Soybean Genotypes Research Articles

Combining AMMI and BLUP analysis to select high‐yielding soybean genotypes in Benin

AbstractThirty soybean [Glycine max (L.) Merr.] genotypes, along with three checks, were evaluated over three seasons across five communes in Benin. The experiments were laid out in an alpha lattice design with three replicates. Additive multiplicative mean interaction (AMMI) and best linear unbiased predictor (BLUP) analysis were combined to assess differential agronomic performance and yield stability among genotypes. There was significant variation (p < 0.001) between genotypes for all traits, with highly significant environmental and genotype × environment interaction (GEI) effects on soybean grain yield (p < 0.001). The likelihood ratio test indicated that both genotype and interaction effects were highly significant (p < 0.001). The low R2 (0.21) for GEI reflected the presence of high residual variation in the GEI component, in contrast to the AMMI analysis of variance, which explained a high proportion of the GEI through the first two interaction principal component axes (52%). The very high value of the predictive accuracy (0.89) confirmed the model's reliability in selecting superior genotypes. The low (0.33) genotypic correlation between environments indicated that it was difficult to select superior genotypes for each environment. Based on the superiority index (weighted average absolute scores from BLUP for yield) of BLUP, simultaneous selection led to the identification of Jenguma 2.67 ± 0.06 t ha−1 as the most stable and productive genotype across environments, followed by Favour 2.34 ± 0.08 t ha−1, and Afayak 2.46 ± 0.08 t ha−1. The agronomic performance of soybean in this study suggested great potential for diversifying cotton‐based cropping systems in Benin, thereby improving their sustainability. The effect of these soybean genotypes on the productivity of intercrop combinations and sequences of cash crops, such as cotton, is yet to be investigated.

MORPHO-PHYSIOLOGICAL DISSECTION OF HEAT TOLERANCE IN CERTAIN POOL OF SOYBEAN GENOTYPES

Under the scenario of climate change, crop diversification through the incorporation of non-conventional oilseed crops like soybean in the cropping pattern is a need of the time. However, being native to regions having mild temperatures, soybean faces difficulty in adaptation in areas of lower latitude with high temperatures and short day lengths during growing periods. This situation directs the researchers to determine the tolerance of soybean genotypes against high temperatures and to establish a selection criterion for the identification of adaptable traits. For this purpose, a study was conducted at Oilseeds Research Institute, Faisalabad. Forty soybean genotypes including approved varieties were screened for tolerance against high temperatures in the growth chamber and glass house. At the seedling stage, genotypes were categorized into tolerant, moderately tolerant, and susceptible categories based on their STI values in the growth chamber and values of certain morpho-physiological parameters in a glass house. Considering the seed yield an ultimate goal in the adaptation process, its study is crucial in field conditions. Tolerant and moderately tolerant genotypes from previous experiments were sown in the field. Data of yield and contributing traits were recorded at maturity and subjected to analysis. Results showed great variability among genotypes for all the traits. AARI Soybean gave the best yield followed by Faisal Soybean, ORI-SOY-91, and ORI-SOY-102. All of these genotypes/varieties also performed well in terms of electrolyte leakage and leaf-relative water content. To conclude, these varieties would show better adaptation in high-temperature areas. Moreover, both the varieties along with 2 best-performing genotypes may prove to be better parents in future hybridization programs.

Identification of Resistant Genotypes against Stem Fly, Melanagromyza sojae (Zehntner) in Soybean

