The Research About Disease Prediction Of Changli Grape Planting Project

Hebei Changli grape planting project is an important part of Hebei's forestry economy and is the main source of supply for wine grapes in China.This study outlined the Changli grape planting project,analyzed the influencing factors affecting Changli grape yield,and determined that the disease is the most serious factor,and focused on the downy mildew,white rot,and anthracnose on grape yield.The epidemiological patterns of these three major diseases were analyzed to determine the three meteorological factors that had the greatest impact on the disease,and the prediction was made to predict the disease in advance to achieve the purpose of prevention in advance.This paper uses a grape planting base in Changli,Hebei Province.Cabernet Sauvignon was the object of study and analyzed the impact of meteorological factors on the incidence of these three diseases..Based on the causal relationship between grape disease incidence rate and meteorological factors,this paper establishes a new prediction method for grape disease occurrence based on the support vector machine,and compares it with the traditional multiple linear regression prediction method.The experimental results show that the accuracy of prediction of grape disease occurrence based on support vector machines is superior to multiple linear regression prediction..In this paper,triangular fuzzy information particles are used to fuzzy granulate the timing of the occurrence of grape diseases,reducing the timing characteristics of the input window.Based on the previous support vector machine,a support vector machine method based on fuzzy information granularity timing is established for grapes.The trend range of disease incidence rates was predicted and compared with a simple prediction method based on support vector machines.The experimental results show that the prediction accuracy of this method is better than that of the support vector machine method.The method is more practical and accurate in predicting the occurrence rate of diseases,and it can simplify the learning problem and make the learning algorithm run faster,which is helpful for the prediction.