Search Results (179)

Intelligent detection of tomato seedling transplant quality represents a core technology for advancing agricultural automation. However, in practical applications, existing algorithms still face numerous technical challenges, particularly with prominent issues of false detections and missed detections during recognition. To address these challenges, we developed the ESG-YOLO object detection model and successfully deployed it on edge devices, enabling real-time assessment of tomato seedling transplanting quality. Our methodology integrates three key innovations: First, an EMA (Efficient Multi-scale Attention) module is embedded within the YOLOv8 neck network to suppress interference from redundant information and enhance morphological focus on seedlings. Second, the feature fusion network is reconstructed using a GSConv-based Slim-neck architecture, achieving a lightweight neck structure compatible with edge deployment. Finally, optimization employs the GIoU (Generalized Intersection over Union) loss function to precisely localize seedling position and morphology, thereby reducing false detection and missed detection. The experimental results demonstrate that our ESG-YOLO model achieves a mean average precision mAP of 97.4%, surpassing lightweight models including YOLOv3-tiny, YOLOv5n, YOLOv7-tiny, and YOLOv8n in precision, with improvements of 9.3, 7.2, 5.7, and 2.2%, respectively. Notably, for detecting key yield-impacting categories such as “exposed seedlings” and “missed hills”, the average precision (AP) values reach 98.8 and 94.0%, respectively. To validate the model’s effectiveness on edge devices, the ESG-YOLO model was deployed on an NVIDIA Jetson TX2 NX platform, achieving a frame rate of 18.0 FPS for efficient detection of tomato seedling transplanting quality. This model provides technical support for transplanting performance assessment, enabling quality control and enhanced vegetable yield, thus actively contributing to smart agriculture initiatives. Full article

This study proposes a lightweight adaptive neural network framework based on an improved YOLOv11n model to address the core challenges in identifying cabbage seedlings in visible light images captured by UAVs. These challenges include the loss of small-target features, poor adaptability to complex lighting conditions, and the low deployment efficiency of edge devices. First, the adaptive dual-path downsampling module (ADown) integrates average pooling and maximum pooling into a dual-branch structure to enhance background texture and crop edge features in a synergistic manner. Secondly, the Illumination Robust Contrast Learning Head (IRCLHead) utilizes a temperature-adaptive network to adjust the contrast loss function parameters dynamically. Combined with a dual-output supervision mechanism that integrates growth stage prediction and interference-resistant feature embedding, this module enhances the model’s robustness in complex lighting scenarios. Finally, a lightweight spatial-channel attention convolution module (LAConv) has been developed to optimize the model’s computational load by using multi-scale feature extraction paths and depth decomposition structures. Experiments demonstrate that the proposed architecture achieves an mAP@0.5 of 99.0% in detecting cabbage seedling growth cycles, improving upon the baseline model by 0.71 percentage points. Furthermore, it achieves an mAP@0.5:0.95 of 2.4 percentage points, reduces computational complexity (GFLOPs) by 12.7%, and drastically reduces inference time from 3.7 ms to 1.0 ms. Additionally, the model parameters are simplified by 3%. This model provides an efficient solution for the real-time counting of cabbage seedlings and lightweight operations in drone-based precision agriculture. Full article

Accurate measurement of seedling traits is essential for plant phenotyping, particularly in understanding growth dynamics and stress responses. Elm trees (Ulmus spp.), ecologically and economically significant, pose unique challenges due to their curved seedling morphology. Traditional manual measurement methods are time-consuming, prone to human error, and often lack consistency. Moreover, automated approaches remain limited and often fail to accurately process seedlings with nonlinear or curved morphologies. In this study, we introduce GLEN, a deep learning-based model for detecting germinating elm seeds and accurately estimating their lengths of germinating structures. It leverages a dual-path architecture that combines pixel-level spatial features with instance-level semantic information, enabling robust measurement of curved radicles. To support training, we construct GermElmData, a curated dataset of annotated elm seedling images, and introduce a novel synthetic data generation pipeline that produces high-fidelity, morphologically diverse germination images. This reduces the dependence on extensive manual annotations and improves model generalization. Experimental results demonstrate that GLEN achieves an estimation error on the order of millimeters, outperforming existing models. Beyond quantifying germinating elm seeds, the architectural design and data augmentation strategies in GLEN offer a scalable framework for morphological quantification in both plant phenotyping and broader biomedical imaging domains. Full article

