Weather-Based Logistic Regression Models for Predicting Wheat Head Blast Epidemics.

Abstract

Wheat head blast is a major disease of wheat in the Brazilian Cerrado. Empirical models for predicting epidemics were developed using data from field trials conducted in Patos de Minas (2013 to 2019) and trials conducted across 10 other sites (2012 to 2020) in Brazil, resulting in 143 epidemics, with each being classified as either outbreak (≥20% head blast incidence) or nonoutbreak. Daily weather variables were collected from the National Aeronautics and Space Administration (NASA) Prediction of Worldwide Energy Resources (POWER) website and summarized for each epidemic. Wheat heading date (WHD) served to define four time windows, with each comprising two 7-day intervals (before and after WHD), which combined with weather-based variables resulted in 36 predictors (nine weather variables × four windows). Logistic regression models were fitted to binary data, with variable selection using least absolute shrinkage and selection operator (LASSO) and sequentially best subset analyses. The models were validated using the leave-one-out cross-validation (LOOCV) technique, and their statistical performance was compared. One model was selected, implemented in a 24-year series, and assessed by experts and literature. Models with two to five predictors showed accuracies between 0.80 and 0.85, sensitivities from 0.80 to 0.91, specificities from 0.72 to 0.86, and area under the curve (AUC) from 0.89 to 0.91. The accuracy of LOOCV ranged from 0.76 to 0.81. The model applied to a historical series included temperature and relative humidity in preheading date, as well as postheading precipitation. The model accurately predicted the occurrence of outbreaks, aligning closely with real-world observations, specifically tailored for locations with tropical and subtropical climates.