Differentiation of Plant-Pathogenic Fungi in Soybean Seeds Using Hyperspectral Sensors

Abstract

Hyperspectral sensors have emerged as a promising approach in the study of plant diseases. The objective was to distinguish between healthy and inoculated seeds, and also to distinguish between genera of plant-pathogenic fungi in soybean seeds, using hyperspectral sensors combined with machine learning. The experimental design was a fully randomized factorial design with six algorithms (Simple Logistic Regression, Support Vector Machine, Artificial Neural Network, Random Forest, REPTree and J48 decision trees) and four phytopathogens (Sclerotinia sclerotiorum, Macrophomina phaseolina, Rhizoctonia solani, and Colletotrichum sp.) plus the control. Spectral analysis of the seeds was performed using a spectroradiometer (Ocean Optics) consisting of two sensors: NIR and Flame, covering the spectrum from 350 to 2500 nm. It was possible to distinguish between healthy and inoculated seeds, as well as identify the type of phytopathogen, based on each spectral signature. The Simple Logistic Regression and Support Vector Machine algorithms performed best. Hyperspectral sensors combined with machine learning constitute a promising tool for the detection of phytopathogens in seeds, enabling rapid and non-destructive analysis. This promising tool could serve as a complementary alternative to traditional diagnostic methods, which, although accurate, are time-consuming and rely on specialized labor.