Soil phosphorus (P) availability is a critical factor affecting the productivity of Phyllostachys edulis (moso bamboo) forests. However, the mechanisms underlying the physiological and growth responses of moso bamboo to varying soil P conditions remain poorly understood. The aim of this study was to elucidate the adaptive mechanisms of moso bamboo to different soil P levels from the perspectives of root morphological and architectural plasticity, as well as the allocation strategies of nutrient elements and photosynthates. One-year-old potted seedlings of moso bamboo were subjected to four P addition treatments (P1: 0, P2: 25 mg·kg⁻¹, P3: 50 mg·kg⁻¹, P4: 100 mg·kg⁻¹) for one year. The biomass of different seedling organs, root morphological and architectural indices, and the contents of nitrogen (N), P, and non-structural carbohydrates in the roots, stems, and leaves were measured in July and December. P addition increased the root length (by 113.8%), root surface area (by 146.5%), root average diameter (by 14.8%), root length ratio of thicker roots (diameter > 0.9 mm), number of root tips (by 31.9%), fractal dimension (by 5.6%), P accumulation (by 235.8%), and contents of starch (ST) and soluble sugars (SS), while it decreased the specific root length (by 31.7%), root branching angle (by 1.9%), root topological index (by 4.8%), root length ratio of finer roots (diameter ≤ 0.3 mm), SS/ST, and N/P. The root–shoot ratio showed a downward trend in July and an upward trend in December. Our results indicated that moso bamboo seedlings tended to form roots with a small diameter, high absorption efficiency, and minimal internal competition to adapt to soil P deficiency and carbon limitation caused by low P. Under low-P conditions, moso bamboo prioritized allocating photosynthates and P to roots, promoting the conversion of starch to soluble sugars to support root morphological and architectural plasticity and maintain root growth and physiological functions. Sole P addition eliminated the constraints of low P on moso bamboo growth and nutrient accumulation but caused imbalances in the N/P. Full article

Accurate and timely estimation of soybean emergence at the plot scale using unmanned aerial vehicle (UAV) remote sensing imagery is essential for germplasm evaluation in breeding programs, where breeders prioritize overall plot-scale emergence rates over subimage-based counts. This study proposes PlotCounter, a deep learning regression model based on the TasselNetV2++ architecture, designed for plot-scale soybean seedling counting. It employs a patch-based training strategy combined with full-plot validation to achieve reliable performance with limited breeding plot data. To incorporate additional agronomic information, PlotCounter is extended into a multitask learning framework (MTL-PlotCounter) that integrates sowing metadata such as variety, number of seeds per hole, and sowing density as auxiliary classification tasks. RGB images of 54 breeding plots were captured in 2023 using a DJI Mavic 2 Pro UAV and processed into an orthomosaic for model development and evaluation, showing effective performance. PlotCounter achieves a root mean square error (RMSE) of 6.98 and a relative RMSE (rRMSE) of 6.93%. The variety-integrated MTL-PlotCounter, V-MTL-PlotCounter, performs the best, with relative reductions of 8.74% in RMSE and 3.03% in rRMSE compared to PlotCounter, and outperforms representative YOLO-based models. Additionally, both PlotCounter and V-MTL-PlotCounter are deployed on a web-based platform, enabling users to upload images via an interactive interface, automatically count seedlings, and analyze plot-scale emergence, powered by a multimodal large language model. This study highlights the potential of integrating UAV remote sensing, agronomic metadata, specialized deep learning models, and multimodal large language models for advanced crop monitoring. Full article

