Soybean Leaf Research Articles

In Situ Nondestructive Detection of Nitrogen Content in Soybean Leaves Based on Hyperspectral Imaging Technology

In this paper, hyperspectral imaging technology, combined with chemometrics methods, was used to detect the nitrogen content of soybean leaves, and to achieve the rapid, non-destructive and in situ detection of the nitrogen content in soybean leaves. Soybean leaves under different fertilization treatments were used as the research object, and the hyperspectral imaging data and the corresponding nitrogen content data of soybean leaves at different growth stages were obtained. Seven spectral preprocessing methods, such as Savitzky–Golay smoothing (SG), first derivative (1-Der), and direct orthogonal signal correction (DOSC), were used to establish the quantitative prediction models for soybean leaf nitrogen content, and the quantitative prediction models of different spectral preprocessing methods for soybean leaf nitrogen content were analyzed and compared. On this basis, successive projections algorithm (SPA), genetic algorithm (GA) and random frog (RF) were employed to select the characteristic wavelengths and compress the spectral data. The results showed the following: (1) The full-spectrum prediction model of soybean leaf nitrogen content based on DOSC pretreatment was the best. (2) The PLS model of soybean leaf nitrogen content based on the five characteristic wavelengths had the best prediction performance. (3) The spatial distribution map of soybean leaf nitrogen content was generated in a pixel manner using the extracted five characteristic wavelengths and the DOSC-RF-PLS model. The nitrogen content level of soybean leaves can be quantified in a simple way; this provides a foundation for rapid in situ non-destructive detection and the spatial distribution difference detection of soybean leaf nitrogen. (4) The overall results illustrated that hyperspectral imaging technology was a powerful tool for the spatial prediction of the nitrogen content in soybean leaves, which provided a new method for the spatial distribution of the soybean nutrient status and the dynamic monitoring of the growth status.

Heterodera glycines HG type 1.2.5.7 causes a decrease in soybean (Glycine max [L.] Merr.) nitrogen fixation and growth variables

ABSTRACT Soybean cyst nematode (SCN), Heterodera glycines, HG type 1.2.5.7 is the most virulent and widespread SCN biotype in the southern states of the USA, but its effect on soybean (Glycine max [L.] Merr.) nitrogen fixation (NF) activity and growth is not well documented. The objectives of this study were to: (1) measure the impact of HG type 1.2.5.7 on NF activity during the early vegetative stage of three soybean genotypes and (2) compare the impact on soybean leaf and root development, and plant growth. The NF activity of two susceptible (S) genotypes (“Ellis” and “Williams 82”) and one resistant (R) genotype (PI 88,788), subjected to a 10,000-egg treatment, was measured using an in-situ flow-through acetylene reduction assay. The average NF activity of the soybean genotypes was decreased by SCN activity. Time points assessment showed that the NF activity was differently impacted among the genotypes. Based on the measured values, the NF activity was decreased by 30% in SCN infected plants of Williams 82 but that of PI 88,788 and Ellis was affected. Likewise, soybean leaf color and leaf area were affected by SCN infection, but there was no impact on root length and root area. These results showed that SCN HG type 1.2.5.7 can exhibit varying negative impact on NF and shoot growth of S soybean genotypes, while R genotypes may be unaffected. Thus, indicating genetic resistance continues to be a critical tool for the management of the SCN.

Enhanced Detection of Soybean Leaf Diseases Using an Improved Yolov5 Model

Enhanced Detection of Soybean Leaf Diseases Using an Improved Yolov5 Model

Multi-Class Recognition of Soybean Leaf Diseases using a Conv-LSTM Model

This research presents an innovative approach for multi-class recognition of soybean leaf diseases using a Convolutional Long Short-Term Memory (Conv-LSTM) model. The model integrates the spatial learning capabilities of convolutional layers with the temporal dependencies of LSTM units, addressing the critical need for accurate disease detection in agriculture, particularly in soybean cultivation where leaf diseases significantly impact crop yield and quality. Through comparative experiments with established deep learning models such as AlexNet, VGG16, and ResNet50, the Conv-LSTM model demonstrates superior performance in terms of accuracy, precision, recall, and F1 score. By effectively capturing both spatial and temporal features in soybean leaf images, the Conv-LSTM model showcases its potential to enhance disease detection accuracy, supporting precision agriculture practices and enabling timely interventions to mitigate crop losses caused by diseases.

