Search Results (5,296)

Accurate and nondestructive monitoring of tomato growth is essential for large-scale greenhouse production; however, it remains challenging for small-fruited cultivars such as cherry tomatoes. Traditional 2D image analysis often fails to capture precise morphological traits, limiting its usefulness in growth modeling and yield estimation. This study proposes an automated phenotyping framework that integrates deep learning-based instance segmentation with high-resolution 3D point cloud reconstruction and ellipsoid fitting to estimate fruit size and ripeness from daily video recordings. These techniques enable accurate camera pose estimation and dense geometric reconstruction (via SfM and MVS), while Nerfacto enhances surface continuity and photorealistic fidelity, resulting in highly precise and visually consistent 3D representations. The reconstructed models are followed by CIELAB color analysis and logistic curve fitting to characterize the growth dynamics. When applied to real greenhouse conditions, the method achieved an average size estimation error of 8.01% compared to manual caliper measurements. During summer, the maximum growth rate (g_max) of size and ripeness were 24.14%, and 95.24% higher than in winter, respectively. Seasonal analysis revealed that winter-grown tomatoes matured approximately 10 days later than summer-grown fruits, highlighting environmental influences on phenological development. By enabling precise, noninvasive tracking of size and ripeness progression, this approach is a novel tool for smart and sustainable agriculture. Full article

Accurately determining citrus origin is essential for establishing and maintaining regional brands with distinctive qualities while safeguarding the rights and interests of both farmers and consumers. In this study, 2693 navel orange samples were collected from 13 major producing regions in China to establish a comprehensive near-infrared spectroscopy (NIRS) dataset. To address the challenge of citrus origin authentication, this study proposes a novel six-layer one-dimensional convolutional neural network (1D-CNN). The classification accuracy of this model reaches 96.16%. Compared with the support vector machine (SVM), partial least squares discriminant analysis (PLS-DA), and three-layer 1D-CNNs with kernel sizes of 3 and 16, the accuracy of the proposed six-layer model is improved by 9.65%, 3.21%, 3.84%, and 1.98%, respectively. Furthermore, the dataset is augmented using a Wasserstein Generative Adversarial Network (WGAN) and Noise Addition. The results indicate that data augmentation can effectively improve the accuracy of various algorithm models. Among them, the 1D-CNN proposed in this study achieves the best performance on the Noise Addition-augmented dataset, with its accuracy, precision, recall, and F1-score reaching 98.39%, 0.9843, 0.9839, and 0.9840, respectively. Compared with the other four comparative models, the accuracy of this model is increased by 1.48%, 1.36%, 1.48%, and 2.85%, respectively. Finally, a visual analysis of the 1D-CNN’s feature-extraction process was conducted. The results demonstrate that the 1D-CNN can effectively extract discriminative NIR spectral features to accurately distinguish citrus from different origins and that data augmentation markedly improves model performance by increasing data diversity. This work provides a robust tool for citrus origin tracing and offers a new perspective for the origin authentication of other agricultural products. Full article

Accurate banana yield prediction is essential for optimizing agricultural management and ensuring food security in tropical regions, yet traditional estimation methods remain labor-intensive and error prone. This study developed a predictive model for banana yield in Buena Fé, Ecuador, using Random Forest integrated with phenological data, soil properties, spectral technology, and UAV imagery. Data were collected from a 75.2 ha banana farm divided into 26 lots, combining multispectral drone imagery, soil physicochemical analyses, and banana agronomic measurements (height, diameter, bunch weight). A rigorous variable selection process identified six key predictors: NDVI, plant height, plant diameter, soil nitrogen, porosity, and slope. Three machine learning algorithms were compared through 5-fold cross-validation with systematic hyperparameter optimization. Random Forest demonstrated superior performance, with R² = 0.956 and RMSE=1164.9 kg ha⁻¹, representing only CV = 2.79% of mean production. NDVI emerged as the most influential predictor (importance = 0.212), followed by slope (0.184) and plant structural variables. Local sensitivity analysis revealed distinct response patterns between low- and high-production scenarios, with plant diameter showing the greatest impact (+74.9 boxes ha⁻¹) under limiting conditions, while NDVI dominated (−140.4 boxes ha⁻¹) under optimal conditions. The model provides a robust tool for precision agriculture applications in tropical banana production systems. Full article

