Trend prediction of irrigation area using improved random forest regression

The food problem is a major common concern in the world, and predicting the irrigation area can promote a solution to this problem. In this paper, the relationship between grain yield and the world's irrigated area is analysed, and a machine model based on an improved random forest regression and limit tree regression algorithm is proposed and applied to the prediction of the irrigation area in China. Specifically, first the arithmetic mean value of the mean square error and mean absolute error are used as the evaluation metric of the improved impure function and irrigation area prediction effect. Second, the grid search method is used to determine the optimal number of decision trees in random forest and limit tree regression so that a new improved random forest model is established to predict the annual irrigation area in China. Finally, the proposed model is compared with other prediction models, and the 10-fold cross-validation experiment results show the effectiveness of the proposed model. It is expected to be applied to the prediction and factor analysis of the annual irrigation area in China.