Soil phosphorus (P) availability is an important determinant of productivity in Pinus massoniana (Masson pine) forests. The mechanistic bases governing the physiological and growth responses of Masson pine to varying soil P conditions remain insufficiently characterized. This study aims to decipher the adaptive strategies of Masson pine to different soil P levels, focusing on root morphological–architectural plasticity and the allocation dynamics of nutrient elements and photosynthetic assimilates. One-year-old potted Masson pine seedlings were exposed to four P addition treatments for one year: P0 (0 mg kg⁻¹), P1 (25 mg kg⁻¹), P2 (50 mg·kg⁻¹), and P3 (100 mg kg⁻¹). In July and December, measurements were conducted on seedling organ biomass, root morphological indices [root length (RL), root surface area (RSA), root diameter (RD), specific root length (SRL), and root length ratio (RLR) for each diameter grade], root architectural indices [number of root tips (RTs), fractal dimension (FD), root branching angle (RBA), and root topological index (TI)], as well as the content of nitrogen (N), phosphorus (P), carbon (C), and non-structural carbohydrates (NSCs) in roots, stems, and leaves. Compared with the P0 treatment, P2 and P3 significantly increased root biomass, root–shoot ratio, RL, RSA, RTs, RLR of finer roots (diameter ≤ 0.4 mm), nutrient accumulation ratio in roots, and starch (ST) content in roots, stems and leaves. Meanwhile, they decreased soluble sugar (SS) content, SS/ST ratio, C and N content, and N/P and C/P ratios in stems and leaves, as well as nutrient accumulation ratio in leaves. The P3 treatment significantly reduced RBA and increased FD and SRL. Our results indicated that Masson pine adapts to low P by developing shallower roots with a reduced branching intensity and promoting the conversion of ST to SS. P’s addition effectively alleviates growth limitations imposed by low P, stimulating root growth, branching, and gravitropism. Although a sole P addition promotes short-term growth and P uptake, it triggers a substantial consumption of N, C, and SS, leading to significant decreases in N/P and C/P ratios and exacerbating N’s limitation, which is detrimental to long-term growth. Under high-P conditions, Masson pine strategically prioritizes allocating limited N and SS to roots, facilitating the formation of thinner roots with low C costs. Full article

Efficient detection and localization of maize seedlings in complex field environments is essential for accurate plant segmentation and subsequent three-dimensional morphological reconstruction. To overcome the limited accuracy and high computational cost of existing models, we propose an enhanced architecture named MaizeStar-YOLO. The redesigned backbone integrates a novel C2F_StarsBlock to improve multi-scale feature fusion, while a PKIStage module is introduced to enhance feature representation under challenging field conditions. Evaluations on a diverse dataset of maize seedlings show that our model achieves a mean average precision (mAP) of 92.8%, surpassing the YOLOv8 baseline by 3.6 percentage points, while reducing computational complexity to 3.0 GFLOPs, representing a 63% decrease. This efficient and high-performing framework enables precise plant–background segmentation and robust three-dimensional feature extraction for morphological analysis. Additionally, it supports downstream applications such as pest and disease diagnosis and targeted agricultural interventions. Full article