This study develops a practical, on-farm methodology for optimizing cotton cultivation through Variable Rate Seeding (VRS), utilizing existing farm data and remote sensing, while minimizing operational interference. The methodology involved an experimental design across five rainfed cotton fields on a Brazilian commercial farm, testing four seeding rates (90%, 100%, 110%, 120%) within grid cells using a 4 × 4 Latin square design. Management zones (MZs) were defined using existing soil clay content and elevation data, augmented by twelve vegetation indices from Sentinel-2 satellite imagery and K-Means clustering. Statistical analysis evaluated plant population density’s effect on cotton yield and its association with MZs. For the 2023/2024 season, results showed no positive yield response to increasing plant density above field averages, with negative responses in many plots (e.g., 84% in Field A), suggesting potential gains from reducing rates. The association between population density effect classes and MZs was highly significant with moderate to relatively strong Cramer’s V values (up to 0.47), indicating MZs effectively distinguished response areas. Lower clay content consistently correlated with yield losses at higher densities. This work empowers farm managers to conduct their own site-specific experimentation for optimal seed populations, enhancing precision agriculture and resource efficiency. Full article

Early prediction of common bean (Phaseolus vulgaris L.) yield is essential for improving productivity in tropical agricultural systems. In this study, we integrated canopy structural metrics obtained with the Tracing Radiation and Architecture of Canopies (TRAC) system, unmanned aerial vehicle (UAV)-based multispectral measurements (normalized difference vegetation index—NDVI, projected canopy area), and phenological variables collected from stages R6 to R8 under non-limiting nitrogen conditions. Exploratory analyses (correlation, variance inflation factors—VIF), dimensionality reduction (principal component analysis—PCA), and regularized regression (Elastic Net/LASSO), combined with bootstrap stability selection, were applied to identify a parsimonious subset of robust predictors. The final model, composed of six variables, explained approximately 72% of the variability in plant-level grain yield, with acceptable errors (RMSE ≈ 10.67 g; MAE ≈ 7.91 g). The results demonstrate that combining early vigor, radiation interception, and canopy architecture provides complementary information beyond simple spectral indices. This non-destructive framework delivers an efficient model for early yield estimation and supports site-specific management decisions in common bean with high spatial resolution. By enhancing input-use efficiency and reducing waste, this approach contributes to sustainable development and aligns with the global Sustainable Development Goals (SDGs) for climate-resilient agriculture. Full article

Cationic polyelectrolytes, characterized by positively charged functional groups, play an essential role in industries ranging from food solutions, water treatment, medical, cosmetic, textiles and agriculture due to their electrostatic interactions, biocompatibility, and functional versatility. This paper critically examines the transition from petroleum-based synthetic polymers such as poly(diallyldimethylammonium chloride) and cationic polyacrylamides to sustainable natural alternatives derived from agri-forestry resources like starch derivatives and cellulose. Through a cradle-to-gate life cycle assessment, we highlight the superior renewability, biodegradability, and lower carbon footprint of bio-based polycations, despite challenges in agricultural sourcing and processing. This study examines cationization processes by comparing the environmental limitations of traditional chemical methods, such as significant waste production and limited scalability, with those of second-generation reactive extrusion (REX), which enables solvent-free and rapid modification. REX also allows for adjustable degrees of substitution and ensures uniform charge distribution, thereby enhancing overall functional performance. Groundbreaking research and optimization achieved through the integration of artificial intelligence and machine learning for parameter regulation and targeted mechanical energy management underscore REX’s strengths in precision engineering. By methodically addressing current limitations and articulating future advancements, this work advances sustainable innovation that contributes to a circular economy in materials science. Full article

The uniform distribution of pesticides via spraying is of crucial importance in achieving effective and environmentally sustainable crop protection. Conventional assessment techniques such as sensor-based patternators and electronic monitoring systems are often expensive, complex to calibrate, and limited in adaptability to different nozzle geometries or operating conditions. The present study introduces and validates a low-cost, image-based method as an alternative to the traditional volumetric approach for evaluating spray pattern uniformity in mechanical patternators. Spray tests were conducted under controlled laboratory conditions in order to minimize environmental variability and ensure repeatability. The present study compared two complementary methods—volumetric measurement and image analysis—to evaluate their agreement and accuracy in determining spray deposition profiles. The findings, which included correlation and multivariate tests, indicated a robust linear relationship between the two approaches (r = 0.990–0.999), with deviations falling below ±3% and no statistically significant multivariate differences (p = 0.067). The image-based approach effectively captured both central and edge regions of the spray pattern, demonstrating precision comparable to volumetric readings. The findings confirm that image analysis provides an accurate, reliable, and repeatable means of assessing spray uniformity without reliance on costly sensor technologies. The proposed method offers a practical and scalable alternative for laboratory calibration, nozzle classification, and research applications focused on optimizing agricultural spraying performance. Full article

Existing focal length calibration methods rely on predefined calibration fields or control point networks, which are unsuitable for real-time applications with variable zoom in industrial and agricultural environments. This paper proposes a method based on global scanning principles and geometric constraints, eliminating control points and using symmetric features. A spatial weighting strategy optimizes redundant measurements by integrating optical distortion and the spatial distribution of measured points, enhancing accuracy. Experimental results show that the method achieves micron-level calibration precision, significantly improving visual measurement system accuracy under complex zoom conditions. Full article

