Fitting of Water Requirement and Yield of Winter Wheat in North China Plain Based on Artificial Neural Network

Abstract

The fitting of water requirement and yield during the growth period of winter wheat can improve yield effectively and improve irrigation water use efficiency with a certain amount of resource input. This paper selects the irrigation amount, precipitation and yield of winter wheat at the Wuqiao Scientific Observation and Experimental Station. Fitting the water requirement and yield of winter wheat based on three types of artificial neural networks. This paper uses support vector machine (SVM), thought evolution algorithm to optimize BP neural network (MAE-BP) and generalized regression neural network (GRNN) to fit the water requirement and yield of two crops. The SVM is the model with the highest fitting accuracy among the three models, the RMSE, MAE, NS and R2 between predictive value and true value are 7.45 kg/hectares, 213.64 kg/hectares, 0.8086, 0.9409 respectively.