Background: Soybean, Glycine max has gained paramount importance in the agriculture of this country. Contribution of soybean in the oilseed basket of the world has been maximum. In India, of late, the cultivation and utilization of soybean has picked up rapidly. Insect infestation is considered to be the single largest impediment among several abiotic and biotic factors. Among them, stem fly, Melanagromyza sojae (Zehnter) is the number one pest of soybean in southern India causing infestation up to a level of 75 to 90 per cent. Hence, the study was carried out to identify the potential donar of resistance in soybean to stem fly. Methods: The trial was carried out at Main Agricultural Research Station, University of Agricultural Sciences, Dharwad, Karnataka in randomized block design (RBD) with two replications during kharif 2022 and 2023. Twenty-one soybean genotypes were screened against stem fly, M. sojae with one check variety JS 335 under in-vivo condition. Observation on seedling mortality was recorded at weekly intervals up to 30 days after germination. Stem fly incidence and stem tunneling due to stem fly at flowering and harvesting stage were recorded and percentage was worked out. Result: The pooled data of two years concluded that, the soybean genotypes DSb 34, DLSb 1, KDS 1096 and NRC 197 could be found under resistant genotype, while DLSb 3, JS 23-09, MAUS 795, NRC 195, NRC 196 and MAUS 791 as moderately resistant. JS 23-03, JS 335, VLS 102, DSb 21, RSC 11-42 and RVS 13-20 were categorized as low resistant genotypes as against SL 1282, RSC 11-35 and PS 1682 as susceptible and CAUMS-2 and AS 24 genotypes as highly susceptible irrespective of the crop growth stages.

Evaluation of soybean genotypes for resistance to collar rot (Sclerotium rolfsii) under field and glasshouse condition

Evaluation of soybean genotypes for resistance to collar rot (Sclerotium rolfsii) under field and glasshouse condition

Dry matter distribution, yield and seed quality of soybean (Glycine max) genotypes as affected by water stress

Water stress is a major constraint for crop productivity and culturing right cultivars may produce a considerable yield under such stressful condition. An experiment was conducted inside a vinyl house to evaluate the effect of water stress on dry matter distribution, yield, and seed quality of eight soybean genotypes, viz. G00006, BD2336, AGS383, PK472, BCS-1, NCS-1, BU Soybean-1 and BARI Soybean-6. They were grown in pots and subjected to water stress (20% of field capacity, FC) and control (80% of FC). The water stress reduced plant height, leaf number, leaf, stem, and root dry matter by 23, 45, 46, 45 and 19%, respectively, across the genotypes. Under water stress, the soybean genotypes G00006, BCS-1, NCS-1 and BARI Soybean-6 beard only 6 to 30% pod and 5 to 34% seed compared to the control condition. The results further indicated that yield of BD2336 and AGS383 were less affected by the stress than those of other genotypes. Interestingly, water stress exerted positive effect on seed germination, viability, speed of germination and vigor index in BD2336 and AGS383, respectively. Nitrogen and seed protein content were found the highest in BCS-1 under control (9.82 and 58.42% respectively) followed by AGS383. Phosphorus content in seed also reduced by the stress in the tested genotypes, except BD2336 (0.29% in control and 0.96% in water stress) and BARI Soybean-6. Potassium content in seed was reduced by the stress in the tested genotypes, except G00006 and BARI Soybean-6. Based on the findings related to water stress effects on yield and seed quality, particularly seed protein of the tested eight soybean genotypes, it was concluded that genotypes AGS383 and BD2336 might be considered for field trial under water deficit condition.

Determination of flavonoid and anthocyanin contents, and antioxidant activity of selected Philippine soybean (Glycine max) genotypes

Soybeans contain flavonoids and anthocyanins that are associated with health benefits related to antioxidant activities. In this study, the total flavonoid content (TFC), total anthocyanin content (TAC), and the relative antioxidant activities (AOA) of selected Philippine soybean genotypes were screened in order to select and recommend promising genotypes that may be used for further breeding and varietal development. Using the aluminum trichloride method, the genotypes POP 1-44 (TFC = 0.619 g/100 g), PHL 29272 (TFC = 0.616 g/100 g), and Tiwala 6 (TFC = 0.608 g/100 g) were determined to have the highest calculated TFC values. pH differential and 2,2-diphenyl-1-picrylhydrazyl (DPPH) assays distinguished all three black-seeded soybean genotypes PHL 29272 (TAC = 177.010 mg/100 g; AOA = 24.476%), PHL 29502 (TAC = 143.750 mg/100 g; AOA = 25.745%), and PHL 29552 (TAC = 123.572 mg/100 g; AOA = 29.297%) with the highest anthocyanin contents and relative antioxidant activities. Genotype PHL 29272 was consistently found among those with the highest results for the three tests. Significant correlations (α = 0.05) were found between flavonoid content and antioxidant activity (p < 0.0001), and between anthocyanin content and antioxidant activity (p < 0.0001). In conclusion, the study was able to identify genotypes that can be recommended as the most suitable candidates for soybean breeding activities.

