scholarly journals Application of machine learning and genetic optimization algorithms for modeling and optimizing soybean yield using its component traits

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0250665
Author(s):  
Mohsen Yoosefzadeh-Najafabadi ◽  
Dan Tulpan ◽  
Milad Eskandari
Keyword(s):  
Machine Learning ◽  
Yield Components ◽  
Soybean Seed ◽  
Complex Trait ◽  
Yield Component ◽  
Yield Potential ◽  
Coefficient Of Determination ◽  
Soybean Yield ◽  
Component Traits ◽  
Yield Component Traits

Improving genetic yield potential in major food grade crops such as soybean (Glycine max L.) is the most sustainable way to address the growing global food demand and its security concerns. Yield is a complex trait and reliant on various related variables called yield components. In this study, the five most important yield component traits in soybean were measured using a panel of 250 genotypes grown in four environments. These traits were the number of nodes per plant (NP), number of non-reproductive nodes per plant (NRNP), number of reproductive nodes per plant (RNP), number of pods per plant (PP), and the ratio of number of pods to number of nodes per plant (P/N). These data were used for predicting the total soybean seed yield using the Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Random Forest (RF), machine learning (ML) algorithms, individually and collectively through an ensemble method based on bagging strategy (E-B). The RBF algorithm with highest Coefficient of Determination (R2) value of 0.81 and the lowest Mean Absolute Errors (MAE) and Root Mean Square Error (RMSE) values of 148.61 kg.ha-1, and 185.31 kg.ha-1, respectively, was the most accurate algorithm and, therefore, selected as the metaClassifier for the E-B algorithm. Using the E-B algorithm, we were able to increase the prediction accuracy by improving the values of R2, MAE, and RMSE by 0.1, 0.24 kg.ha-1, and 0.96 kg.ha-1, respectively. Furthermore, for the first time in this study, we allied the E-B with the genetic algorithm (GA) to model the optimum values of yield components in an ideotype genotype in which the yield is maximized. The results revealed a better understanding of the relationships between soybean yield and its components, which can be used for selecting parental lines and designing promising crosses for developing cultivars with improved genetic yield potential.

scholarly journals Evaluating Genotype × Environment Interactions of Yield Traits and Adaptability in Rice Cultivars Grown under Temperate, Subtropical and Tropical Environments

Agriculture ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 558
Author(s):  
Xing Huang ◽  
Su Jang ◽  
Backki Kim ◽  
Zhongze Piao ◽  
Edilberto Redona ◽  
...  
Keyword(s):  
Yield Component ◽  
Yield Potential ◽  
High Yield ◽  
Environment Interaction ◽  
Accurate Identification ◽  
Rice Varieties ◽  
Panicle Number ◽  
Tropical Conditions ◽  
Component Traits ◽  
Yield Component Traits

Rice yield is a complex trait that is strongly affected by environment and genotype × environment interaction (GEI) effects. Consideration of GEI in diverse environments facilitates the accurate identification of optimal genotypes with high yield performance, which are adaptable to specific or diverse environments. In this study, multiple environment trials were conducted to evaluate grain yield (GY) and four yield-component traits: panicle length, panicle number, spikelet number per panicle, and thousand-grain weight. Eighty-nine rice varieties were cultivated in temperate, subtropical, and tropical regions for two years. The effects of both GEI (12.4–19.6%) and environment (23.6–69.6%) significantly contributed to the variation of all yield-component traits. In addition, 37.1% of GY variation was explained by GEI, indicating that GY performance was strongly affected by the different environmental conditions. GY performance and genotype stability were evaluated using simultaneous selection indexing, and 19 desirable genotypes were identified with high productivity and broad adaptability across temperate, subtropical, and tropical conditions. These optimal genotypes could be recommended for cultivation and as elite parents for rice breeding programs to improve yield potential and general adaptability to climates.

scholarly journals Synergistic effect of P and K interaction on yield and yield components of mungbean (Vigna radiata (L.) Wilczek) varieties

2021 ◽  
Vol 45 (1) ◽  
Author(s):  
E. M. Abd El Lateef ◽  
Asal M. Wali ◽  
M. S. Abd El-Salam
Keyword(s):  
Synergistic Effect ◽  
Seed Yield ◽  
Yield Components ◽  
Field Experiments ◽  
Fertilizer Application ◽  
Yield Component ◽  
Beneficial Effects ◽  
Yield And Yield Components ◽  
Component Traits ◽  
Yield Component Traits