The soil microbiome is an essential component of agroecosystems. However, managing it remains a challenge due to our limited knowledge of how various environmental factors interact and shape its spatial distribution. This study presents a hierarchical ecological model to explain the assembly of the microbiome in sloping agricultural landscapes. Through a comprehensive analysis of bacterial and fungal communities, as well as the examination of metabolic and phytopathogenic profiles across a topographic gradient, we have demonstrated that topography acts as the main filter, structuring bacterial communities. Land use, on the other hand, serves as a secondary filter, refining fungal functional guilds. Our results suggest that hydrological conditions in floodplains favor the growth of stress-tolerant bacterial communities with low diversity, dominated by Actinomycetota. Fungal communities, on the other hand, are directly influenced by land use. Long-term fallow periods lead to an enrichment of arbuscular mycorrhiza, while agroecosystems shift towards pathogenic and saprotrophic niches. Furthermore, we identify specific topographic positions that may be hotspots for phytopathogenic pressure. These hotspots are linked to certain taxa, such as Ustilaginaceae and Didymellaceae, which may pose a threat to plant health. The derived hierarchical model provides a scientific foundation for topography-aware precision agriculture. It promotes stratified management, prioritizing erosion control and soil restoration on slopes, customizing nutrient inputs in fertile floodplains, and implementing targeted phytosanitary monitoring in identified risk areas. Our research thus offers a practical framework for harnessing soil spatial variability to improve soil health and proactively manage disease risks in agricultural systems. Full article

This study investigated the application of Species Distribution Models (SDMs), based on Boosted Regression Tree (BRT) and Random Forest (RF), to predict the distribution of citrus crops in a Mediterranean climate by comparing climate data from WorldClim with those from the Regional Territorial Information System of Sicily (S.I.T.R.). To this aim, 19 bioclimatic variables were calculated from monthly temperature and precipitation data in the period 2003–2021 by using the biovars package in R software. Soil properties, terrain elevation, slope, and soil water retention capacity were considered to adequately simulate pedoclimatic conditions in the Syracuse area in Sicily (Italy). The SDM algorithms performed well (AUC: 0.84–0.93; TSS: 0.51–0.69), and Random Forest was selected to compare global and local outcomes. Using data from local meteorological stations increased the model’s reliability, resulting in a difference of approximately ~800 ha in the predicted citrus distribution compared to WorldClim data. This approach also provided a more accurate representation of precipitation patterns, for instance, in the municipality of Augusta, where WorldClim underestimated the average annual rainfall by 284 mm. These findings emphasise the importance of incorporating local environmental data into SDMs to improve prediction accuracy and inform future hybrid approaches to enhance model robustness in the context of climate change. Finally, the results contribute to expanding knowledge of citrus soil and climate conditions, with potential implications for land-use planning. Full article

Strawberries are important cash crops. Traditional manual picking is costly and inefficient, while automated harvesting robots are hindered by field challenges like stem-leaf occlusion, fruit overlap, and appearance/maturity variations from lighting and viewing angles. To address the need for accurate cross-maturity fruit identification and keypoint detection, this study constructed a strawberry image dataset covering multiple varieties, ripening stages, and complex ridge-cultivation field conditions: MSRBerry. Based on the YOLO11-pose framework, we proposed DHN-YOLO with three key improvements: replacing the original C2PSA with the CDC module to enhance subtle feature capture and irregular shape adaptability; substituting C3K2 with C3H to strengthen multi-scale feature extraction and robustness to lighting-induced maturity/color variations; and upgrading the neck into a New-Neck via CA and dual-path fusion to reduce feature loss and improve critical region perception. These modifications enhanced feature quality while cutting parameters and accelerating inference. Experimental results showed DHN-YOLO achieved 87.3% precision, 88% recall, and 78.6% mAP@50:95 for strawberry detection (0.9%, 1.6%, 5% higher than YOLO11-pose), and 83%, 87.5%, 83.6% for keypoint detection (1.9%, 2.1%, 4.6% improvements). It also reached 71.6 FPS with 15 ms single-image inference. The overall performance of DHN-YOLO also surpasses other mainstream models such as YOLO13, YOLO10, DETR and so on. This demonstrates DHN-YOLO meets practical needs for robust strawberry and picking point detection in complex agricultural environments. Full article

