Filters
Agro-morphological characterization and machine learning-based prediction of genetic diversity in six-row barley genotypes from Türkiye
Abstract The restricted genetic diversity observed in modern barley represents a significant obstacle to enhancing productivity. This study addresses this issue by characterising 445 six-row barley genotypes from the Osman Tosun Gene Bank in Türkiye. A comprehensive analysis of 22 agro-morphological traits, comprising 11 qualitative and 11 quantitative traits, was conducted to explore morphological, growth and phenological diversity. Principal component analysis identified four principal components, which collectively explained 72.86% of the total variance. Of these, the first two components accounted for 52.45%. Based on agro-morphological similarities, the genotypes were grouped into seven clusters. Clusters 5, 6, and 7 contained genotypes with high-yield traits, including early maturity, increased grain per spike, and higher thousand grain weight. The findings contribute directly to the expansion of the barley gene pool. Moreover, this study provides a comprehensive characterisation of the hitherto overlooked six-row barley germplasm present in Türkiye. This offers invaluable genetic resources for future breeding and molecular studies. Furthermore, the study compares the performance of three machine learning models (XGBoost, MARS, and Gaussian Processes) in predicting the harvest index from various traits. The XGBoost model demonstrated superior predictive ability, with the lowest RMSE (0.137), MAPE (0.222), and MAD (0.101) values, and was able to explain 99.8% of the barley variation. This research highlights the potential of machine learning algorithms in enhancing barley breeding by accurately predicting beneficial traits for yield improvement.
Prediction of Grain Yield in Wheat by CHAID and MARS Algorithms Analyses
Genetic information obtained from ancestral species of wheat and other registered wheat has brought about critical research, especially in wheat breeding, and shown great potential for the development of advanced breeding techniques. The purpose of this study was to determine correlations between some morphological traits of various wheat (Triticum spp.) species and to demonstrate the application of MARS and CHAID algorithms to wheat-derived data sets. Relationships among several morphological traits of wheat were investigated using a total of 26 different wheat genotypes. MARS and CHAID data mining methods were compared for grain yield prediction from different traits using cross-validation. In addition, an optimal CHAID tree structure with minimum RMSE was obtained and cross-validated with nine terminal nodes. Based on the smallest RMSE of the cross-validation, the eight-element MARS model was found to be the best model for grain yield prediction. The MARS algorithm proved superior to CHAID in grain yield prediction and accounted for 95.7% of the variation in grain yield among wheats. CHAID and MARS analyses on wheat grain yield were performed for the first time in this research. In this context, we showed how MARS and CHAID algorithms can help wheat breeders describe complex interaction effects more precisely. With the data mining methodology demonstrated in this study, breeders can predict which wheat traits are beneficial for increasing grain yield. The adaption of MARS and CHAID algorithms should benefit breeding research.