Unravelling Species Diversity and Pathogenicity of Fusarium spp. Associated with Soybean Leaf and Root in Heilongjiang Province, China.

Soybean (Glycine max L.) holds significant global importance and is extensively cultivated in Heilongjiang Province, China. Soybean can be infected by Fusarium species, causing root rot, seed decay, stem rot, and leaf blight. In 2021 to 2022, a field survey of soybean diseases was carried out in 11 regions of Heilongjiang Province, and 186 soybean leaves with leaf blight symptoms and 123 soybean roots with root rot symptoms were collected. Unexpectedly, a considerable number of Fusarium isolates were obtained not only from root samples but also from leaf samples. A total of 584 Fusarium isolates (416 from leaves and 168 from roots) were obtained and identified as 18 Fusarium species based on morphological features and multilocus phylogenetic analyses with tef1 and rpb2 sequences. Fusarium graminearum and Fusarium sp. 1 in FOSC were the dominant species within soybean leaf and root samples, respectively. Pathogenicity tests were conducted for all Fusarium isolates on both soybean leaves and roots. Results showed that F. graminearum, F. ipomoeae, F. citri, F. compactum, F. flagelliforme, F. acuminatum, and F. sporotrichioides were pathogenic to both soybean leaves and roots. F. solani, F. avenaceum, F. pentaseptatum, F. serpentinum, F. annulatum, and Fusarium sp. 1 in FOSC were pathogenic to soybean roots, not to leaves. To our knowledge, this is the first study to thoroughly investigate soybean-associated Fusarium populations in leaves and roots in Heilongjiang Province.

α-Tocopherol mediates alleviation of salt stress effects in Glycine max through up-regulation of the antioxidant defense system and secondary metabolites

α-Tocopherol (αT) has been reported to overcome the adverse effects of many environmental stresses, including salinity. A pot experiment was performed to investigate the response of salt-stressed soybean plants to the foliar application using 50, 100, or 200 mg αT L–1. The stress was applied by irrigation with three different dilutions of seawater [e.g., EC = 0.23 (tap water as a control), 3.13, or 6.25 dS m–1]. The gradual increase in salinity level gradually increased net carbon dioxide (CO2) assimilation, relative growth rate, antioxidant capacity, secondary metabolites (total phenolic compounds, flavonoids, and tannins), enzymatic activities, and DNA fragmentation due to the gradual increase in lipid peroxidation as a result of an increase in hydrogen peroxide (H2O2). On the contrary, yield components (number and weight of seeds plant–1) and photosynthetic pigment (total chlorophyll and carotenoids) contents gradually decreased with increasing salinity level. However, leaf treatment with αT, especially at 200 mg αT L‒1, preserved the highest antioxidant activities (antioxidant capacity, secondary metabolites, and enzymes), which were associated with the preservation of soybean yield and leaf pigments. These positive results occurred due to the reduction in lipid peroxidation as a result of a significant decrease in the level of H2O2. Therefore, our results recommend the use of 200 mg αT L–1 as a commercial formula for soybeans grown under saline irrigation of no more than 6.25 dS m–1.

Morphological and Molecular Analysis of Two Mycophagous Nematodes, Aphelenchoides bicaudatus and A. rutgersi (Nematoda: Aphelenchoididae) from Florida Strawberry.

