Employing Weather-Based Disease and Machine Learning Techniques for Optimal Control of Septoria Leaf Blotch and Stripe Rust in Wheat

Septoria tritici blotch (STB) is among the most important crop diseases causing continuous threats to wheat production worldwide. STB epidemics are the outcome of interactions between susceptible host cultivars,
favorable environmental conditions, and sufficient quantities of pathogen
inoculum. Thus, to determine whether fungicide sprays should be applied to
prevent the risk of epidemics that might otherwise lead to yield loss, weatherbased systems as stand-alone or combined with other disease or agronomic
variables have been implemented in decision-support systems (DSS). Given the
economic importance of wheat in Morocco and increasing concerns caused by
fungal plant pathogens in wheat-growing regions, DSS integrating a disease risk
model would help to limit potentially harmful side effects of fungicide applications while ensuring economic benefits. Here we describe the use of an artificial intelligence algorithm, i.e. the artificial neural network, within a weatherbased modelling approach to predict the progress of STB in wheat in Luxembourg. The reproducibility of area-specific modelling approaches is often a
hurdle for their application in operational disease warning system at a regional
scale. Hence, we explore the potential of coupling artificial intelligence algorithms with weather-based model for predicting in-season progress of a major
economically important fungal disease – wheat stripe rust – in selected wheatproducing regions in Morocco.