Autofluorescence-spectral imaging as an innovative method for rapid, non-destructive and reliable assessing of soybean seed quality

André Dantas de Medeiros,Clíssia Barboza da Silva,Marina de Lima Nogueira,André Rodrigues dos Reis,Marcia Eugenia Amaral de Carvalho,Nielsen Moreira Oliveira

doi:10.1038/s41598-021-97223-5

Abstract

In the agricultural industry, advances in optical imaging technologies based on rapid and non-destructive approaches have contributed to increase food production for the growing population. The present study employed autofluorescence-spectral imaging and machine learning algorithms to develop distinct models for classification of soybean seeds differing in physiological quality after artificial aging. Autofluorescence signals from the 365/400 nm excitation-emission combination (that exhibited a perfect correlation with the total phenols in the embryo) were efficiently able to segregate treatments. Furthermore, it was also possible to demonstrate a strong correlation between autofluorescence-spectral data and several quality indicators, such as early germination and seed tolerance to stressful conditions. The machine learning models developed based on artificial neural network, support vector machine or linear discriminant analysis showed high performance (0.99 accuracy) for classifying seeds with different quality levels. Taken together, our study shows that the physiological potential of soybean seeds is reduced accompanied by changes in the concentration and, probably in the structure of autofluorescent compounds. In addition, altering the autofluorescent properties in seeds impact the photosynthesis apparatus in seedlings. From the practical point of view, autofluorescence-based imaging can be used to check modifications in the optical properties of soybean seed tissues and to consistently discriminate high-and low-vigor seeds.

Highlights

In the agricultural industry, advances in optical imaging technologies based on rapid and nondestructive approaches have contributed to increase food production for the growing population
Traditional fluorescence imaging is mainly based on fluorescence spectroscopy (e.g. FTIR or Raman microspectroscopy) that can be applied to determine autofluorescent compounds, or non-fluorescent compounds can be measured by using multiple fluorescent tracers to highlight molecular, physiological or anatomical features[11,12]
We tested the use of these machine learning algorithms combined with autofluorescencespectral imaging for classification of soybean seeds based on their physiological quality levels

Summary

Introduction

Advances in optical imaging technologies based on rapid and nondestructive approaches have contributed to increase food production for the growing population. The seed industry uses standardized germination and vigor tests to predict field performance of seedlots These tests provide valuable information on seed physiological potential; they are relatively time-consuming with subjective results that depend on specialized analysts, being difficult to reproduce the r esults[4]. Traditional fluorescence imaging is mainly based on fluorescence spectroscopy (e.g. FTIR or Raman microspectroscopy) that can be applied to determine autofluorescent compounds, or non-fluorescent compounds can be measured by using multiple fluorescent tracers to highlight molecular, physiological or anatomical features[11,12] This technique assesses only a small part of an object (i.e., a “spot measurement”), so they do not provide spatial information that it is important for many seed inspection applications. We tested the use of these machine learning algorithms combined with autofluorescencespectral imaging for classification of soybean seeds based on their physiological quality levels

Methods

Results

Discussion

Conclusion