Abstract Background The relation between the macronutrients P and K seems to be synergistic due to the beneficial effects of the interaction between (P × K) and varies according to the variety used. Therefore, two field experiments were conducted during 2018 and 2019 summer seasons to study the effect of interaction of phosphatic fertilization at 0, 37.5 and 75 kg P2O5 ha−1 and potassic fertilization at 0 and 57.6 kg K2O ha−1 on the yield and yield components of two mungbean varieties, viz. Kawmy-l and V2010, as well as determining the relationship between the two nutrients interaction. Results The results showed that there were varietal differences in yield and yield components regardless fertilizer application. Either phosphatic or potassic fertilization significantly increased mungbean yield and yield components traits. Significant effects due to the interaction (V × P) were reported on yield component traits in both seasons. Furthermore, the triple interaction (V × P × K) indicates that synergistic effect was reported for the two varieties and was more clearer for V2010 where it needed both of P and K nutrients to out yield the greatest seed yield ha−1, while Kawmy-1 gave the greatest seed yield ha−1 without K application. Conclusion It could be concluded from this study that mungbean varieties differ in their response to the synergistic interaction effect of P and K and the combination of 75 kg P2O5 + 57.6 kg K2O is preferable for V2010 and 75 kg P2O5 alone for Kawmy-1 to produce the greatest yield.

Genetic analysis of grain yield conditioned on its component traits in rice (Oryza sativa L.)

2008 ◽  
Vol 59 (2) ◽  
pp. 189 ◽  
Author(s):  
G. F. Liu ◽  
J. Yang ◽  
H. M. Xu ◽  
Y. Hayat ◽  
J. Zhu
Keyword(s):  
Grain Yield ◽  
Yield Components ◽  
Genetic Relationships ◽  
Mapping Method ◽  
Yield Component ◽  
Doubled Haploid Population ◽  
Environment Interaction ◽  
Panicle Number ◽  
Component Traits ◽  
Yield Component Traits

Grain yield (GY) of rice is a complex trait consisting of several yield components. It is of great importance to reveal the genetic relationships between GY and its yield components at the QTL (quantitative trait loci) level for multi-trait improvement in rice. In the present study, GY per plant in rice and its 3 yield component traits, panicle number per plant (PN), grain number per panicle (GN), and 1000-grain weight (GW), were investigated using a doubled-haploid population derived from a cross of an indica variety IR64 and a japonica variety Azucena. The phenotypic values collected from 2 cropping seasons were analysed by QTLNetwork 2.0 for mapping QTLs with additive (a) and/or additive × environment interaction (ae) effects. Furthermore, conditional QTL analysis was conducted to detect QTLs for GY independent of yield components. The results showed that the general genetic variation in GY was largely influenced by GN with the contribution ratio of 29.2%, and PN and GN contributed 10.5% and 74.6% of the genotype × environment interaction variation in GY, respectively. Four QTLs were detected with additive and/or additive × environment interaction effects for GY by the unconditional mapping method. However, for GY conditioned on PN, GN, and GW, 6 additional loci were identified by the conditional mapping method. All of the detected QTLs affecting GY were associated with at least one of the 3 yield components. The results revealed that QTL expressions of GY were contributed differently by 3 yield component traits, and provide valuable information for effectively improving GY in rice.

scholarly journals QTL mapping for grain yield and three yield components in a population derived from two high-yielding spring wheat cultivars

2021 ◽  
Author(s):  
Kyle Isham ◽  
Rui Wang ◽  
Weidong Zhao ◽  
Justin Wheeler ◽  
Natalie Klassen ◽  
...  
Keyword(s):  
Grain Yield ◽  
Spring Wheat ◽  
Yield Components ◽  
Heading Date ◽  
Kernel Weight ◽  
Yield Component ◽  
Six Traits ◽  
Component Traits ◽  
Yield Component Traits ◽  
Spikelet Number Per Spike

