Neural network design
| Hi-index | 0.00 |
In order to build prediction model of the water surface evaporation so as to easily plan and manage water resources, authors presented a method with the principal component analysis(PCA) and radial basis function(RBF) neural network model for predicting the water surface evaporation. Firstly, the PCA was used to eliminate the correlation of the initial input layer data so that the problem of efficiency caused by too many input parameters and by too large network scale in neural network modeling could be solved. And then, the prediction model of water surface evaporation was built through taking the results of PCA as inputs of the RBF neural network. The research result showed that the model proposed had a better prediction accuracy that the average prediction accuracy reached 95.3%, and enhanced 5.5% and 5.0% compared with the conventional BP network and RBF network respectively, which met the requirements of actual water resources planning and provided a theoretical reference for other region of water surface evaporation forecasting.