Application of Artificial Neural Network in forecasting water consumption of Populus (P.×euramericana cv.'74/76') seedlings

In this experiment, by using the method of artificial neural network and DPS DATA PROCESSING SYSTEM combined with the meteorological data of air temperature, relative air humidity, solar radiation, wind speed, soil water content and dew point temperature as the input variable, the author established the artificial neural network system to forecast the seedling water consumption of P.×euramericana cv.“74/76”, and through the experiments it has been examined that three neural network system models can be applied in forecasting water consumption of seedlings, and the average relative error of Back Propagation (BP) neural network prediction model was 0.04, the projection pursuit regression (PPR) neural network prediction model was 0.03, the multiple stepwise regression anatomic model was 0.10, moreover, the latter two ones had good stability, while that of BP neural network prediction model was poor. Therefore, we propose that PPR neural network model can be used in prediction of seedling water consumption. Furthermore, the maximum relative error of PPR neural network predication model was 0.073, the minimum relative error was 0.002. The neural network model is superior to the former linear model that the neural network model performs a higher forecasting accuracy with relatively shorter time consumption in training.