This study introduces an IoT-enabled smart greenhouse system tailored for rice cultivation and designed as a controlled experimental platform to evaluate fertilizer application methods. Traditional greenhouse farming often struggles with unpredictable weather, pest infestations, and inefficient resource use. To overcome these challenges, the proposed system optimizes environmental conditions and enables precise monitoring and control through the Thingsboard IoT platform, which tracks temperature, humidity, and sunlight intensity in real time. The cultivation process involved Inceptisol soil preparation, slurrying, fertilization, seeding, transplantation, and continuous monitoring. The novelty lies in its dual-purpose design, enabling both cultivation and structured agronomic experimentation under identical environmental conditions. The system enables both rice cultivation and comparative testing of nano-silica fertilizer applied via root (soil) and foliar (leaf) methods. Automated temperature control (maintaining 20–36.5 °C) and humidity regulation (10–85% RH) with a mist blower response time under 5 s ensured consistent conditions. Sensor accuracy was validated with deviations of 0.4% (±0.11 °C) and 0.77% (±0.5% RH). Compared to conventional setups, this system achieved superior environmental stability and control precision, improving experimental reproducibility. Its integration potential with machine learning models opens new possibilities for forecasting plant responses based on historical data. Overall, the study demonstrates how advanced technology can enhance agricultural precision, sustainability, and research reliability. Full article

The multi-factor coupling mechanism of droplet impact dynamics remains unclear due to insufficient analysis of leaf structure–droplet interaction and inadequate integration of simulations and experiments, limiting precision pesticide application. To address this, we developed a droplet impact model using the Volume of Fluid (VOF) method combined with high-speed camera experiments and systematically analyzed the effects of impact velocity, angle, and droplet size on slip behavior via response surface methodology. Methodologically, we innovatively integrated 3D reverse modeling technology to reconstruct soybean leaf microstructures, overcoming the limitations of traditional planar models that ignore topological features. This approach, coupled with the VOF method, enabled precise tracking of droplet spreading, retraction, and slip processes. Scientifically, our study advances beyond previous single-factor analyses by revealing the synergistic mechanisms of impact parameters through response surface methodology, identifying impact angle as the most critical factor (42.3% contribution), followed by velocity (28.7%) and droplet size (19.5%). Model validation demonstrated high consistency between simulation predictions and experimental observations, confirming its reliability. Practically, the optimized parameter combination (90° impact angle, 1.5 m/s velocity, and 300 μm droplet size) reduced slip displacement by over 50% compared to non-optimized conditions, providing a quantitative tool for spray parameter control. This work enhances the understanding of droplet–leaf interaction mechanisms and offers technical guidance for improving pesticide deposition efficiency in agricultural production. Full article

Agricultural machinery components suffer from severe soft abrasive wear when interacting with flexible materials like rice stalks. To address this, we investigate the friction-reduction mechanism, parameter optimization, and experimental validation of a biomimetic non-smooth surface inspired by the dung beetle’s microstructure. The bionic design was first established by characterizing the beetle’s unique micro-bump array. To ensure simulation accuracy, the critical bonding parameters of a flexible rice stalk DEM model were precisely calibrated via three-point bending tests combined with Response Surface Methodology (RSM). Subsequent DEM simulations revealed that the bionic surface disrupts continuous sliding by reducing the contact area and inducing high-frequency micro-vibrations in the stalk. Using RSM, the bump geometry was systematically optimized, yielding an optimal combination of a 2.975 mm diameter and a 1.0 mm spacing, which theoretically reduces the average normal contact force by 69.3%. Finally, reciprocating wear tests confirmed that the optimized bio-inspired surface exhibited significantly lower mass loss and effectively suppressed the formation of plowing grooves compared to a smooth surface, showing high agreement with simulation predictions. This study provides both a fundamental understanding of the friction-reduction mechanism and precise quantitative guidance for engineering wear-resistant agricultural components. Full article

Plant diseases have a large impact on agricultural production, leading to crop yield reduction and causing economic losses. For the development of intelligent agriculture, it is very important to identify crop diseases accurately. With the help of image recognition methods, precise prevention and control of diseases can be achieved, which significantly reduces the use of pesticides and ultimately improves crop yield and quality. Therefore, this study proposes a theoretical method that combines Attention-Guided PCA (AG-PCA) dimensionality reduction with a spatial attention mechanism. Our method is verified on the ResNet model. The AG-PCA module dynamically selects principal component features based on attention weights, which greatly preserves key disease features during dimensionality reduction. At the same time, a spatial attention mechanism is embedded in the residual blocks to enhance the representation ability of disease regions and suppress background interference. On the AppleLeaf9 dataset containing 10,211 images of 9 disease categories, the model achieved an accuracy of 93.69%, significantly outperforming the baseline methods. Experimental results indicate that it performs stably in complex backgrounds and fine-grained classification tasks, and demonstrates strong generalization ability, showing promising application potential. Full article