BackgroundRice is one of the major food crops in the world, and the monitoring of its growth condition is of great significance for guaranteeing food security and promoting sustainable agricultural development. Leaf area index (LAI) is a key indicator for assessing the growth condition and yield potential of rice, and the traditional methods for obtaining LAI have problems such as low efficiency and large error. With the development of remote sensing technology, unmanned aerial multispectral remote sensing combined with deep learning technology provides a new way for efficient and accurate estimation of LAI in rice.ResultsIn this study, a multispectral camera mounted on a UAV was utilized to acquire rice canopy image data, and rice LAI was uniformly estimated over multiple periods by the multilayer perceptron (MLP) and convolutional neural network (CNN) models in deep learning. The results showed that the CNN model based on five-band reflectance images (490, 550, 670, 720, and 850 nm) as input after feature screening exhibited high estimation accuracy at different growth stages. Compared with the traditional MLP model with multiple vegetation indices as inputs, the CNN model could better process the original multispectral image data, effectively avoiding the problem of vegetation index saturation, and improving the accuracies by 4.89, 5.76, 10.96, 1.84 and 6.01% in the rice tillering, jointing, booting, and heading periods, respectively, and the overall accuracy was improved by 6.01%. Moreover, the model accuracies (MLP and CNN) before and after variable screening showed noticeable changes. Conducting variable screening contributed to a substantial improvement in the accuracy of rice LAI estimation.ConclusionsUAV multispectral remote sensing combined with CNN technology provides an efficient and accurate method for the unified multi-period estimation of rice LAI. Moreover, the generalization ability and adaptability of the model were further improved by rational variable screening and data enhancement techniques. This study can provide a technical support for precision agriculture and a more accurate solution for rice growth monitoring. More feature extraction and variable screening methods can be further explored in future studies by optimizing the model structure to improve the accuracy and stability of the model.

The biomechanics of growing trees, particularly coconut trees, are intricate due to various abiotic factors such as sunlight, wind, gravitropism, and cultivation practices. Existing structural growth models fail to capture the unique characteristics of coconut trees, which lack branches and have large crown leaves. This research introduces a novel coconut tree modeling approach, integrating abiotic factors and modified Cosserat rod theory. Factors like sunlight availability, wind speed, cultivation practices, and gravitropism influence coconut tree growth rates. The model encompasses both primary and secondary growth processes. Primary growth is influenced by gravitropism, sunlight availability, and wind effects, while secondary growth is determined by variations in trunk diameter. Additionally, the model incorporates the diameter at breast height to accommodate cultivation practice variations. Comparisons between the proposed model, classical rod theory, and biomechanics growth models reveal that the proposed model aligns more closely with real-time data on spatial and temporal growth characteristics. This research marks the first attempt to model coconut tree growth considering abiotic factors comprehensively. In summary, this study presents a pioneering coconut tree growth model that integrates abiotic factors and modified Cosserat rod theory. By considering unique features of coconut trees and environmental influences, the model offers more accurate predictions compared to existing approaches, enhancing our understanding of coconut tree biomechanics and growth patterns. Coconut tree modeling has diverse applications in precision agriculture, automated harvesting, tree health monitoring, climate change analysis, urban planning, and the biomass industry, helping optimize yield, resource management, and sustainability. It also plays a crucial role in genetic research, disaster preparedness, and risk assessment, enabling advancements in robotics, environmental conservation, and industrial applications for improved productivity and resilience.

BackgroundSunflowers (Helianthus annuus L.), a vital oil crop, are facing a severe challenge from broomrape (Orobanche cumana), a parasitic plant that seriously jeopardizes the growth and development of sunflowers, limits global production and leads to substantial economic losses, which urges the development of resistant sunflower varieties.ResultsThis study aims to identify resistance genes from a comprehensive transcriptomic profile of 103 sunflower varieties based on gene expression data and then constructs predictive models with the key resistant genes. The least absolute shrinkage and selection operator (LASSO) regression and random forest feature importance ranking method were used to identify resistance genes. These genes were considered as biomarkers in constructing machine learning models with Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Logistic Regression (LR), and Gaussian Naive Bayes (GaussianNB). The SVM model constructed with the 24 key genes selected by the LASSO method demonstrated high classification accuracy (0.9514) and a robust AUC value (0.9865), effectively distinguishing between resistant and susceptible varieties based on gene expression data. Furthermore, we discovered a correlation between key genes and differential metabolites, particularly jasmonic acid (JA).ConclusionOur study highlights a novel perspective on screening sunflower varieties for broomrape resistance, which is anticipated to guide future biological research and breeding strategies.

