Soil salinization poses a critical challenge to global food security, impacting plant growth, development, and crop yield. This study investigates the efficacy of deep learning techniques alongside chlorophyll fluorescence (ChlF) imaging technology for discerning varying levels of salt stress in soybean seedlings. Traditional methods for stress identification in plants are often laborious and time-intensive, prompting the exploration of more efficient approaches. A total of six classic convolutional neural network (CNN) models—AlexNet, GoogLeNet, ResNet50, ShuffleNet, SqueezeNet, and MobileNetv2—are evaluated for salt stress recognition based on three types of ChlF images. Results indicate that ResNet50 outperforms other models in classifying salt stress levels across three types of ChlF images. Furthermore, feature fusion after extracting three types of ChlF image features in the average pooling layer of ResNet50 significantly enhanced classification accuracy, achieving the highest accuracy of 98.61% in particular when fusing features from three types of ChlF images. UMAP dimensionality reduction analysis confirms the discriminative power of fused features in distinguishing salt stress levels. These findings underscore the efficacy of deep learning and ChlF imaging technologies in elucidating plant responses to salt stress, offering insights for precision agriculture and crop management. Overall, this study demonstrates the potential of integrating deep learning with ChlF imaging for precise and efficient crop stress detection, offering a robust tool for advancing precision agriculture. The findings contribute to enhancing agricultural sustainability and addressing global food security challenges by enabling more effective crop stress management.

Salt stress impedes normal development, compromises plant quality, and reduces crop yield. The germination phase in soybean marks the initial stage of its growth cycle. Characterizing salt tolerance during this period can help stimulate soybean growth in natural environments and aid the rapid screening of salt-tolerant soybean varieties. Our study characterized the salt tolerance of 36 soybean germplasms in culture dishes during the germination period. Soybeans were subjected to varying concentrations (0, 60, 120, and 180 mmol/L) of NaCl solution to simulate diverse levels of salt stress, and parameters such as germination energy, germination rate, and root length were measured. Statistical techniques such as analysis of variance, membership function, cluster analysis, and quadratic regression equations were used, and the salt tolerance of these 36 soybean germplasms was determined. The critical indicators and the most effective screening concentration for assessing the germination salt tolerance of soybean were identified. Soybeans tolerated low salt concentrations; however, salt concentrations greater than 120 mmol/L significantly inhibited germination indicators. The germination rate, germination vigor, vitality index, seed germination index, total fresh weight, and total dry weight could be used to identify salt tolerance. The semi-lethal concentration of soybean was 155.4 mmol/L, and the coefficient of variation was 20.00%, indicating that it could be used as a screening concentration for evaluating salt tolerance during soybean germination. A total of 36 soybean varieties were classified into four salt tolerance levels through cluster analysis. QN-27, QN-35, and QN-36 were highly salt-resistant materials, and QN-2, QN-17, and QN-19 were salt-sensitive materials. Characterizing salt tolerance during soybean germination can facilitate the selection and breeding of salt-tolerant soybean varieties. Future research utilizing this approach can aid in the selection of soybean varieties with salinity tolerance.

Phenotypic characterization of mature soybean pods is a crucial aspect of breeding programs, yet efficiently obtaining accurate pod phenotypic parameters remains a major challenge. Recent advances in deep learning, particularly in keypoint detection models, have introduced innovative methods for pod phenotype extraction. However, precise identification and analysis of fine-scale phenotypic traits in soybean pods remain challenging in current research. We propose Pod-pose, an innovative top-down keypoint detection model for precise soybean pod phenotyping that adapts human pose estimation techniques to plant phenotyping. Specifically, Pod-pose integrates the architectural strengths of various advanced YOLO (You Only Look Once) models through bottleneck structure optimization and positional feature enhancement to achieve superior detection accuracy. Furthermore, we implemented a two-stage detection method augmented with transfer learning, which not only reduces training complexity but also significantly enhances the model's performance. Extensive evaluation of our custom-built dataset demonstrated Pod-Pose's superior performance, with the X variant achieving an Average Precision of 0.912 at an IoU threshold of 0.5 (AP@IoU = 0.5). Notably, four critical pod-related phenotypic traits were successfully quantified: pod length, bending length, curvature, and inflection point width. This study establishes Pod-Pose as a viable solution for pod phenotyping, with potential applications in soybean breeding optimization.

