Application of PCA-MLP neural network model in runoff prediction in Ningxia Section of Yellow River
To improve the prediction accuracy of monthly runoff volume on a short-time scale and to simplify the structure of the neural network model,PCA-MLP neural network model combined with Principal Component Analysis(PCA)and Multi-Layer Perceptron(MLP)neural network is proposed to forecast the monthly runoff volume during the flood season.The model first employs PCA to determine the main influencing factors on runoff volume and then inputs the data of the main influencing factors into MLP neural network model to predict monthly runoff volume.Monthly runoff volume and influencing factors data from Qingtongxia Hydrological Station in Ningxia during the flood season from 2010 to 2019 were used as training samples to train the neural network model,with data from 2020 to 2022 used as testing samples for comparative analysis.The forecast results indicate that the factors influencing the flood season's runoff volume are mainly historical runoff and climatic characteristics.The prediction results of the testing set achieved a coefficient of determination of 0.851,demonstrating that the model can provide guidance for the prediction of monthly runoff volume in Ningxia during the flood season.
国家科技期刊平台
NSTL
万方数据
