Use of multicolour fluorescence imaging for diagnosis of bacterial and fungal infection on zucchini by implementing machine learning

Zucchini (Cucurbita pepo L.) is a cucurbitaceous plant ranking high in economic importance among vegetable crops worldwide. Pathogen infections cause alterations in plants primary and secondary metabolism that lead to a significant decrease in crop quality and yield. Such changes can be monitored by remote and proximal sensing, providing spatial and temporal information about the infection process. Remote sensing can also provide specific signatures of disease that could be used in phenotyping and to detect a pest, forecast its evolution and predict crop yield. In this work, metabolic changes triggered by soft rot (caused by Dickeya dadantii) and powdery mildew (caused by Podosphaera fusca) on zucchini leaves have been studied by multicolour fluorescence imaging and by thermography. The fluorescence parameter F520/F680 showed statistically significant differences between infected (with D. dadantii or P. fusca) and mock-control leaves during the whole period of study. Artificial neural networks, logistic regression analyses and support vector machines trained with a set of features characterising the histograms of F520/F680 images could be used as classifiers, discriminating between healthy and infected leaves. These results show the applicability of multicolour fluorescence imaging on plant phenotyping.