Prediction of Thickness and Growth Rate of Populus ussuriensis Leaves by Climatic Factors Based on Adaptive Neural Network

In order to improve the prediction accuracy of radial basis function (RBF) neural network model, an adaptive RBF neural network is proposed, based on which establishes the prediction model of climatic factors′ effects on early wood′s cell wall ratio and growth rate, which can be very good to improve the lack of traditional RBF algorithm. We can learn from the simulation experiments that the algorithm can predict the growth law of Populus ussuriensis plantation more accurately, at the same time, its simulation speed has been significantly improved, the error has been significantly reduced when compared with the traditional RBF algorithm.