Accurate and efficient assessment of highland barley (Hordeum vulgare L.) density is crucial for optimizing cultivation and management practices. However, challenges such as overlapping spikes in unmanned aerial vehicle (UAV) images and the computational requirements for high-resolution image analysis hinder real-time detection capabilities. To address these issues, this study proposes an improved lightweight YOLOv5 model for highland barley spike detection. We chose depthwise separable convolution (DSConv) and ghost convolution (GhostConv) for the backbone and neck networks, respectively, to reduce the parameter and computational complexity. In addition, the integration of convolutional block attention module (CBAM) enhances the model’s ability to focus on target object in complex backgrounds. The results show that the improved YOLOv5 model has a significant improvement in detection performance. Precision and recall increased by 3.1% to 92.2% and 86.2%, respectively, with an F1 score of 0.892. The AP0.5 reaches 92.7% and 93.5% for highland barley in the growth and maturation stages, respectively, and the overall mAP0.5 improved to 93.1%. Compared to the baseline YOLOv5n model, the number of parameters and floating-point operations (FLOPs) were reduced by 70.6% and 75.6%, respectively, enabling lightweight deployment without compromising accuracy. In addition,the proposed model outperformed mainstream object detection algorithms such as Faster R-CNN, Mask R-CNN, RetinaNet, YOLOv7, and YOLOv8, in terms of detection accuracy and computational efficiency. Although this study also suffers from limitations such as insufficient generalization under varying lighting conditions and reliance on rectangular annotations, it provides valuable support and reference for the development of real-time highland barley spike detection systems, which can help to improve agricultural management.

BackgroundThe expected grain yield response to plant density in winter wheat (Triticum aestivum L.) follows a diminishing returns function. To our knowledge, all previous studies dealing with plant density have assumed constant variance. The gap relies on quantifying the optimum plant density that optimizes grain yield at the lowest risk. Here, we propose a Bayesian hierarchical framework to model the variance of grain yield response to plant density. We demonstrate our framework by identifying the plant density in each seed size, seed treatment and environment combination that maximizes the expected yield and minimizes yield variance.ResultsTo fit the model, we used data from field experiments conducted in the Canadian Prairies to identify informative priors and Kansas experiments to demonstrate and validate our framework. Kansas experiments were conducted in 25 environments and consisted of a complete factorial combination of three seed cleaning methods leading to three different seed sizes (light, moderate, heavy), two or three seeding rates, and two seed chemical treatments (insecticide + fungicide vs. none). We described both expected yield and variance of yield in response to plant density. The proposed model allowed us to quantify the minimum risk plant density (minRPD), which represents the minimum plant density at which grain yield variance becomes constant. Plant density at the minRPD was always greater than the agronomic optimum plant density (AOPD, i.e.: the plant density that maximizes expected yield); thus, minRPD could be used to estimate the minimum plant density that maximizes expected yield and minimizes yield variance. When compared at the AOPD, four seed cleaning × chemical treatments combinations resulted in similar yield advantages over the control under high and low yielding environments. However, in low-yielding environments, only two cleaning × chemical treatments combinations resulted in smaller variance when compared at the minRPD against the control. All seed cleaning × chemical treatments combinations resulted in similar AOPD. However, two cleaning × chemical treatments combinations had greater minRPD in low-yield environments compared to the control.ConclusionModeling grain yield response to plant density with the proposed framework is suitable for heteroscedastic data scenarios. Future research may focus on exploring how genotypes, environments and their interaction modulate the difference between AOPD and minRPD and, extend the framework to a variety of processes involving crop management decisions.

