Characteristic features of statistical models and machine learning methods derived from pest and disease monitoring datasets

While many studies have used traditional statistical methods when analysing monitoring data to predict future population dynamics of crop pests and diseases, increasing studies have used machine learning methods. The characteristic features of these methods have not been fully elucidated and arranged. We compared the prediction performance between two statistical and seven machine learning methods using 203 monitoring datasets recorded over several decades on four major crops in Japan and meteorological and geographical information as the explanatory variables. The decision tree and random forest of machine learning were found to be most efficient, while regression models of statistical and machine learning methods were relatively inferior. The best two methods were better for biased and scarce data, while the statistical Bayesian model was better for larger dataset sizes. Therefore, researchers should consider data characteristics when selecting the most appropriate method.

Automated summary

While traditional statistical methods and machine learning methods have been widely used to predict future population dynamics of crop pests and diseases, the characteristic features of these methods have not been fully understood. By comparing two statistical and seven machine learning methods using 203 monitoring datasets on four major crops in Japan, it was found that the decision tree and random forest methods of machine learning were the most effective, while the regression models of both statistical and machine learning methods were relatively inferior. The best methods were better for biased and scarce data, while the statistical Bayesian model was better for larger dataset sizes. Therefore, researchers should consider data characteristics when selecting the most appropriate method.