Methods, models and systems for predicting yellow rust in wheat crops

摘要

A method of constructing a model, preferably a Random Forest model, for predicting the presence of Yellow Rust in wheat crops, is disclosed, the method comprising the steps of: i. obtaining, for a plurality of sample wheat plots, a plurality of values for first, second and third vegetation indices V1, V2, V3, wherein the first vegetation index VI is defined by V1 = (R531+10nm _ R570+10nm) / (R531+10nm +R570+10nm), the second vegetation index V2 is defined by V2=V1* (-1) / (V4*R700+10nm /R670+10nm), wherein V4 is defined by V4 = (R800+10nm _ R670+10nm) / (R800+10nm +R670+10nm) and the third vegetation index V3 is defined by V3 = (R734+10nm _ R747+10nm) / (R715+10nm +R726+10nm), wherein Rx is the wheat canopy reflectance at the wavelength X nm, ii. obtaining, from the plurality of sample wheat plots, a plurality of Yellow Rust scores, the score for each sample wheat plot specifying the presence of Yellow Rust in that sample wheat plot, and ill. constructing or calculating a model associating the plurality of values for the vegetation indices VI, V2 and V3 with the plurality of Yellow Rust scores. Methods and systems for predicting the presence of Yellow Rust are also disclosed.