Seed physiological traits and environmental factors influence seedling establishment of vegetable soybean (Glycine max L.).

Edamame (Glycine max (L.) Merr.), a specialty soybean prized for its nutritional value and taste, has witnessed a surge in demand within the U.S. However, subpar seedling stands have hindered its production potential, necessitating increased inputs for farmers. This study aims to uncover potential physiological factors contributing to low seedling emergence in edamame. We conducted comprehensive assessments on thirteen prominent edamame genotypes alongside two food-grade and two grain-type soybean genotypes, focusing on germination and emergence speed in both laboratory and field settings. Additionally, we employed single electrical conductivity tests and identified and quantified seed leachate components to distinguish among soybean types. Furthermore, using a LabField™ simulation table, we examined seed emergence across a wide soil temperature range (5°C to 45°C) for edamame and other soybean types. All seeds were produced under the same environmental conditions, harvested in Fall 2020, and stored under uniform conditions to minimize quality variations. Our findings revealed minimal divergence in emergence percentages among the seventeen genotypes, with over 95% germination and emergence in laboratory conditions and over 70% emergence in the field. Nonetheless, edamame genotypes typically exhibited slower germination speeds and higher leachate exudates containing higher soluble sugars and amino acids. Seed size did not significantly impact total emergence but was negatively correlated with germination and emergence speed, although this effect could be mitigated under complex field conditions. Furthermore, this study proposed differences that distinguish edamame from other soybean types regarding ideal and base temperatures, as well as thermal time. The finds offer valuable insights into edamame establishment, potentially paving the way for supporting local edamame production in the U.S.

Classification of Soybean Genotypes as to Calcium, Magnesium, and Sulfur Content Using Machine Learning Models and UAV–Multispectral Sensor

Making plant breeding programs less expensive, fast, practical, and accurate, especially for soybeans, promotes the selection of new soybean genotypes and contributes to the emergence of new varieties that are more efficient in absorbing and metabolizing nutrients. Using spectral information from soybean genotypes combined with nutritional information on secondary macronutrients can help genetic improvement programs select populations that are efficient in absorbing and metabolizing these nutrients. In addition, using machine learning algorithms to process this information makes the acquisition of superior genotypes more accurate. Therefore, the objective of the work was to verify the classification performance of soybean genotypes regarding secondary macronutrients by ML algorithms and different inputs. The experiment was conducted in the experimental area of the Federal University of Mato Grosso do Sul, municipality of Chapadão do Sul, Brazil. Soybean was sown in the 2019/20 crop season, with the planting of 103 F2 soybean populations. The experimental design used was randomized blocks, with two replications. At 60 days after crop emergence (DAE), spectral images were collected with a Sensifly eBee RTK fixed-wing remotely piloted aircraft (RPA), with autonomous takeoff control, flight plan, and landing. At the reproductive stage (R1), three leaves were collected per plant to determine the macronutrients calcium (Ca), magnesium (Mg), and sulfur (S) levels. The data obtained from the spectral information and the nutritional values of the genotypes in relation to Ca, Mg, and S were subjected to a Pearson correlation analysis; a PC analysis was carried out with a k-means algorithm to divide the genotypes into clusters. The clusters were taken as output variables, while the spectral data were used as input variables for the classification models in the machine learning analyses. The configurations tested in the models were spectral bands (SBs), vegetation indices (VIs), and a combination of both. The combination of machine learning algorithms with spectral data can provide important biological information about soybean plants. The classification of soybean genotypes according to calcium, magnesium, and sulfur content can maximize time, effort, and labor in field evaluations in genetic improvement programs. Therefore, the use of spectral bands as input data in random forest algorithms makes the process of classifying soybean genotypes in terms of secondary macronutrients efficient and important for researchers in the field.

