Application of Machine Learning Algorithms in Plant Breeding: Predicting Yield From Hyperspectral Reflectance in Soybean

Abstract

Recent substantial advances in high-throughput field phenotyping have provided plant breeders with affordable and efficient tools for evaluating a large number of genotypes for important agronomic traits at early growth stages. Nevertheless, the implementation of large datasets generated by high-throughput phenotyping tools such as hyperspectral reflectance in cultivar development programs is still challenging due to the essential need for intensive knowledge in computational and statistical analyses. In this study, the robustness of three common machine learning (ML) algorithms, multilayer perceptron (MLP), support vector machine (SVM), and random forest (RF), were evaluated for predicting soybean (Glycine max) seed yield using hyperspectral reflectance. For this aim, the hyperspectral reflectance data for the whole spectra ranged from 395 to 1005 nm, which were collected at the R4 and R5 growth stages on 250 soybean genotypes grown in four environments. The recursive feature elimination (RFE) approach was performed to reduce the dimensionality of the hyperspectral reflectance data and select variables with the largest importance values. The results indicated that R5 is more informative stage for measuring hyperspectral reflectance to predict seed yields. The 395 nm reflectance band was also identified as the high ranked band in predicting the soybean seed yield. By considering either full or selected variables as the input variables, the ML algorithms were evaluated individually and combined-version using the ensemble-stacking (E-S) method to predict the soybean yield. The RF algorithm had the highest performance with a value of 84% yield classification accuracy among all the individual tested algorithms. Therefore, by selecting RF as the metaClassifier for E-S method, the prediction accuracy increased to 0.93, using all variables, and 0.87, using selected variables showing the success of using E-S as one of the ensemble techniques. This study demonstrated that soybean breeders could implement E-S algorithm using either the full or selected spectra reflectance to select the high-yielding soybean genotypes, among a large number of genotypes, at early growth stages.

Keywords: artificial intelligence; data-driven model; ensemble methods; high-throughput phenotyping; random forest; recursive feature elimination.

FIGURE 1

The location of the experiments in 2018 and 2019.

FIGURE 2

The distribution of soybean genotypes in each yield class.

FIGURE 3

A schematic representation of the machine learning algorithms used in this study to classify the soybean yield using reflectance bands: (A) Multilayer perceptron, (B) Support vector machine, and (C) Random forest.

FIGURE 4

The scheme of data collection and machine learning algorithm development and validation. OP, optimizing parameters; MLP, multilayer perceptron; SVM, support vector machine; RF, random forest; E–S, ensemble–stacking strategy.

FIGURE 5

The minimum, mean, and maximum values of each reflectance band were measured for 245 soybean genotypes evaluated at (A) R4 and (B) R5 growth stages at four different field environments.

FIGURE 6

The importance of selected variables based on the recursive feature elimination (RFE) strategy for soybean reflectance bands measured at R4 (A) and R5 (B) soybean growth stages.

FIGURE 7

The soybean yield classes versus the 395 nm reflectance band at R5 growth stages.

FIGURE 8

The accuracy of RF, MLP, SVM, and E–S algorithms for predicting soybean yield using full and RFE selected variables (-VS) measured at R4 (A) and R5 (B) soybean growth stages in four environments. The mean performance was shown as × in each figure. MLP, multilayer perceptron; SVM, support vector machine; RF, random forest; E–S, ensemble–stacking strategy; RFE, recursive feature elimination.

FIGURE 9

The estimate values of (A) Matthews correlation coefficient (MCC), (B) Precision, (C) Recall, and (D) F-Measure for RF, MLP, SVM, and the E–S algorithms used for predicting soybean yield from all and selected variables collected (-VS) at the R5 growth stage. The mean performance is indicated with × in each figure. MLP, multilayer perceptron; SVM, support vector machine; RF, random forest; E–S, ensemble–stacking strategy; RFE, recursive feature elimination.