From 2016 to 2021, nematode surveys in Florida strawberry fields revealed several species of foliar nematodes (Aphelenchoides spp.). Aphelenchoides besseyi sensu stricto was detected only in 2016 and 2017 on photosynthetic strawberry leaves/buds, but other not well characterized populations of Aphelenchoides sp. were found on declining/dessicated leaves. Morphological analyses showed that these samples of Aphelenchoides sp. consisted of A. bicaudatus, a species detected in Florida for the first time, and A. rutgersi, a species previously reported in Florida from the citrus rhizosphere. These two species differed from A. besseyi in the shape of their tail terminus: bifurcate in A. bicaudatus; mucronate with a ventral thin mucro in A. rutgersi; and stellate in A. besseyi. One population each of these species was used for morphological and molecular analyses after being reared on Monilinia fructicola. Body and tail length differences were observed among Florida A. bicaudatus and other populations from the Far East and South Africa. Phylogenetic analyses of the rRNA gene sequences showed that Florida A. bicaudatus grouped with those of species from South Korea, Taiwan, and the Netherlands and several other populations listed as Aphelenchoides sp. from Brazil, Costa Rica, and Japan, which were considered as representatives of A. bicaudatus in this study. Similarly, sequences of Florida A. rutgersi grouped with those from environmental samples in Japan and North Carolina, which were listed as Aphelenchoides sp. and were considered as representatives of A. rutgersi in this study. Photosynthetic strawberry leaf samples were free from both A. bicaudatus and A. rutgersi, indicating that these two species did not damage strawberry. They were associated with desiccated leaves and/or propagative stolons, usually infected by fungi, confirming that they are mycetophagous under field conditions in this study. Results of soybean leaf inoculation on moist filter paper containing A. bicaudatus specimens showed that this species could become phytophagous under artificial conditions. Nematodes penetrated the leaf epidermis and migrated into the mesophyll causing leaf tissue discoloration/necrosis, which remained localized within the infested area. Soybean leaf damage was almost negligible, and no nematode reproduction was observed in the inoculated soybean areas.

Quality control of Bradyrhizobium inoculant strains: detection of nosZ and correlation of symbiotic efficiency with soybean leaf chlorophyll levels

Greenhouse gas emissions, such as N2O from excessive N-fertilizer use, are of concern. Symbiotic N2-fixation by pulses such as soybean might mitigate this issue, for which inoculants carrying locally adapted Bradyrhizobium strains are recommended. In the frame of this goal, enhancing the quality control of these inoculants is required on two key aspects: determining the presence of nosZ, for the strains being able to reduce N2O, and assessing N2-fixation potential. Previously it was demonstrated that, in soybean leaves, N-contents are well correlated with chlorophyll contents. However, no such correlations were made with either N obtained from N2-fixation or with nodules mass, which is an indicator of nodular activity. Here we aimed to leverage the correlation between N and chlorophyll levels to develop a simple and non-destructive laboratory method to be applied in quality control of inoculants, able to assess the N2-fixing capacity of rhizobial strains. To establish such correlations, we cultivated soybeans in vermiculite with N-free nutrient solution, and inoculated them with various Bradyrhizobium field isolates that displayed a range of symbiotic N2-fixing capacities. Subsequently, we measured chlorophyll with a portable chlorophyllometer, and correlated these measures with symbiotic parameters. Moreover, we tested for the presence of nosZ by PCR. We observed significant correlations between chlorophyll and shoot nitrogen obtained from N2-fixation and, in addition, we corroborated that chlorophyll contents were significantly correlated also with nodules mass. Two B. diazoefficiens strains stood out and possessed nosZ. In contrast, B. elkanii and B. japonicum isolates displayed lower chlorophyll and symbiotic performance, and lacked nosZ. Our findings highlight the potential of measuring chlorophyll contents and testing for the presence of nosZ as two straightforward techniques that may enhance laboratory tests for quality control, enabling selection of superior and safe locally isolated strains for soybean inoculants without increased production costs.

Application of hyperspectral technology for leaf function monitoring and nitrogen nutrient diagnosis in soybean (Glycine max L.) production systems on the Loess Plateau of China

