WAVELET TRANSFORM AND NEURAL NETWORKS FOR REFERENCE CROP EVAPOTRANSPIRATION FORECASTING
Reference Crop Evapotranspiration (RCE) forecasting plays an important role in the agricultural production management. A novel approach is proposed in this paper for RCE forecasting by combining the wavelet transform and neural networks. Firstly the RCE time series is decomposed to different frequency components with wavelet analysis. Then the artificial neural network is used in multi-scale forecasting of these coefficients. Finally, based on the formula reconstructed, the forecasted RCE time series is obtained. The effectiveness of this method is verified by an example. The results show the application of the wavelet transform and artificial neural network is encouraging, which serves as a new method for non-linear systematic time series forecasting.
Time series Wavelet transforms Artificial neural network Reference Crop Evapotranspiration
Weiguang Wang Xuzhang Xue Renduo Zhang
National Engineering Research Center for Information Technology in Agriculture, Beijing, 100089 Stat National Engineering Research Center for Information Technology in Agriculture, Beijing, 100089 School of Environmental Science and Engineering, Zhongshan University, Guangzhou, 510275
国际会议
北京
英文
424-429
2005-10-14（万方平台首次上网日期，不代表论文的发表时间）