The Automation of Hyperspectral Training Library Construction: A Case Study for Wheat and Potato Crops

The potential of hyperspectral measurements for early disease detection has been investigated by many experts over the last 5 years. One of the difficulties is obtaining enough data for training and building a hyperspectral training library. When the goal is to detect disease at a previsible stage, before the pathogen has manifested either its first symptoms or in the area surrounding the existing symptoms, it is impossible to objectively delineate the regions of interest containing the previsible pathogen growth from the areas without the pathogen growth. To overcome this, we propose an image labelling and segmentation algorithm that is able to (a) more objectively label the visible symptoms for the construction of a training library and (b) extend this labelling to the pre-visible symptoms. This algorithm is used to create hyperspectral training libraries for late blight disease (Phytophthora infestans) in potatoes and two types of leaf rust (Puccinia triticina and Puccinia striiformis) in wheat. The model training accuracies were compared between the automatic labelling algorithm and the classic visual delineation of regions of interest using a logistic regression machine learning approach. The modelling accuracies of the automatically labelled datasets were higher than those of the manually labelled ones for both potatoes and wheat, at 98.80% for P. infestans in potato, 97.69% for P. striiformis in soft wheat, and 96.66% for P. triticina in durum wheat.

Automated summary

The study explores the potential of hyperspectral measurements for early disease detection and proposes an image labelling and segmentation algorithm for more accurate construction of training libraries and distinction between visible symptoms and pre-visible symptoms. Through this algorithm, successful creation of hyper spectral training libraries for late blight disease in potatoes and two types of leaf rust in wheat is achieved, demonstrating that the modeling accuracies of automatically labelled datasets are significantly higher than manually labelled datasets.