Farmland mulching and nitrogen application are the main agricultural management measures to improve soybean (Glycine max L.) production in dryland agriculture on the Loess Plateau. However, the interaction effects of various farmland mulching materials and nitrogen application rates on soybean leaf functionality and nitrogen nutrition status remains contradictory and inconclusive, and effective and rapid diagnostic of the leaf functionality and nitrogen status are still not well-understood. Therefore, the aim of this study is twofold: 1) to investigate the interactive effects of different mulching methods and nitrogen application levels on soybean leaf growth, physiological traits, and final grain yield throughout the entire growth period; 2) to establish a chlorophyll content monitoring model based on spectral parameters and a diagnostic model for soybean nitrogen status, and to assess the effectiveness of the latter in accurately diagnosing soybean nitrogen requirements. A two-year (2021 and 2022) field experiment, which consisted of four nitrogen levels (0, 60, 120 and 180 kg N ha−1) and four mulching strategies (NM: no mulching, SM: straw mulching, FM: film mulching, SFM: straw and film mulching), was conducted in the soybean growing seasons. Subsequently, nitrogen dilution curves were established based on chlorophyll content and the optimal spectral index to compute corresponding nitrogen nutrition index (NNI) values. The results indicated that: 1) FM, in comparison to SM and SFM, had the ability to delay leaf senescence, increase chlorophyll content, and improve physiological growth parameters, thereby increasing seed yield; 2) the application of 120 kg N ha−1 stood out, boosting soybean photosynthetic productivity and providing a solid foundation for high soybean yields; 3) the Random forest (RF) model had the highest accuracy in chlorophyll content estimation (R2 =0.854, RMSE=2.765 and MRE=5.758 % in validation set); and 4) both the nitrogen dilution curves constructed based on chlorophyll content and the optimal spectral index proved to be reasonably accurate in quantitatively diagnosing the nitrogen status of soybeans. Specifically, N0 and N180 indicated sustained nitrogen deficiency and excess, respectively, while N60 and N120 effectively met soybean's nitrogen requirements. In summary, the FMN120 effectively stabilized seed yield by regulating key functional traits in soybean leaves. This study provides a theoretical basis for the application of precision agriculture and remote sensing technology in monitoring and diagnosing plant nitrogen nutrition in soybean production.

Response of Evapotranspiration, Photosynthetic Characteristics and Yield of Soybeans to Groundwater Depth

To clarify the physiological mechanism of different groundwater depths affecting soybean evapotranspiration, photosynthetic characteristics and yield, a field experiment with four groundwater depth levels (1 m (D1), 2 m (D2), 3 m (D3) and 4 m (D4)) was conducted through the groundwater simulation system in 2021 and 2022. In this study, a quantitative analysis was conducted on the groundwater recharge and irrigation water demand and evapotranspiration (ET) of soybean fields with different treatments, and the effects of different treatments on soybean leaf area index (LAI), chlorophyll content index (SPAD), intercepted photosynthetic active radiation (IPAR), photosynthetic gas exchange parameters, dry matter accumulation (DMA) and yield were explored. The results showed the following: (1) Groundwater depth affected soybean ET and the source of ET. With the increase in groundwater depth, groundwater recharge and its contribution to ET gradually decreased, but the amount of irrigation required gradually increased, resulting in the ET as D1 > D4 > D2 > D3. (2) Soybean LAI, SPAD and IPAR were significantly affected by the different groundwater depths, of which the D1 treatment always maintained the maximum, followed by the D4 treatment, and the D3 treatment was the minimum. The photosynthetic gas exchange parameters under different treatments changed synergistically, showing significant differences in the flowering and podding stages, notably D1 > D4 > D2 > D3. Soybean DMA and yield first decreased and then increased with the increase in groundwater depth, and the average DMA and yield under the D1 treatment increased by 27.71%, 46.80% and 22.82% and 20.29%, 29.91% and 12.83% in the two years, respectively, compared to the D2, D3 and D4 treatments. (3) The structural equation model demonstrated that the groundwater depth indirectly affected the growth of soybean leaf area by affecting groundwater recharge, which in turn regulated soybean ET and photosynthetic capacity and ultimately affected DMA and yield. The above results showed that in the case of shallow groundwater depth (D1), the largest groundwater recharge promoted the growth of soybean leaf area and chlorophyll synthesis and increased the absorption and utilization of solar radiation. And it improved the leaf stomata conditions, accelerated the gas exchange between the plant and atmosphere, enhanced the photosynthetic production capacity and ET and achieved maximum DMA and yield. Soybean leaf growth and photosynthesis diminish with the increase in groundwater depth. In the case of deep groundwater depth (D4), the maximum irrigation improved the growth and photosynthetic performance of soybean leaves, which was favorable to ET, and ultimately led to increases in DMA and yield.

Weed detection in soybean fields using improved YOLOv7 and evaluating herbicide reduction efficacy.