Amid global environmental change, the intensification of nitrogen (N) deposition exerts critical impacts on the growth of forest vegetation and the structure and function of ecosystems in subtropical China. However, the physiological and growth response mechanisms of subtropical tree species remain poorly understood. This study explored adaptive mechanisms of typical subtropical tree species to N deposition, analyzing biomass accumulation, root plasticity, and nutrient/photosynthate allocation strategies. One-year-old potted seedlings of Phyllostachys edulis (moso bamboo) and Cunninghamia lanceolata (Chinese fir) were subjected to four N-addition treatments (N0: 0, N1: 6 g·m⁻²·a⁻¹, N2: 12 g·m⁻²·a⁻¹, N3: 18 g·m⁻²·a⁻¹) for one year. In July and December, measurements were conducted on seedling organ biomass, root morphological and architectural traits, as well as nutrient elements (N and phosphorus(P)) and non-structural carbohydrate (soluble sugars and starch) contents in roots, stems, and leaves. Our results demonstrate that the Chinese fir exhibits stronger tolerance to N deposition and greater root morphological plasticity than moso bamboo. It adapts to N deposition by developing root systems with a higher finer root (diameter ≤ 0.2 mm) ratio, lower construction cost, greater branching intensity and angle, and architecture approaching dichotomous branching. Although N deposition promotes short-term biomass and N accumulation in both species, it reduces P and soluble sugars contents, leading to N/P imbalance and adverse effects on long-term growth. Under conditions of P and photosynthate scarcity, the Chinese fir preferentially allocates soluble sugars to leaves, while moso bamboo prioritizes P and soluble sugars to roots. In the first half of the growing season, moso bamboo allocates more biomass and N to aboveground parts, whereas in the second half, it allocates more biomass and P to roots to adapt to N deposition. This study reveals that Chinese fir enhances its tolerance to N deposition through the plasticity of root morphology and architecture, while moso bamboo exhibits dynamic resource allocation strategies. The research identifies highly adaptive root morphological and architectural patterns, demonstrating that optimizing the allocation of elements and photosynthates and avoiding elemental balance risks represent critical survival mechanisms for subtropical tree species under intensified N deposition. Full article

The distinctive leaf and twig heteromorphism in Euphrates poplar (Populus euphratica Oliv.) reflects its adaptive strategies to cope with arid environments across ontogenetic stages. In the key distribution area of P. euphratica forests in China, we sampled P. euphratica twigs (which grow in the current year) at different age classes (1-, 3-, 5-, 8-, and 11-year-old trees), then analyzed their morphological traits, biomass allocation, as well as allometric relationships. Results revealed significant ontogenetic shifts: seedlings prioritized vertical growth by lengthening stems (32.06 ± 10.28 cm in 1-year-olds) and increasing stem biomass allocation (0.36 ± 0.14 g), while subadult trees developed shorter stems (6.80 ± 2.42 cm in 11-year-olds) with increasesd petiole length (2.997 ± 0.63 cm) and lamina biomass (1.035 ± 0.406 g). Variance partitioning showed that 93%–99% of the trait variation originated from age and individual differences. Standardized major axis analysis demonstrated a consistent “diminishing returns” allometry in biomass allocation (lamina–stem slope = 0.737, lamina–petiole slope = 0.827), with age-modulated intercepts reflecting developmental adjustments. These patterns revealed an evolutionary trade-off strategy where subadult trees optimized photosynthetic efficiency through compact architecture and enhanced hydraulic safety, while seedlings prioritized vertical space occupation. Our findings revealed that heteromorphic twigs play a pivotal role in modular trait coordination, providing mechanistic insights into P. euphratica’s adaptation to extreme aridity throughout its lifespan. Full article

Object detection is essential for precision agriculture applications like automated plant counting, but the minimum dataset requirements for effective model deployment remain poorly understood for arable crop seedling detection on orthomosaics. This study investigated how much annotated data is required to achieve standard counting accuracy (R² = 0.85) for maize seedlings across different object detection approaches. We systematically evaluated traditional deep learning models requiring many training examples (YOLOv5, YOLOv8, YOLO11, RT-DETR), newer approaches requiring few examples (CD-ViTO), and methods requiring zero labeled examples (OWLv2) using drone-captured orthomosaic RGB imagery. We also implemented a handcrafted computer graphics algorithm as baseline. Models were tested with varying training sources (in-domain vs. out-of-distribution data), training dataset sizes (10–150 images), and annotation quality levels (10–100%). Our results demonstrate that no model trained on out-of-distribution data achieved acceptable performance, regardless of dataset size. In contrast, models trained on in-domain data reached the benchmark with as few as 60–130 annotated images, depending on architecture. Transformer-based models (RT-DETR) required significantly fewer samples (60) than CNN-based models (110–130), though they showed different tolerances to annotation quality reduction. Models maintained acceptable performance with only 65–90% of original annotation quality. Despite recent advances, neither few-shot nor zero-shot approaches met minimum performance requirements for precision agriculture deployment. These findings provide practical guidance for developing maize seedling detection systems, demonstrating that successful deployment requires in-domain training data, with minimum dataset requirements varying by model architecture. Full article