Abstract Key message Four genomic regions on chromosomes 4A, 6A, 7B, and 7D were discovered, each with multiple tightly linked QTL (QTL clusters) associated with two to three yield components. The 7D QTL cluster was associated with grain yield, fertile spikelet number per spike, thousand kernel weight, and heading date. It was located in the flanking region of FT-D1, a homolog gene of Arabidopsis FLOWERING LOCUS T, a major gene that regulates wheat flowering. Abstract Genetic manipulation of yield components is an important approach to increase grain yield in wheat (Triticum aestivum). The present study used a mapping population comprised of 181 doubled haploid lines derived from two high-yielding spring wheat cultivars, UI Platinum and LCS Star. The two cultivars and the derived population were assessed for six traits in eight field trials primarily in Idaho in the USA. The six traits were grain yield, fertile spikelet number per spike, productive tiller number per unit area, thousand kernel weight, heading date, and plant height. Quantitative Trait Locus (QTL) analysis of the six traits was conducted using 14,236 single-nucleotide polymorphism (SNP) markers generated from the wheat 90 K SNP and the exome and promoter capture arrays. Of the 19 QTL detected, 14 were clustered in four chromosomal regions on 4A, 6A, 7B and 7D. Each of the four QTL clusters was associated with multiple yield component traits, and these traits were often negatively correlated with one another. As a result, additional QTL dissection studies are needed to optimize trade-offs among yield component traits for specific production environments. Kompetitive allele-specific PCR markers for the four QTL clusters were developed and assessed in an elite spring wheat panel of 170 lines, and eight of the 14 QTL were validated. The two parents contain complementary alleles for the four QTL clusters, suggesting the possibility of improving grain yield via genetic recombination of yield component loci.

scholarly journals Combining Ability Analysis of Yield Components in Cucumber

2002 ◽  
Vol 127 (6) ◽  
pp. 931-937 ◽  
Author(s):  
Ana I. López-Sesé ◽  
Jack Staub
Keyword(s):  
Combining Ability ◽  
Yield Components ◽  
Block Design ◽  
Yield Component ◽  
Branch Number ◽  
Fruit Number ◽  
Horticultural Traits ◽  
Combining Ability Analysis ◽  
Component Traits ◽  
Yield Component Traits

Three U.S.-adapted Cucumis sativus var. sativus L. lines and one C. sativus var. hardwickii (R.) Alef.-derived line were crossed in a half-diallel design to determine their combining ability for several yield-related traits (yield components). Six F1 progenies were evaluated in a randomized complete block design with eight replications in 1999 and 2000 for fruit number and length/diameter ratio (L:D), lateral branch number, number of female flowering nodes, and days to anthesis. Combining ability was significantly influenced (p < 0.05) by year for most of the horticultural traits examined. General combining ability (GCA) was significant for all traits in each year. Specific combining ability (SCA) was significant in magnitude and direction for only fruit number and days to anthesis. Data indicate that the C. sativus var. hardwickii-derived inbred line WI 5551 possessed SCA for yield component traits, and thus maybe useful for improving fruit yield in commercial cucumber.

scholarly journals Principal component analyses in mungbean genotypes under summer season

2021 ◽  
Vol 17 (2) ◽  
pp. 287-292
Author(s):  
Priya Tiwari ◽  
Stuti Sharma
Keyword(s):  
Principal Component ◽  
Complex Trait ◽  
Yield Component ◽  
Plant Seed ◽  
Eigen Value ◽  
Eigen Values ◽  
Component Traits ◽  
Total Variability ◽  
Yield Component Traits ◽  
Number Of Seeds

Yield is a complex trait subjective to several components and environmental factors. Therefore, it becomes necessary to apply such technique which can identify and prioritize the key traits to lessen the number of traits for valuable selection and genetic gain. Principal component analysis is primarily a renowned data reduction technique which identifies the least number of components and explain maximum variability, it also rank genotypes on the basis of PC scores. PCA was calculated using Ingebriston and Lyon (1985) method. In present study, PCA performed for phenological and yield component traits presented that out of thirteen, only five principal components (PCs) exhibited more than 1.00 eigen value, and showed about 80.28 per cent of total variability among the traits. Scree plot explained the percentage of variance associated with each principal component obtained by illustrating a graph between eigen values and principal component numbers. PC1 showed 26.12 per cent variability with eigen value 3.40. Graph depicted that the maximum variation was observed in PC1 in contrast to other four PCs. The PC1 was further associated with the phenological and yield attributing traits viz., number of nodes per plant, number of pod cluster per plant, number of pod per plant. PC2 exhibited positive effect for harvest index. The PC3 was more related to yield related traits i.e., number of seeds per pod, number of seeds per plant and biological yield per plant, whereas PC4 was more loaded with phenological traits. PC5 was further related to yield and yield contributing traits i.e. number of primary branches per plant, seed yield per plant and 100 seed weight. A high value of PC score of a particular genotype in a particular PC denotes high value for those variables falling under that specific principal component. Pusa Vishal found in PC 2, in PC 3, PC 4 and PC 5, can be considered as an ideal breeding material for selection and for further deployment in defined breeding programme.