Remarkable inter-class similarity and intra-class variability of tomato leaf diseases seriously affect the accuracy of identification models. A novel tomato leaf disease identification model, DWTFormer, based on frequency-spatial feature fusion, was proposed to address this issue. Firstly, a Bneck-DSM module was designed to extract shallow features, laying the groundwork for deep feature extraction. Then, a dual-branch feature mapping network (DFMM) was proposed to extract multi-scale disease features from frequency and spatial domain information. In the frequency branch, a 2D discrete wavelet transform feature decomposition module effectively captured the rich frequency information in the disease image, compensating for spatial domain information. In the spatial branch, a multi-scale convolution and PVT (Pyramid Vision Transformer)-based module was developed to extract the global and local spatial features, enabling comprehensive spatial representation. Finally, a dual-domain features fusion model based on dynamic cross-attention was proposed to fuse the frequency-spatial features. Experimental results on the tomato leaf disease dataset demonstrated that DWTFormer achieved 99.28% identification accuracy, outperforming most existing mainstream models. Furthermore, 96.18% and 99.89% identification accuracies have been obtained on the AI Challenger 2018 and PlantVillage datasets. In-field experiments demonstrated that DWTFormer achieved an identification accuracy of 97.22% and an average inference time of 0.028 seconds in real plant environments. This work has effectively reduced the impact of inter-class similarity and intra-class variability on tomato leaf disease identification. It provides a scalable model reference for fast and accurate disease identification.

BackgroundStudies of multicopy genes impose challenges related to gene redundancy and sequence similarity among copies. However, recent advances in molecular biology and genomics tools associated with dedicated databases facilitate their study. Thus, the present work emphasizes the need for rigorous methodologies and standardized approaches to interpret RT-qPCR results accurately.ResultsData from Physcomitrium patens provides a comprehensive five-step protocol, using thiamine thiazole synthase (THI1) and sucrose 6-phosphate phosphohydrolase (S6PP) genes as proof of concept to showcase a systematic workflow for studying multicopy genes. Beyond examining genes of interest, we highlight the critical role of choosing appropriate internal controls in the analytical process for interpreting gene expression patterns accurately. We emphasize the importance of identifying the relevant orthologous gene, recognizing the inherent challenges in determining the most functional copy for subsequent studies. Our objective is to enhance comprehension of gene redundancy by dissecting multicopy genes' genomic landscape and its characteristics. Furthermore, we address the decision-making process surrounding the expression level quantification of multicopy genes.ConclusionsThe study of multicopy genes discloses early events for functional adaptation. Here, we discuss the significance of multicopy genes in plant biology and provide an experimental protocol to analyze them. As plant systems are strongly influenced by light/dark cycles, challenges inherent to circadian processes are also acknowledged. Therefore, our comprehensive approach aims to advance the understanding of multicopy gene dynamics, offering practical methodologies and contributing with valuable insights to the scientific community.

BackgroundAs an important economic crop, the growth status of the root system of cabbage directly affects its overall health and yield. To monitor the root growth status of cabbage seedlings during their growth period, this study proposes a new network architecture called Swin-Unet++. This architecture integrates the Swin-Transformer module and residual networks and uses attention mechanisms to replace traditional convolution operations for feature extraction. It also adopts the residual concept to fuse contextual information from different levels, addressing the issue of insufficient feature extraction for the thin and mesh-like roots of cabbage seedlings.ResultsCompared with other backbone high-precision semantic segmentation networks, SwinUnet + + achieves superior segmentation results. The results show that the accuracy of Swin-Unet + + in root system segmentation tasks reached as high as 98.19%, with a model parameter of 60 M and an average response time of 29.5 ms. Compared with the classic Unet network, the mIoU increased by 1.08%, verifying that the Swin-Transformer and residual networks can accurately extract the fine-grained features of roots. Furthermore, when images after different semantic segmentations are compared to locate the root position through contours, Swin-Unet + + has the best positioning effect. On the basis of the root pixels obtained from semantic segmentation, the calculated maximum root length, extension width, and root thickness are compared with actual measurements. The resulting goodness of fit R² values are 94.82%, 94.43%, and 86.45%, respectively. Verifying the effectiveness of this network in extracting the phenotypic traits of cabbage seedling roots.ConclusionsThe Swin-Unet + + framework developed in this study provides a new technique for the monitoring and analysis of cabbage root systems, ultimately leading to the development of an automated analysis platform that offers technical support for intelligent agriculture and efficient planting practices.

