to develop flexible, energy-efficient lighting protocols that maintain crop productivity while reducing electricity consumption in indoor settings. Results indicated that short periods of disruptive light did not negatively impact physiological responses, and plants exhibited tolerance to abiotic stress induced by intermittent lighting. Post-harvest data indicated that intermittent lighting regimes maintained or enhanced growth compared to continuous lighting, with spectral composition further influencing productivity. Plants under LSI-14L10D and B/R/FR spectra produced up to 93 g fresh fruit per plant and 30.4 g dry mass, while consuming up to 16 kWh less energy than continuous lighting—highlighting the potential of flexible lighting strategies for improved energy-use efficiency. Full article

When monitoring seed positions in soil using ultrasonic waves, the main challenge is obtaining acoustic wave characteristics at the seed locations. This study developed a three-dimensional ultrasonic model with the double media of seed–soil using the discrete element method to visualize signal variations and analyze propagation characteristics. The effects of the compression ratio (0/6/12%), excitation frequency (20/40/60 kHz), and amplitude (5/10/15 μm) on signal variation and attenuation were analyzed. The results show consistent trends: time/frequency domain signal intensity increased with a higher compression ratio and amplitude but decreased with frequency. Comparing ultrasonic signals at soil particles before and after the seed along the propagation path shows that the seed significantly absorbs and attenuates ultrasonic waves. Time domain intensity drops 93.99%, and first and residual wave frequency peaks decrease by 88.06% and 96.39%, respectively. Additionally, comparing ultrasonic propagation velocities in the double media of seed–soil and the single soil medium reveals that the velocity in the seed is significantly higher than that in the soil. At compression ratios of 0%, 6%, and 12%, the sound velocity in the seed is 990.47%, 562.72%, and 431.34% of that in the soil, respectively. These findings help distinguish seed presence and provide a basis for ultrasonic seed position monitoring after sowing. Full article

This research focuses on route optimization for autonomous ground vehicles, with key applications in precision agriculture, logistics and surveillance. Its goal is to create planning techniques that increase productivity and flexibility in changing settings. To achieve this, a PRISMA-based systematic literature review was carried out, encompassing works published during the last five years in databases like IEEE Xplore, ScienceDirect and Scopus. The search focused on topics related to route optimization, unmanned ground vehicles and heuristic algorithms. From the analysis of 56 selected articles, trends, technologies and challenges in real-time route planning were identified. Fifty-seven percent of the recent studies focus on UGV optimization, with prominent applications in agriculture, aiming to maximize efficiency and reduce costs. Heuristic algorithms, such as Humpback Whale Optimization, Firefly Search and Particle Swarm Optimization, are commonly employed to solve complex search problems. The findings underscore the need for more flexible planning techniques that integrate spatiotemporal and curvature constraints, allowing systems to respond effectively to unforeseen changes. By increasing their effectiveness and adaptability in practical situations, our research helps to provide more reliable autonomous navigation solutions for crucial applications. Full article

Rice disease identification plays a critical role in ensuring yield stability, enabling precise prevention and control, and promoting agricultural intelligence. However, existing approaches rely heavily on manual inspection, which is labor-intensive and inefficient. Moreover, the significant variability in disease features poses further challenges to accurate recognition. To address these issues, this paper proposes a novel rice leaf disease detection model—RLDD-YOLOv11n. First, the improved RLDD-YOLOv11n integrates the SCSABlock residual attention module into the neck layer to enhance multi-semantic information fusion, thereby improving the detection capability for small disease targets. Second, recognizing the limitations of the native upsampling module in YOLOv11n in reconstructing rice-disease-related features, the CARAFE upsampling module is incorporated. Finally, a rice leaf disease dataset focusing on three common diseases—Bacterial Blight, Rice Blast, and Brown Spot—was constructed. The experimental results demonstrate the effectiveness of the proposed improvements. RLDD-YOLOv11n achieved a mean Average Precision (mAP) of 88.3%, representing a 2.8% improvement over the baseline model. Furthermore, compared with existing mainstream lightweight YOLO models, RLDD-YOLOv11n exhibits a superior detection performance and robustness. Full article

The global transition to a digital era is crucial for society, as most daily activities are driven by digital technologies aimed at enhancing productivity and efficiency in the production of food, fibers, and bioenergy. However, the segregation of digital techniques and equipment in both rural and urban areas poses significant obstacles to technological efforts aimed at combating hunger, ensuring sustainable agriculture, and fostering innovations aligned with the United Nations Sustainable Development Goals (SDGs 02 and 09). Rural regions, which are often less connected to technological advancements, require digital transformation to shift from subsistence farming to market-integrated production. Recent efforts to expand digitalization in these areas have shown promising results. Digital agriculture encompasses terms such as artificial intelligence (AI), the Internet of Things (IoT), big data, and precision agriculture integrating information and communication with geospatial and satellite technologies to manage and visualize natural resources and agricultural production. This digitalization involves both internal and external property management through data analysis related to location, climate, phytosanitary status, and consumption. By utilizing sensors integrated into unmanned aerial vehicles (UAVs) and connected to mobile devices and machinery, farmers can monitor animals, soil, water, and plants, facilitating informed decision-making. An important limitation in studies on nutritional diagnostics is the lack of accuracy validation based on plant responses, particularly in terms of yield. This issue is observed even in conventional leaf tissue analysis methods. The absence of such validation raises concerns about the reliability of digital tools under real field conditions. To ensure the effectiveness of spectral reflectance-based diagnostics, it is essential to conduct additional studies in commercial fields across different regions. These studies are crucial to confirm the accuracy of these methods and to strengthen the development of digital and precision agriculture. Full article

