针对径流时间序列的非线性特点,利用重构相空间的嵌入维数确定神经网络结构,建立了基于相空间重构理论的BP神经网络月径流预测模型,并采用该模型预测了瀑布沟水库的径流时间序列。结果表明,该BP神经网络预测模型收敛速度快、预测精度较高。 According to the nonlinear characteristics of runoff time series, the neural network structure is determined by using the embedding dimension of reconstructed phase space, and the monthly runoff prediction model of BP neural network based on phase space reconstruction theory is established. The model is used to predict the monthly runoff of the Pubugou Reservoir Runoff time series. The results show that the BP neural network prediction model has fast convergence rate and high prediction accuracy.