Prediction of leaf Bloch disease risk in Norwegian spring wheat based on weather factors and host phenology

Abstract Leaf blotch diseases (LBD), such as Septoria nodorum bloch ( Parastagnospora ), tritici Zymoseptoria ) and Tan spot Pyrenophora tritici-repentis can cause severe yield losses (up to 50%) in Norwegian spring wheat Triticum aestivum are mainly controlled by fungicide applications. A forecasting model predict disease risk be an important tool optimize control. The association between specific weather variables the development of LBD differs growth stages. In this study, a mathematical estimate phenological was derived based on sowing date, air temperature photoperiod. Weather factors associated with severity were then identified for selected stages correlation study data (17 years). Although information regarding host resistance previous crop added factors, two purely weather-based prediction models (CART, classification regression tree algorithm) one black box (KNN, K nearest neighbor most accurate moderate high (>5% infection). predictive accuracy these (76–83%) compared that existing used Norway Denmark (60 61% accuracy, respectively). newly developed performed better than models, but still had tendency overestimate risk. Specificity new varied 49 74% 40 37% models. These promising decision tools improve integrated management Norway.