Identification of New Isolates of Phytophthora sojae and Selection of Resistant Soybean Genotypes.

Phytophthora root and stem rot (PRR), caused by Phytophthora sojae, can occur at any growth stage under poorly drained and humid conditions. The expansion of soybean cultivation in South Korean paddy fields has increased the frequency of PRR outbreaks. This study aimed to identify four P. sojae isolates newly collected from domestic fields and evaluate race-specific resistance using the hypocotyl inoculation technique. The four isolates exhibited various pathotypes, with GJ3053 exhibiting the highest virulence complexity. Two isolates, GJ3053 and AD3617, were screened from 205 soybeans, and 182 and 190 genotypes (88.8 and 92.7%, respectively) were susceptible to each isolate. Among these accessions, five genotypes resistant to both isolates were selected. These promising genotypes are candidates for the development of resistant soybean cultivars that can effectively control PRR through gene stacking.

Simultaneous genetic transformation and genome editing of mixed lines in soybean (Glycine max) and maize (Zea mays)

Robust genome editing technologies are becoming part of the crop breeding toolbox. Currently, genome editing is usually conducted either at a single locus, or multiple loci, in a variety at one time. Massively parallel genomics platforms, multifaceted genome editing capabilities, and flexible transformation systems enable targeted variation at nearly any locus, across the spectrum of genotypes within a species. We demonstrate here the simultaneous transformation and editing of many genotypes, by targeting mixed seed embryo explants with genome editing machinery, followed by re-identification through genotyping after plant regeneration. Transformation and Editing of Mixed Lines (TREDMIL) produced transformed individuals representing 101 of 104 (97%) mixed elite genotypes in soybean; and 22 of 40 (55%) and 9 of 36 (25%) mixed maize female and male elite inbred genotypes, respectively. Characterization of edited genotypes for the regenerated individuals identified over 800 distinct edits at the Determinate1 (Dt1) locus in samples from 101 soybean genotypes and 95 distinct Brown midrib3 (Bm3) edits in samples from 17 maize genotypes. These results illustrate how TREDMIL can help accelerate the development and deployment of customized crop varieties for future precision breeding.

Assessment of Polygenic Traits Association with Yield in Soybean Genotypes

Soybean is one of the important oilseed crop at global level with special concern to India. Despite its global dominance, India's contribution to the soybean scene remains relatively modest, with a production ranking of fourth but only a 5% share of the world's output. For this concern, the analysis of the relationships among yield attributing characters and their associations with seed yield is essential to establish selection criteria. The experimental material used in the present study comprised of fourteen lines (8 F1s and 6 parental lines). The characters viz., number of pods/plant, primary branches/plant, harvest index, plant height, secondary branch/plant, biological yield, 100-seed weight and days-to-50% flowering recorded significant positive correlation coefficient with seed yield both at genotypic and phenotypic level. Path coefficient analysis further pinpointed 100-seed weight, harvest index, and pods per plant as the traits with the most direct positive impact on seed yield. Additionally, the study identified plant height, pods/plant, primary branches/plant, 100-seed weight, and the harvest index as the key contributors to soybean yield, suggesting these traits as primary targets for manipulation in breeding programs aimed at yield improvement.

Physiological and Molecular Analysis of Soybean Seed Longevity and Validation of Candidate Markers