Genome editing has revolutionized plant science, providing an unprecedented ability to precisely manipulate plant genomes. For this study, genome editing was utilized to target and modify the NF-YA8 transcription factor (TF) in tomato plants (Solanum lycopersicum L. var. Heinz 1706). The primary objective of this research was to introduce targeted mutations in a non-transgenic manner to the NF-YA8 gene, which encodes the alpha subunit of the Nuclear Factor-Y (NF-Y) heterotrimeric TF, and explore its potential for developing new and improved tomato varieties. Through the transient expression of custom-engineered zinc finger nucleases (ZFNs) in tomato seeds, mutations were successfully introduced in the target gene. The recovered mutant NF-YA8 coding sequences showed a significant level of similarity to the wild type, with a range of 86.9% to 98.21%. Genotyping M2 lines revealed monogenic mutations at or near the intended target site. Phenotypic changes were also evident in both vegetative and reproductive stages of plants. The research revealed that NF-YA8 functions as a high-level regulator, orchestrating a developmental cascade that influences key agronomic traits throughout the plant’s life cycle, including cotyledon development, stem architecture, inflorescence architecture, flowering time, and fruit size and shape. Full article

Salinity stress poses a major challenge to agricultural productivity worldwide, including for pumpkin, a globally cultivated vegetable crop with great economic value. To deal with salt stress, plants exhibit an array of responses such as changes in their root system architecture. However, the root phenotype and gene expression of pumpkin in response to different concentrations of NaCl remains unclear. To this end, this study evaluated the effects of salinity stress on root architecture in C. moschata (Cmo-1, Cmo-2 and Cmo-3) and C. maxima (Cma-1, Cma-2 and Cma-3), as well as their hybrids of C. moschata and C. maxima (Ch-1, Ch-2 and Ch-3) at the germination and seedling stages. The results showed that the total root length and the number of root tips decreased by more than 10% and 5%, respectively, under 180 mM NaCl conditions compared to those under the 0 mM NaCl conditions. In contrast, the total root length and the number of root tips were increased or decreased under 60 mM NaCl conditions. Meanwhile, salt stress was considered severe when treated with more than 120 mM NaCl, which could be used to evaluate the salt tolerance of the germplasm resources of pumpkin. In addition, the transcriptional changes in the roots of both Cmo-3 and Cma-2 under salt stress were analyzed via RNA-sequencing. We found 4299 and 2141 differential expression genes (DEGs) in Cmo-3 and Cma-2, respectively. Plant hormone signal transduction, Phenylpropanoid biosynthesis and the MAPK signaling pathway were found to be the significant KEGG pathways. The expression of ARF (auxin response factor), B-ARR (type-B response regulator) and PYR (pyrabactin resistance)/PYL (PYR-LIKE) genes was downregulated by NaCl treatment. In contrast, the expression of SnRK2 (sucrose non-fermenting-1-related protein kinase 2) and AHP (histidine-containing phosphotransmitter) genes was downregulated in Cmo-3 and upregulated in Cma-2. These findings will help us better understand the mechanisms of salt tolerance in pumpkins and potentially provide insight into enhancing salt tolerance in crop plants. Full article