With the increasing environmental awareness and the demand for sustainable agriculture, herbicide reduction has become an important goal. Accurate and efficient weed detection in soybean fields is the key to test the effectiveness of herbicide application, but current technologies and methods still have some problems in terms of accuracy and efficiency, such as relying on manual detection and poor adaptability to some complex environments. Therefore, in this study, weeding experiments in soybean fields with reduced herbicide application, including four levels, were carried out, and an unmanned aerial vehicle (UAV) was utilized to obtain field images. We proposed a weed detection model-YOLOv7-FWeed-based on improved YOLOv7, adopted F-ReLU as the activation function of the convolution module, and added the MaxPool multihead self-attention (M-MHSA) module to enhance the recognition accuracy of weeds. We continuously monitored changes in soybean leaf area and dry matter weight after herbicide reduction as a reflection of soybean growth at optimal herbicide application levels. The results showed that the herbicide application level of electrostatic spraying + 10% reduction could be used for weeding in soybean fields, and YOLOv7-FWeed was higher than YOLOv7 and YOLOv7-enhanced in all the evaluation indexes. The precision of the model was 0.9496, the recall was 0.9125, the F1 was 0.9307, and the mAP was 0.9662. The results of continuous monitoring of soybean leaf area and dry matter weight showed that herbicide reduction could effectively control weed growth and would not hinder soybean growth. This study can provide a more accurate, efficient, and intelligent solution for weed detection in soybean fields, thus promoting herbicide reduction and providing guidance for exploring efficient herbicide application techniques.

Monitoring of Nitrogen Concentration in Soybean Leaves at Multiple Spatial Vertical Scales Based on Spectral Parameters.

Nitrogen is a fundamental component for building amino acids and proteins, playing a crucial role in the growth and development of plants. Leaf nitrogen concentration (LNC) serves as a key indicator for assessing plant growth and development. Monitoring LNC provides insights into the absorption and utilization of nitrogen from the soil, offering valuable information for rational nutrient management. This, in turn, contributes to optimizing nutrient supply, enhancing crop yields, and minimizing adverse environmental impacts. Efficient and non-destructive estimation of crop LNC is of paramount importance for on-field crop management. Spectral technology, with its advantages of repeatability and high-throughput observations, provides a feasible method for obtaining LNC data. This study explores the responsiveness of spectral parameters to soybean LNC at different vertical scales, aiming to refine nitrogen management in soybeans. This research collected hyperspectral reflectance data and LNC data from different leaf layers of soybeans. Three types of spectral parameters, nitrogen-sensitive empirical spectral indices, randomly combined dual-band spectral indices, and "three-edge" parameters, were calculated. Four optimal spectral index selection strategies were constructed based on the correlation coefficients between the spectral parameters and LNC for each leaf layer. These strategies included empirical spectral index combinations (Combination 1), randomly combined dual-band spectral index combinations (Combination 2), "three-edge" parameter combinations (Combination 3), and a mixed combination (Combination 4). Subsequently, these four combinations were used as input variables to build LNC estimation models for soybeans at different vertical scales using partial least squares regression (PLSR), random forest (RF), and a backpropagation neural network (BPNN). The results demonstrated that the correlation coefficients between the LNC and spectral parameters reached the highest values in the upper soybean leaves, with most parameters showing significant correlations with the LNC (p < 0.05). Notably, the reciprocal difference index (VI6) exhibited the highest correlation with the upper-layer LNC at 0.732, with a wavelength combination of 841 nm and 842 nm. In constructing the LNC estimation models for soybeans at different leaf layers, the accuracy of the models gradually improved with the increasing height of the soybean plants. The upper layer exhibited the best estimation performance, with a validation set coefficient of determination (R2) that was higher by 9.9% to 16.0% compared to other layers. RF demonstrated the highest accuracy in estimating the upper-layer LNC, with a validation set R2 higher by 6.2% to 8.8% compared to other models. The RMSE was lower by 2.1% to 7.0%, and the MRE was lower by 4.7% to 5.6% compared to other models. Among different input combinations, Combination 4 achieved the highest accuracy, with a validation set R2 higher by 2.3% to 13.7%. In conclusion, by employing Combination 4 as the input, the RF model achieved the optimal estimation results for the upper-layer LNC, with a validation set R2 of 0.856, RMSE of 0.551, and MRE of 10.405%. The findings of this study provide technical support for remote sensing monitoring of soybean LNCs at different spatial scales.

