Application of a U-Net Neural Network to the Puccinia sorghi–Maize Pathosystem

Abstract

Phenotyping in phytopathology has become a critical area of research, particularly as pathogen distribution changes and the ability to overcome both innate resistance and control methods develop among pathogen populations. Computer vision approaches to analyze plant disease data can be both faster and more reliable than traditional, manual approaches. However, the requirement of manually annotating training data for the majority of machine learning applications can present a challenge for pipeline development. Here, we describe a machine learning approach to quantify Puccinia sorghi incidence on maize leaves utilizing U-Net convolutional neural network models. We analyze several U-Net models with increasing amounts of training image data, either randomly chosen from a large data pool, or randomly chosen from a subset of disease time course data. As training dataset size increases, models perform better, but the rate of performance decreases. Additionally, the use of a diverse training dataset can improve model performance and reduce the amount of annotated training data required for satisfactory performance. Models with as few as 48 training images are able to replicate the ground truth results within our testing dataset. The final model utilizing our entire training dataset performs similarly to our ground truth data, with an intersection over union value of 0.5002 and an F1 score of 0.6669. This work illustrates the capacity of U-Nets to accurately answer real world plant pathology questions related to quantification and estimation of plant disease symptoms.