The enhancement of rice quality stands as a pivotal focus in crop breeding research, with spectral analysis-based non-destructive quality assessment emerging as a widely adopted tool in agriculture. A prevalent trend in this field prioritizes the assessment of effectiveness of individual spectral technologies while overlooking the influence of sample type on spectral quality testing outcomes. Thus, the present study employed Microscopic Hyperspectral Imaging, Raman, and Laser-Induced Breakdown Spectroscopy (LIBS) to acquire spectral data from paddy rice, brown rice, polished rice, and rice flour. The data were then modeled and analyzed with respect to the amylopectin and protein contents of the rice samples via regression methods. Correlation analysis revealed varying degrees of correlation, both positive and negative, among the three spectral techniques and the analytes of interest. LIBS and Raman spectroscopy demonstrated stronger correlations with the analytes compared to microscopic hyperspectral imaging. Based on the selected correlation variables, feature screening and regression modeling were conducted. The modeling results indicated that microscopic hyperspectral data modeling yielded the lowest coefficient of determination of R² = 0.2, followed by Raman data modeling result was higher than it, which was about 0.5. The modeling effect of polished rice is the best. LIBS data modeling performed best, with a coefficient of determination of 0.6. The influence of different sample types on the modeling results was less than that of Raman spectroscopy, and modeling results of grains were better. The feature matching analysis of Raman and libs spectroscopy techniques showed that there were spectral variables that could match amylopectin and protein in the features obtained by multiple modeling statistics, but some modeling variables failed to match. LIBS matched more variables than Raman. These findings provide valuable insights into the application effectiveness of different spectral techniques in detecting rice contents across diverse sample types.

PurposeHyperspectral imaging combined with machine learning offers a promising, cost-effective alternative to invasive chemical analysis for early plant disease detection. In this study, the use of 3D Convolutional Neural Networks (3D-CNNs) was explored to detect presymptomatic viral infections in the model plant Nicotiana benthamiana L. and assess the generalization of these models across different plant genotypes.MethodsFour genotypes of Nicotiana benthamiana L. (wild-type, DCL2/4, AGO2, and NahG) were inoculated with different potexviruses (PepMV mild or severe strain, PVX, BaMV). Viral infection was verified via northern blot analysis at 5 and 10 days post inoculation (DPI). Hyperspectral images were captured over 10 days following inoculation, focusing on the top 3 leaves where symptoms typically appear. The dataset was carefully processed to remove errors, and raster masks were generated to isolate only the leaf pixels. The Extremely Randomized Trees algorithm was used for Effective Wavelength selection, and a novel 3D-CNN architecture was developed to classify 16×16×16 nonoverlapping cubes extracted from the unmasked leaf surfaces. The aim was to classify each cube into healthy or diseased for each of the four viruses at different time points.ResultsAccuracies of 0.78–0.87 were achieved for AGO2 mutants at the cube level, and overall plant-level accuracies of 0.68–0.89. The model’s generalization capabilities were tested across other genotypes, yielding accuracies of up to 0.75 for DCL2/4, 0.83 for NahG, and 0.78 for the wild-type. The timing of disease detection was also assessed, finding that accuracies approached 0.8 as early as 6–8 DPI depending on the virus. The results were validated against northern blot analyses and benchmarked against another state-of-the-art methodology for Nicotiana benthamiana viral infections, achieving superior overall classification accuracies.ConclusionThe proposed patch-based method demonstrated key advantages: (a) exploiting both spectral and textural information, (b) deriving a large training dataset from few hyperspectral images, (c) providing localized classification explainability within leaf regions, and (d) achieving high accuracy for early detection of viral infections.