Smart rice disease detection is a key part of intelligent agriculture. To address issues like low efficiency, poor accuracy, and high costs in traditional methods, this paper introduces an enhanced lightweight version of the YOLOv11-RD algorithm, enhancing multi-scale feature extraction through the integration of the enhanced LSKAC attention mechanism and the SPPF module. It also lowers computational complexity and enhances local feature capture through the C3k2-CFCGLU block. The C3k2-CSCBAM block in the neck region reduces the training overhead and boosts target learning in complex backgrounds. Additionally, a lightweight 320 × 320 LSDECD detection head improves small-object detection. Experiments on a rice disease dataset extracted from agricultural operation videos demonstrate that, compared to YOLOv11n, the algorithm improves mAP50 and mAP50-95 by 2.7% and 11.5%, respectively, while reducing the model parameters by 4.58 M and the computational load by 1.1 G. The algorithm offers significant advantages in lightweight design and real-time performance, outperforming other classical object detection algorithms and providing an optimal solution for real-time field diagnosis. Full article

China is the world’s largest producer of chili peppers, which occupy particularly important economic and social values in various fields such as medicine, food, and industry. However, during its production process, chili peppers are affected by pests and diseases, resulting in significant yield reduction due to the temperature and environment. In this study, a lightweight pepper disease identification method, DD-YOLO, based on the YOLOv8n model, is proposed. First, the deformable convolutional module DCNv2 (Deformable ConvNetsv2) and the inverted residual mobile block iRMB (Inverted Residual Mobile Block) are introduced into the C2F module to improve the accuracy of the sampling range and reduce the computational amount. Secondly, the DySample sampling operator (Dynamic Sample) is integrated into the head network to reduce the amount of data and the complexity of computation. Finally, we use Large Separable Kernel Attention (LSKA) to improve the SPPF module (Spatial Pyramid Pooling Fast) to enhance the performance of multi-scale feature fusion. The experimental results show that the accuracy, recall, and average precision of the DD-YOLO model are 91.6%, 88.9%, and 94.4%, respectively. Compared with the base network YOLOv8n, it improves 6.2, 2.3, and 2.8 percentage points, respectively. The model weight is reduced by 22.6%, and the number of floating-point operations per second is improved by 11.1%. This method provides a technical basis for intensive cultivation and management of chili peppers, as well as efficiently and cost-effectively accomplishing the task of identifying chili pepper pests and diseases. Full article

Accurately extracting parcels from satellite images is crucial in precision agriculture. Traditional edge detection fails in complex scenes with difficult post-processing, and deep learning models are time-consuming in terms of sample preparation and less transferable. Based on this, we designed a method combining multi-resolution remote sensing images based on the Segment Anything Model (SAM). Using cropland masking, overlap prediction and post-processing, we achieved 10 m-resolution parcel extraction with SAM, with performance in plain areas comparable to existing deep learning models (P: 0.89, R: 0.91, F1: 0.91, IoU: 0.87). Notably, in hilly regions with fragmented cultivated land, our approach even outperformed these models (P: 0.88, R: 0.76, F1: 0.81, IoU: 0.69). Subsequently, the 10 m parcels results were utilized to crop the high-resolution image. Based on the histogram features and internal edge features of the parcels, used to determine whether to segment downward or not, and at the same time, by setting the adaptive parameters of SAM, sub-meter parcel extraction was finally realized. Farmland boundaries extracted from high-resolution images can more accurately characterize the actual parcels, which is meaningful for farmland production and management. This study extended the application of deep learning large models in remote sensing, and provided a simple and fast method for accurate extraction of parcels boundaries. Full article

This study addresses the problem of early detection of leaf miner infestations in chickpea crops, a significant agricultural challenge. It is motivated by the potential of hyperspectral imaging, once properly combined with machine learning, to enhance the accuracy of pest detection. Originality consists of the application of these techniques to chickpea plants in controlled laboratory conditions using a natural infestation protocol, something not previously explored. The two major methodologies adopted in the approach are as follows: (1) spectral feature-based classification using hyperspectral data within the 400–1000 nm range, wherein a random forest classifier is trained to classify a plant as healthy or infested with eggs or larvae. Dimensionality reduction methods such as principal component analysis (PCA) and kernel principal component analysis (KPCA) were tried, and the best classification accuracies (over 80%) were achieved. (2) VI-based classification, leveraging indices associated with plant health, such as NDVI, EVI, and GNDVI. A support vector machine and random forest classifiers effectively classified healthy and infested plants based on these indices, with over 81% classification accuracies. The main objective was to design an integrated early pest detection framework using advanced imaging and machine learning techniques. Results show that both approaches have resulted in high classification accuracy, highlighting the potential of this approach in precision agriculture for timely pest management interventions. Full article

Issues of poor real-time performance and low accuracy in the detection of load volume in the hopper during the mechanized harvesting of wine grapes are addressed in this study through the development of a proposed volume detection method based on ultrasonic sensors. First, the ultrasonic sensor beamwidth and detection height were determined through calibration tests. Next, a test bench was used to explore the influence of the number of ultrasonic sensors and conveying speed on the detected grape pile height. Data-based regression and hopper configuration-based geometric models correlating grape load volume with detected pile height were subsequently constructed; their accuracies were compared using test bench experiments to identify the optimal detection scheme. The regression model was more accurate than the geometric model under the considered conveying speeds with a maximum relative error of 8.0% for the former. Finally, field tests determined that the average grape load volume detection error during actual harvesting was 14.4%. Therefore, this study provides an effective solution for the detection of grape load volume in the hopper during mechanized harvesting and establishes a theoretical basis for the development of intelligent grape harvesting methods. Full article