Neural networks in forecasting models: Nile River application
暂无分享,去创建一个
The neural network approach is applied to the prediction of the flow of the River Nile. A multilayer feedforward network is constructed and trained by the backpropagation algorithm. We propose several different methods for single-step ahead forecast and multi-step ahead forecast in an attempt to get the least prediction error. These methods investigate different ways to preprocess the inputs and the outputs. We consider ten-days ahead forecast and one-month ahead forecast. In both cases good results were observed.
[1] Juan B. Valdés,et al. Streamflow Forecasting for Han River Basin, Korea , 1994 .
[2] Edward A. McBean,et al. River Flow Forecasting Model For Sturgeon River , 1985 .
[3] Robert J. Marks,et al. Electric load forecasting using an artificial neural network , 1991 .