A Reliable Method to Recognize Soybean Seed Maturation Stages Based on Autofluorescence-Spectral Imaging Combined With Machine Learning Algorithms

Abstract

In recent years, technological innovations have allowed significant advances in the diagnosis of seed quality. Seeds with superior physiological quality are those with the highest level of physiological maturity and the integration of rapid and precise methods to separate them contributes to better performance in the field. Autofluorescence-spectral imaging is an innovative technique based on fluorescence signals from fluorophores present in seed tissues, which have biological implications for seed quality. Thus, through this technique, it would be possible to classify seeds in different maturation stages. To test this, we produced plants of a commercial cultivar (MG/BR 46 "Conquista") and collected the seeds at five reproductive (R) stages: R7.1 (beginning of maturity), R7.2 (mass maturity), R7.3 (seed disconnected from the mother plant), R8 (harvest point), and R9 (final maturity). Autofluorescence signals were extracted from images captured at different excitation/emission combinations. In parallel, we investigated physical parameters, germination, vigor and the dynamics of pigments in seeds from different maturation stages. To verify the accuracy in predicting the seed maturation stages based on autofluorescence-spectral imaging, we created machine learning models based on three algorithms: (i) random forest, (ii) neural network, and (iii) support vector machine. Here, we reported the unprecedented use of the autofluorescence-spectral technique to classify the maturation stages of soybean seeds, especially using the excitation/emission combination of chlorophyll a (660/700 nm) and b (405/600 nm). Taken together, the machine learning algorithms showed high performance segmenting the different stages of seed maturation. In summary, our results demonstrated that the maturation stages of soybean seeds have their autofluorescence-spectral identity in the wavelengths of chlorophylls, which allows the use of this technique as a marker of seed maturity and superior physiological quality.

Keywords: Glycine max; chlorophyll fluorescence; seed maturity; seed quality; support vector machine.

FIGURE 1

Flowchart of the main steps to classify the maturation stages of soybean seeds based on autofluorescence-spectral imaging combined with machine learning algorithms.

FIGURE 2

Physical and physiological properties of soybean seeds from different maturation stages. Each bar represents the mean of four replicates of 25 seeds ± standard deviation. Different letters indicate significant difference (α = 0.05) by Tukey test (n = 20).

FIGURE 3

Chlorophyll a, chlorophyll b and total carotenoids in soybean seeds from different maturation stages. Each bar represents the mean of four replicates ± standard deviation. Different letters indicate significant difference (α = 0.05) by Tukey test (n = 20).

FIGURE 4

Autofluorescence-spectral data from different excitation/emission combinations in soybean seeds at different seed maturation stages. Each bar represents the mean of four replicates of 25 seeds ± standard deviation. Different letters indicate significant difference (α = 0.05) by Tukey test (n = 20).

FIGURE 5

Gini-based importance for each excitation/emission combinations in the random forest analysis to segment soybean seeds of different maturation stages: R7.1, R7.2, R7.3, R8, and R9 (n = 500 seeds).

FIGURE 6

Framework of soybean seeds at different maturation stages assisted by RGB images (each individual pixel is represented by red, green and blue channels) and corresponding autofluorescence-spectral images captured in the excitation/emission combinations of 405/600 nm (chlorophyll b) and 660/700 nm (chlorophyll a), after image transformation by the nCDA algorithm. The seedling images were captured at 7 days after sowing using a representative seedling of each maturation stage.

FIGURE 7

Comparison of the random forest (RF), neural network (NN), and support vector machine (SVM) algorithms discriminating soybean seed maturation stages using autofluorescence-spectral data, and performance of the models based on accuracy, kappa, precision and recall (presented in percentage). The models were created using autofluorescence-spectral data extracted from seeds in the R7.1, R7.2, R7.3, R8, and R9 stages (n = 500 seeds).

FIGURE 8

Pearson’s correlation coefficients between physical properties, physiological quality, pigment content and autofluorescence-spectral markers (nm) in soybean seeds of different maturation stages (R7.1, R7.2, R7.3, R8, and R9).