Background: Seed longevity is a major constraint in soybean seed production. The major focus of this study is to analyze the physiological and molecular changes associated with seed longevity and identify promising germplasm which are good storers for soybean breeding program. Methods: Nineteen genotypes were studied for seed longevity using accelerated ageing test and genetic integrity based on SSR marker data. Genotypes were clustered into distinct groups based on seed morphological and physiological parameters (Mahalanobis D2 analysis). SSR markers for seed longevity were validated in the germplasm. Result: Per cent reduction in germination after accelerated ageing was significantly and positively correlated with traits associated with seed storability such as seed length, seed width, seed thickness and 100 seed weight and negatively correlated with seedling vigour indices. Hence, it would be worthwhile to rely upon these parameters for enhancing the seed storability in soybean. Genetic integrity of the germplasm was evaluated based on SSR markers in accelerated ageing seeds. SSR markers (Satt 285, Satt 534, Satt 538, Satt 281, Satt 162, Satt 631 and Satt 371) revealed significant association for the seed longevity characters such as seed length, seed width, seed thickness and seed weight. Candidate markers (Satt 371, Satt 281, Satt162, Satt 285, Satt 534) which can differentiate the soybean genotypes for storability have been identified in this study. The genotypes were grouped into seven clusters with monogenotypic cluster III (PSPB23) having minimum reduction in germination after accelerated ageing.

Exploring the impact of copper excess on soybean genotypes: insights from root morphology and plant ionome

ABSTRACT Global growing demand for food production and commodity increased prices stimulate soybean cultivation in Brazil even in areas with high soil copper (Cu) concentration. This can promote root injuries and nutritional imbalances, reducing the growth and yield of Cu-sensitive soybean genotypes. The study aimed to investigate soybean genotypes potentially adapted to Cu-contaminated zones. Four soybean genotypes (NA 5909, DM 5958, M 6410, and DM 6563) and three Cu concentrations in the nutrient solution (0.03, 1.2, and 2.4 mg L−1) were evaluated. Root and shoot dry mass, root morphology, and inorganic composition of plant tissues were determined. The shoot and root dry mass was affected by Cu excess, especially in DM 5958 genotype, which decreased by up to 46%. Otherwise, the DM 6563 genotype stood out for growing satisfactorily under Cu excess and keeping significant amounts of Cu in the belowground biomass. The Cu excess promoted root thickening and shortening, and altered the ionome of soybean plants by decreasing the concentrations of K, Ca, Mg, and Fe, yet increasing P and N, which caused decreased plant growth. Finally, our outcomes indicated DM 6563 genotype exhibits promising traits for Cu phytostabilization, making it preferable for cultivation in Cu-contaminated areas.

Envirotype-based delineation of environmental effects and genotype × environment interactions in Indian soybean (Glycine max, L.)

Soybean is a rainfed crop grown across a wide range of environments in India. Its grain yield is a complex trait governed by many minor genes and influenced by environmental effects and genotype × environment interactions. In the current investigation, grain yield data of different sets of 41, 30 and 48 soybean genotypes evaluated during 2019, 2020 and 2021, respectively across 19 locations and twenty years’ data on 19 different climatic parameters at these locations was used to study the environmental effects on grain yield, to understand the genotype × environment interactions and to identify the mega-environments. Through analysis of variance (ANOVA), it was found that predominant portion of the variation was explained by environmental effects (E) (53.89, 54.86 and 60.56% during 2019, 2020 and 2021, respectively), followed by genotype × environment interactions (GEI) (31.29, 33.72 and 28.82% during 2019, 2020 and 2021, respectively). Principal Component Analysis (PCA) revealed that grain yield was positively associated with RH (Relative humidity at 2 m height), FRUE (Effect of temperature on radiation use efficiency), WSM (Wind speed at 2 m height) and RTA (Global solar radiation based on latitude and Julian day) and negatively associated with VPD (Deficit of vapour pressure), Trange (Daily temperature range), ETP (Evapotranspiration), SW (Insolation incident on a horizontal surface), n (Actual duration of sunshine) and N (Daylight hours). Identification of mega-environments is critical in enhancing the selection gain, productivity and varietal recommendation. Through envirotyping and genotype main effect plus genotype by environment interaction (GGE) biplot methods, nineteen locations across India were grouped into four mega-environments (MEs). ME1 included five locations viz., Bengaluru, Pune, Dharwad, Kasbe Digraj and Umiam. Eight locations—Anand, Amreli, Lokbharti, Bidar, Parbhani, Ranchi, Bhawanipatna and Raipur were included in ME2. Kota and Morena constitutes ME3, while Palampur, Imphal, Mojhera and Almora were included in ME4. Locations Imphal, Bidar and Raipur were found to be both discriminative and representative; these test locations can be utilized in developing wider adaptable soybean cultivars. Pune and Amreli were found to be high-yielding locations and can be used in large scale breeder seed production.

