An improved back propagation neural network prediction model for subsurface drip irrigation system

Abstract A crop yield-irrigation water model, based on an improved genetic algorithm (GA)-back propagation (BP) neural network prediction algorithm, has been developed in this study. It mainly uses the improved BP neural network based on the GA algorithm to develop the yield-irrigation water model for predicting the corn yield for different irrigation systems under subsurface drip irrigation. The model with the GA-BP algorithm gives more accurate predictions of the yield. The average error is only 0.71%. The GA-BP algorithm also speeds up the convergence of the network, improves the accuracy of the prediction, and describes the relationship between the yield and irrigation water under subsurface drip irrigation more accurately. Hence, the model can be used to design irrigation systems under subsurface drip irrigation more accurately.