Vesicle-coacervate-driven efficient deposition of a sprayed droplet on hydrophobic soybean leaf surfaces

The inherent superhydrophobicity of a plant's leaves results in a low deposition efficiency of pesticides used to improve crop production.

Eco-Friendly Silver Nanoparticles Synthesized from a Soybean By-Product with Nematicidal Efficacy against Pratylenchus brachyurus.

This study explores an eco-friendly approach to synthesizing silver nanoparticles (AgNPs) using soybean leaf extracts, employing a reaction with silver nitrate at 65 °C for 2.5 h. Optimal results were achieved at extract concentrations of 3.12 and 6.25 mg of the leaf mL-1, termed 3.12AgNP and 6.25AgNP, respectively. UV-Vis spectrophotometric analysis between 350 and 550 nm exhibited a peak at 410-430 nm, along with a color transition in the suspensions from pale yellow to brown, indicating successful synthesis. Dynamic light scattering (DLS) further delineated the favorable properties of these AgNPs, including nanometric dimensions (73-104 nm), negative charge, and moderate polydispersity, portraying stable and reproducible synthesis reactions. The bioreduction mechanism, possibly expedited by leaf extract constituents such as amino acids, phenolic acids, and polysaccharides, remains to be fully elucidated. Notably, this study underscored the potent nematicidal effectiveness of biosynthesized AgNPs, especially 6.25AgNP, against Pratylenchus brachyurus, which is a common plant-parasitic nematode in tropical soybean cultivation regions. In vitro tests illustrated significant nematicidal activity at concentrations above 25 µmol L-1, while in vivo experiments displayed a pronounced nematode population diminishment in plant roots, particularly with a 6.25AgNP rhizosphere application at concentrations of 500 µmol L-1 or twice at 250 µmol L-1, attaining a reproduction factor below 1 without any morphological nematode alterations. This research highlights the potential of 6.25AgNPs derived from soybean leaf extracts in forging sustainable nematicidal solutions, marking a significant stride toward eco-friendly phytonematode management in soybean cultivation. This novel methodology signals a promising avenue in harnessing botanical resources for nematode control and propelling a greener agricultural horizon.

Deep Learning Model for Classifying and Evaluating Soybean Leaf Disease Damage.

Soybean (Glycine max (L.) Merr.) is a major source of oil and protein for human food and animal feed; however, soybean crops face diverse factors causing damage, including pathogen infections, environmental shifts, poor fertilization, and incorrect pesticide use, leading to reduced yields. Identifying the level of leaf damage aids yield projections, pesticide, and fertilizer decisions. Deep learning models (DLMs) and neural networks mastering tasks from abundant data have been used for binary healthy/unhealthy leaf classification. However, no DLM predicts and categorizes soybean leaf damage severity (five levels) for tailored pesticide use and yield forecasts. This paper introduces a novel DLM for accurate damage prediction and classification, trained on 2930 near-field soybean leaf images. The model quantifies damage severity, distinguishing healthy/unhealthy leaves and offering a comprehensive solution. Performance metrics include accuracy, precision, recall, and F1-score. This research presents a robust DLM for soybean damage assessment, supporting informed agricultural decisions based on specific damage levels and enhancing crop management and productivity.

Machine learning algorithm for soybean leaf disease detection

Agriculture is now the primary source of income for nearly 45% of India's population. This makes it important to aid farmers with crop cultivation, protection, and harvesting. Soybean is one of the most widely grown plants in India, especially in the states of Madhya Pradesh and Maharashtra. But soybean crops are prone to diseases like yellow mosaicand anthracnose, amongst others. We propose hybrid deep learning algorithm to detect diseases in soybean plant leavesusing computer vision techniques. In the experimentation, various classification algorithms were compared using accuracy.

