Method for constructing flue-cured tobacco disease dynamic prediction model

The invention relates to the technical field of dynamic prediction models, and discloses a method for constructing a flue-cured tobacco disease dynamic prediction model, which comprises the following steps: S1, meteorological factor nondimensionalization: firstly, collecting meteorological factor data and flue-cured tobacco disease observation data of a pathological area, including brown spot and common mosaic virus disease investigation records, the meteorological station data comprises an average value and an extreme value of the meteorological data; s2, calculating disease factors; s3, data processing: carrying out correlation analysis and stepwise regression analysis on the calculated data through python 2.0 programming; and S4, establishing a dynamic illness state prediction model. According to the method, the meteorological factors and the compound factors of the early-stage illness state are used, meanwhile, the influence of wind is considered, the method is more targeted, in the aspect of the forecast