نوع مقاله : مقاله پژوهشی
نویسنده
استادیار آب و هواشناسی، بخش جغرافیا، دانشگاه شهید باهنر کرمان، کرمان، ایران
چکیده
کلیدواژهها
عنوان مقاله [English]
نویسنده [English]
Estimates, forecasts and Runoff management have always been an interest to researchers. Therefore, using any of the methods commonly used in estimating seemingly destructive phenomenon that, unfortunately, due to the complexity of the relationship between rainfall and Runoff and non-linearity of the relationship, the results are not good. Todays, with the advancement of science and the development of new techniques in all aspects of science, understanding and settle in for a good hope to have created such relationship. One of approaches that have attracted attention of researchers in recent decades is using of Neural Networks. In this study, the Neural- Wavelet Network for Estimating Runoff in Khersan catchment area is used. The results obtained from this model with results from a Neural Network of Return Propagation and Neural Network of Fundamental-Radial, as older models, compared and analyzed. Comparison of results was performed by correlation coefficient and Root Mean Square Error. The results show that the accuracy of the Neural- Wavelet Network compared to Neural Network of Return Propagation and Neural Network of Fundamental-Radial is better.
کلیدواژهها [English]