Genome-Wide Identification and Comprehensive Analysis of the FtsH Gene Family in Soybean (Glycine max)

The filamentation temperature-sensitive H (FtsH) gene family is critical in regulating plant chloroplast development and photosynthesis. It plays a vital role in plant growth, development, and stress response. Although FtsH genes have been identified in a wide range of plants, there is no detailed study of the FtsH gene family in soybean (Glycine max). Here, we identified 34 GmFtsH genes, which could be categorized into eight groups, and GmFtsH genes in the same group had similar structures and conserved protein motifs. We also performed intraspecific and interspecific collinearity analysis and found that the GmFtsH family has large-scale gene duplication and is more closely related to Arabidopsis thaliana. Cis-acting elements analysis in the promoter region of the GmFtsH genes revealed that most genes contain developmental and stress response elements. Expression patterns based on transcriptome data and real-time reverse transcription quantitative PCR (qRT-PCR) showed that most of the GmFtsH genes were expressed at the highest levels in leaves. Then, GO enrichment analysis indicated that GmFtsH genes might function as a protein hydrolase. In addition, the GmFtsH13 protein was confirmed to be localized in chloroplasts by a transient expression experiment in tobacco. Taken together, the results of this study lay the foundation for the functional determination of GmFtsH genes and help researchers further understand the regulatory network in soybean leaf development.

Fast and low-cost method for direct and simultaneous determination of nitrogen and carbon in soybean leaves using benchtop and portable near-infrared devices.

The current techniques for determining carbon and nitrogen content to provide information about the nutritional status of plants are time-consuming and expensive. For this reason, the objective of this study was to develop an analytical method for the direct and simultaneous determination of nitrogen and carbon elemental content in soybean leaves using near-infrared spectroscopy and compare the performance of conventional (1100-2500 nm spectral range) and portable equipment (1100-1700 nm spectral range). Partial least-squares regression models were developed using 27 soybean leaf samples collected during the 2021 harvest and applied for the simultaneous determination of carbon and nitrogen in 13 samples collected during the 2022 harvest. The root-mean-square error of prediction values for nitrogen and carbon were low (2.42 g kg-1 and 4.37 g kg-1 respectively) for the benchtop method yielded low but higher for the portable method (3.82 g kg-1 and 10.7 g kg-1 respectively). The benchtop method did not show significant differences when compared with the reference method for determining nitrogen and carbon. In contrast, the portable methodology showed potential as a screening method for determining nitrogen levels, particularly in fieldwork. The methodologies evaluated in this study were implemented and evaluated under real crop monitoring conditions, using independent sets of calibration and prediction samples. Their utilization enables the acquisition of cost-effective, safe analytical data aligning with the principles of green analytical chemistry. © 2023 Society of Chemical Industry.

Soybean Leaf Diseases Recognition Based on Generative Adversarial Network and Transfer Learning

Soybean leaf disease labeling data are not easy to obtain, and soybean leaf disease model training often needs a lot of data. Due to the limitations of fixed rules such as rotation and clipping, traditional data enhancement cannot generate images with diversity and variability. In view of the above problems, this study proposed a data enhancement method based on generative adversarial network to expand the original soybean leaf disease dataset. This method was based on cyclic confrontation network, and its discriminator uses dense connection strategy to realize feature reuse, so as to reduce the amount of calculation. In the training process, improved transfer learning is used to automatically fine tune the pre-training model. The accuracy of the optimized method in 9 kinds of soybean leaf disease image recognition is 95.84%, which is 0.98% higher than the traditional fine-tuning method. The experimental results show that this method based on generating confrontation network has significant ability in generating soybean leaf disease image, and can expand the existing dataset. In addition, this method also provides an effective data enhancement solution for the expansion of other crop disease image datasets.

A Comprehensive Review on Multi-Class Recognition of Soybean Leaf Diseases

This paper presents a comprehensive review of the current state-of-the-art methodologies in the multi-class recognition of soybean leaf diseases, addressing the challenges faced by soybean cultivation globally. Focusing on diseases like rust, bacterial blight, anthracnose, and powdery mildew, the review encompasses traditional image processing techniques as well as modern advancements in deep learning, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs). Topics covered include dataset compilation, preprocessing, feature extraction, and the application of various machine learning algorithms. Special emphasis is placed on exploring the potential of transfer learning, domain adaptation, and the integration of spectral imaging and remote sensing technologies for enhanced disease detection. By providing a thorough comparative analysis, this review aims to guide future research efforts, aiding researchers, agronomists, and practitioners in developing robust and scalable solutions to combat soybean leaf diseases and improve global agricultural productivity.