Accurate soybean pod counting remains a significant challenge in field-based phenotyping due to complex factors such as occlusion, dense distributions, and background interference. We present SmartPod, an advanced deep learning framework that addresses these challenges through three key innovations: (1) a novel vision Transformer architecture for enhanced feature representation, (2) an efficient attention mechanism for the improved detection of overlapping pods, and (3) a semi-supervised learning strategy that maximizes performance with limited annotated data. Extensive evaluations demonstrate that SmartPod achieves state-of-the-art performance with an Average Precision at an IoU threshold of 0.5 (AP@IoU = 0.5) of 94.1%, outperforming existing methods by 1.7–4.6% across various field conditions. This significant improvement, combined with the framework’s robustness in complex environments, positions SmartPod as a transformative tool for large-scale soybean phenotyping and precision breeding applications.

Various biotic and abiotic stresses challenge plant growth and production, with salt stress notably impeding normal development, compromising quality, and reducing yield in plants. The objective is to identify salt-tolerant soybean germplasm resources and develop a comprehensive method for assessing salt tolerance during soybean germination. This study involved the utilization of 36 soybean germplasm to induce varying degrees of salt stress through the application of 0, 60, 120, and 180 mmol/L NaCl solutions, employing the Petri dish germination identification method to assess nine phenotypic indices, such as germination potential, rate, and radicle length. The salt tolerance of soybean germination was comprehensively assessed using one-way ANOVA, multi-factor ANOVA, principal component analysis, affiliation function, quadratic regression equation analysis, and cluster analysis. These methods were employed to investigate the impact of varied NaCl concentrations on different germination indices, determine the best screening parameters for identifying soybean germination salt tolerance, and identify soybean germplasm with varying salt tolerances. The results indicated that soybean seeds exhibited tolerance to low salt concentrations, while concentrations exceeding 120 mmol/L led to significant inhibition of germination indicators. Notably, the vitality index and radicle length were highly sensitive indicators reflecting the impact of salt stress on seed germination. By analyzing the quadratic regression equation correlating the germination index and the salt tolerance coefficient, an LC50 value of 155.4 mmol/L with a coefficient of variation of 20.00% was derived. This value serves as a viable screening concentration for identifying salt tolerance during the soybean germination stage. Additionally, clustering analysis categorized 36 soybean varieties into 4 salt tolerance levels, with QN-27, QN-35, and QN-36 demonstrating high salt tolerance, and QN-2, QN-17, and QN-19 were classified as salt-sensitive materials.

Introduction: The emergence rate of crop seedlings is an important indicator for variety selection, evaluation, field management, and yield prediction. To address the low recognition accuracy caused by the uneven size and varying growth conditions of crop seedlings under salt-alkali stress, this research proposes a peanut seedling recognition model, MS-YOLOv8.Methods: This research employs close-range remote sensing from unmanned aerial vehicles (UAVs) to rapidly recognize and count peanut seedlings. First, a lightweight adaptive feature fusion module (called MSModule) is constructed, which groups the channels of input feature maps and feeds them into different convolutional layers for multi-scale feature extraction. Additionally, the module automatically adjusts the channel weights of each group based on their contribution, improving the feature fusion effect. Second, the neck network structure is reconstructed to enhance recognition capabilities for small objects, and the MPDIoU loss function is introduced to effectively optimize the detection boxes for seedlings with scattered branch growth.Results: Experimental results demonstrate that the proposed MS-YOLOv8 model achieves an AP50 of 97.5% for peanut seedling detection, which is 12.9%, 9.8%, 4.7%, 5.0%, 11.2%, 5.0%, and 3.6% higher than Faster R-CNN, EfficientDet, YOLOv5, YOLOv6, YOLOv7, YOLOv8, and RT-DETR, respectively.Discussion: This research provides valuable insights for crop recognition under extreme environmental stress and lays a theoretical foundation for the development of intelligent production equipment.