Many stressors contribute to productivity and quality losses in agricultural production, ranging from the rising global population to shrinking agricultural lands. To boost yield and quality, plants must be protected from abiotic and biotic stressors. Seed priming is the process of boosting germination and seedling development by treating seeds with particular pre-treatments before germination. Seed priming is used to improve plant yield and germination. Plant defense elicitors stimulate the plant’s natural immune system when administered externally, strengthening the plant and making it more resistant/tolerant to diseases. β-Aminobutyric Acid (BABA) is a plant defense elicitor, and in this study, the effect of BABA seed priming on Clavibacter michiganensis ssp. michiganensis (Cmm), which causes bacterial cancer in tomato (Solanum lycopersicum L.), was investigated. Tomato seeds were subjected to seed priming for 72 h with 12 mM BABA (BABA priming) or water (water priming) as the control group. Tomato seedlings that germinated normally were utilized as a positive control. When the plants reached the 3–4 leaf stage, they were infected with Cmm. According to the data, BABA priming was the most effective experimental group in reducing disease severity. Furthermore, it has been shown that the use of BABA as a spray or water-priming application gives better protection than the control treatment. To understand the molecular basis of this suppression, plant samples were obtained at two separate time points (0th and the 7th day), and transcriptional changes of essential plant immunity genes (NPR1, PAL, PR1, WRKY70, WRKY33b, TPK1b, and PR5) were studied. The qRT-PCR results showed that NPR1 gene expression increased considerably with the BABA priming treatment compared to the control. BABA priming at the 0th hour enhanced NPR1 gene expression by approximately five times. In addition, BABA priming increased PR1 gene expression. Furthermore, foliar spraying of BABA (BABA priming+BABA-Sp) on seed-primed plants resulted in a nine-fold increase in PR1 gene expression. At day 7, the BABA priming+Cmm treatment increased PR5 gene expression. Along with the control of other genes, the molecular architecture of BABA seed priming has been attempted to be discovered. The application of BABA seed priming is expected to contribute to the literature and have favorable impacts on plant protection against Cmm. Full article

Ammonium greatly influences nutrient partitioning and root architecture, particularly in the tuberous crops where assimilate translocation is critical for yield formation. However, relatively few studies have systematically delved into the physiological and molecular mechanisms of ammonium on assimilate translocation and root growth in sweetpotato (Ipomoea batatas Lam.). In this study, we investigated the morphological, physiological, and molecular effects of different concentrations of ammonium (0, 0.5, 1.0, 3.0, 5.0 mM) on the growth of the Sushu16 variety in the root-swelling stage. The plant weight and leaf area index of Sushu16 seedlings exhibited a progressive increase with elevated ammonium levels. However, the weight, volume, and number of storage roots (SRs) displayed a trend of a rapid rise and substantial decline, peaking at 1 mM ammonium. Similarly, the chlorophyll content, photosynthetic rate, and stomatal conductance were significantly increased with 1 mM ammonium treatment. Further, the contents of CK, ABA, and IAA increased first and then decreased, reaching a maximum at 1 mM ammonium. Notably, the “down then up” trend of sucrose content in leaves and stems contrasted with the fall–rise pattern of starch content in SRs at 1 mM ammonium. Furthermore, we screened 34 significant DEGs involved in photosynthesis, starch biosynthetic processes, and hormone signal pathway in SRs by RNA-Seq. All the results indicated that 1 mM ammonium had a promotive effect on source–sink conversion and SR production in Sushu16, which highlights potential targets for breeding or agronomic strategies to optimize yield formation in sweetpotato. Full article

This study evaluated the effects of six innovative peat-free substrate formulations, combined with either a conventional solid fertilizer or a novel liquid fertilizer developed by the research team, on the early growth and root morphology of Fagus sylvatica L. and Quercus robur L. seedlings. Treatments were analyzed through two-way ANOVA and species-specific linear regression models. Following one year of field growth, survival rates remained high across all treatments. While R22 (a peat-free substrate with liquid fertilizer) exhibited the highest mean values for seedling height and diameter, only height showed statistically significant variation among treatments (p < 0.05), with no significant differences observed for diameter increment. It was further, revealed that seedlings treated with peat-free substrates and liquid fertilizers exhibited adequate survival, with several combinations especially R22 showing comparable performance to traditional peat-based media with solid fertilizer. Root morphological traits, particularly fine root length (≤0.50 mm) were strong predictors of above-ground growth in F. sylvatica, but less so in Q. robur, which relied more on total root length. The results highlight species-specific root–shoot coordination strategies, with beech exhibiting above-ground growth pattern and oak a gravitropic one. The findings concluded that R22 substrates confirmed exceptional performance with enhanced root growth comparable to peat after one year of forest planting, indicating strong potential for future development without the environmental concerns associated with peat use. Full article