Comparative Transcriptomics of Soybean Genotypes with Partial Resistance Toward Phytophthora sojae, Conrad, and M92-220 to Moderately Susceptible Fast Neutron Mutant Soybeans and Sloan.

The breeding of disease-resistant soybeans cultivars to manage Phytophthora root and stem rot caused by the pathogen Phytophthora sojae involves combining quantitative disease resistance (QDR) and Rps gene-mediated resistance. To identify and confirm potential mechanisms of QDR toward P. sojae, we conducted a time course study comparing changes in gene expression among Conrad and M92-220 with high QDR to susceptible genotypes, Sloan, and three mutants derived from fast neutron irradiation of M92-220. Differentially expressed genes from Conrad and M92-220 indicated several shared defense-related pathways at the transcriptomic level but also defense pathways unique to each cultivar, such as stilbenoid, diarylheptanoid, and gingerol biosynthesis and monobactam biosynthesis. Gene Ontology pathway analysis showed that the susceptible fast neutron mutants lacked enrichment of three terpenoid-related pathways and two cell wall-related pathways at either one or both time points, in contrast to M92-220. The susceptible mutants also lacked enrichment of potentially important Kyoto Encyclopedia of Genes and Genomes pathways at either one or both time points, including sesquiterpenoid and triterpenoid biosynthesis; thiamine metabolism; arachidonic acid; stilbenoid, diarylheptanoid, and gingerol biosynthesis; and monobactam biosynthesis. Additionally, 31 genes that were differentially expressed in M92-220 following P. sojae infection were not expressed in the mutants. These 31 genes have annotations related to unknown proteins; valine, leucine, and isoleucine biosynthesis; and protein and lipid metabolic processes. The results of this study confirm previously proposed mechanisms of QDR, provide evidence for potential novel QDR pathways in M92-220, and further our understanding of the complex network associated with QDR mechanisms in soybean toward P. sojae.

Effects of fast and slow-wilting soybean genotypes on fall armyworm (Spodoptera frugiperda) growth and development

ABSTRACT Soybean (Glycine max) is the most important plant protein source, and Fall Armyworm (FAW, Spodoptera frugiperda) is considered a major pest. This study aimed to examine the impact of FAW feeding on soybean accessions that vary in their water use efficiency (WUE) traits, by examining FAW growth and life history parameters along with plant growth response to pest damage. Soybean accessions were grown in a greenhouse and exposed to FAW larval feeding for 48 h at three different soybean growth stages: V3, R3, and R6. The growth and development of the FAW and soybeans were monitored. Results showed that faster wilting soybean accessions grow taller and have more leaves than slower wilting accessions, but yield was higher in slower wilting soybean accessions. FAW experienced the highest mortality on mid-stage (R3) soybean plants, but they gained the least mass on early stage (V3) soybean plants. These results can assist in better understanding plant insect-interactions at different life stages in both soybean and FAW with implications for management.

Comparative transcriptome analysis between two different cadmium-accumulating genotypes of soybean (Glycine max) in response to cadmium stress