scholarly journals Responses of Branch Number and Yield Component of Soybean Cultivars Tested in Different Planting Densities

Agriculture ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 69
Author(s):  
Cailong Xu ◽  
Ruidong Li ◽  
Wenwen Song ◽  
Tingting Wu ◽  
Shi Sun ◽  
...  
Keyword(s):  
Key Management ◽  
Management Practices ◽  
Yield Component ◽  
Planting Density ◽  
Yield Potential ◽  
High Yield ◽  
Branch Number ◽  
Soybean Yield ◽  
Soybean Cultivars ◽  
Pod Number

Increasing planting density is one of the key management practices to enhance soybean yield. A 2-yr field experiment was conducted in 2018 and 2019 including six planting densities and two soybean cultivars to determine the effects of planting density on branch number and yield, and analyze the contribution of branches to yield. The yield of ZZXA12938 was 4389 kg ha−1, which was significantly higher than that of ZH13 (+22.4%). In combination with planting year and cultivar, the soybean yield increased significantly by 16.2%, 31.4%, 41.4%, and 46.7% for every increase in density of 45,000 plants ha−1. Yield will not increase when planting density exceeds 315,000 plants ha−1. A correlation analysis showed that pod number per plant increased with the increased branch number, while pod number per unit area decreased; thus, soybean yield decreased. With the increase of branch number, the branch contribution to yield increased first, and then plateaued. ZH13 could produce a high yield under a lower planting density due to more branches, while ZZXA12938 had a higher yield potential under a higher planting density due to the smaller branch number and higher tolerance to close planting. Therefore, seed yield can be increased by selecting cultivars with a little branching capacity under moderately close planting.

scholarly journals Genetic imprints of domestication for disease resistance, oil quality, and yield component traits in groundnut (Arachis hypogaea L.)

2018 ◽  
Vol 294 (2) ◽  
pp. 365-378 ◽  
Author(s):  
Pawan Khera ◽  
Manish K. Pandey ◽  
Nalini Mallikarjuna ◽  
Manda Sriswathi ◽  
Manish Roorkiwal ◽  
...  
Keyword(s):  
Disease Resistance ◽  
Arachis Hypogaea ◽  
Oil Quality ◽  
Yield Component ◽  
Arachis Hypogaea L ◽  
Component Traits ◽  
Yield Component Traits

scholarly journals COMPARISON OF YIELD AMONG DIFFERENT HIGH YIELDING VARIETIES OF WETLAND RICE

Agric ◽  
2021 ◽  
Vol 33 (1) ◽  
pp. 57-66
Author(s):  
Kiki Kusyaeri Hamdani ◽  
Yati Haryati
Keyword(s):  
Yield Components ◽  
Block Design ◽  
Yield Component ◽  
Yield Potential ◽  
Duncan Multiple Range Test ◽  
Rice Varieties ◽  
Randomized Complete Block Design ◽  
High Yielding Varieties ◽  
Range Test ◽  
Better Than

New superior varieties (VUB) are a reliable technological innovation to increase rice productivity. This study aims to determine the yield potential of some lowland rice VUB. The assessment was carried out on land owned by a member of the Sumber Rejeki Farmer Group, Cintaratu Village, Lakbok District, Ciamis Regency at Dry Season II in June-September 2020. The study used a randomized complete block design (RCBD) with six varieties of treatment and was repeated ten times. The varieties tested were Inpari 32, Inpari 42, Padjadjaran, Cakrabuana, Inpari IR Nutrizinc, and Siliwangi varieties. The variables observed included the growth component, yield component, and yield component. Data were analyzed using the F test followedby the Duncan Multiple Range Test at the Q=5% level. In addition, a correlation test was conducted between the growth components, yield components, and yields. The results of the study indicated that the new superior rice varieties studied had different performance in growth, number of tillers, yield, and yield components. Inpari 42 variety produced the highest productivity, namely 6.88 ton ha-1 which was supported by the number of grains per panicle, percentage of filled grains per panicle, and percentage of empty grain per panicle which were better than other varieties. Plant height and number of grains per panicle were positively correlated with yield.

Sign in / Sign up

Export Citation Format

Share Document