BackgroundCadmium (Cd) is extremely toxic and non-essential for plants. Different soybean varieties differ greatly in their Cd accumulation ability, but little is known about the underlying molecular mechanisms.ResultsHere, we performed transcriptomic analysis using Illumina pair-end sequencing on root tissues from two soybean varieties (su8, high-Cd-accumulating (HAS) and su7, low Cd-accumulating (LAS)) grown with 0 or 50 μM CdSO4. A total of 18.76 million clean reads from the soybean root samples were obtained after quality assessment and data filtering. After Cd treatment, 739 differentially expressed genes (DEGs; 265 up and 474 down) were found in HAS; however, only 259 DEGs (88 up and 171 down) were found in LAS, and 64 genes were same between the two varieties. Pathway enrichment analysis suggested that after cadmium treatment, the DEGs between LAS and HAS were mainly enriched in glutathione metabolism and plant-pathogen interaction pathways. KEGG analysis showed that phenylalanine metabolism responding to cadmium stress in LAS, while ABC transporters responding to cadmium stress in HAS. Besides we found more differential expressed heavy metal transporters such as ABC transporters and zinc transporters in HAS than LAS, and there were more transcription factors differently expressed in HAS than LAS after cadmium treatment in two soybean varieties, eg. bHLH transcription factor, WRKY transcription factor and ZIP transcription factor.ConclusionsFindings from this study will shed new insights on the underlying molecular mechanisms behind the Cd accumulation in soybean.

Evaluation of Novel Soybean Genotypes for Yield, Yield components, Seed Quality and Resistance to Cotton Leafworm

Evaluation of Novel Soybean Genotypes for Yield, Yield components, Seed Quality and Resistance to Cotton Leafworm

Aspectos ecofisiológicos e produção de biomassa de genótipos de soja sob condições de estresse por alagamento do solo

ABSTRACT The objective of this study was to evaluate the ecophysiological aspects and biomass production of three soybean genotypes subjected to soil flooding in the vegetative and/or reproductive stages. The design adopted was completely randomized with 5 replications, in a 3 x 3 factorial arrangement, with three soybean genotypes: PELBR 17-46, PELBR 15-7016, and 75I77RSF IPRO; and three water treatment conditions: soil flooding for 10 days in the vegetative period + 10 days in the reproductive period; soil flooding for 10 days only in the reproductive period, and the control treatment, where the soil was maintained at 70% of field capacity. There was a reduction in the relative water content for the PELBR 15-7016 and PELBR 17-46 genotypes in the vegetative/reproductive stages and in the reproductive stage, while for the 75I77RSF IPRO there was no difference. The levels of chlorophyll a, chlorophyll b, and total chlorophyll were reduced only for the PELBR 15-7016 and 75I77RSF IPRO genotypes. The dry matter in the leaves and roots was lower for PELBR 17-46 and PELBR 15-7016 when subjected to stress in the R2 soybean stage and for the grain production. PELBR 17-46 and PELBR 15-7016 genotypes are more susceptible to stress, while the 75I77RSF IPRO showed mechanisms to overcome waterlogging stress.

Classification of soybean groups for grain yield and industrial traits using Vnir-Swir spectroscopy

This research aimed to evaluate the accuracy of machine learning techniques in distinguishing groups soybean genotypes according to grain industrial traits using hyperspectral reflectance of the leaves. A total of 32 soybean genotypes were evaluated and allocated in randomized blocks with four replications. At 60 days after emergence, spectral analysis was carried out on three leaf samples from each plot. The spectral analysis of the leaves was carried out with a hyperspectral sensor providing ranges from 350 to 2500 nm. Once the wavelengths were obtained, they were grouped into averages of representative intervals into bands. At the end of the crop cycle, grain yield was obtained, and subsequently the determination of carbohydrate, oil, and protein content. Initially, the genotypes were subjected to cluster analysis using the k-means algorithm and subsequently, the data was subjected to machine learning analysis, using six models: J48 Decision Trees (J48) and REPTree (DT), Random Forest (RF), Artificial Neural Networks (ANW), Logistic Regression (LR) and Support Vector Machine (SVM). Logistic regression (LR) was used as a reference point as it is a traditional regression algorithm. The clusters formed acted as the output of the models, while for the input of the models, two groups of data were used: the spectral variables (SV) obtained by the sensor (350–2500 nm) and the spectral averages of the bands selected (BS) (350–2200 nm). The use of machine learning techniques presented lower responses than the standard technique used in the work, that is, LR, which presented superiority in the classification of soybean genotypes in terms of industrial traits. The use of wavelengths provided better performance of the algorithms in the classification in relation to selected bands.