تاثیر موجک بر افزایش دقت مدل‌های تخمینی در مدل‌سازی بارش-رواناب (مطالعۀ موردی: حوضۀ صوفی‌چای)

فرآیند بارش-رواناب از مهم‌ترین و پیچیده‌ترین پدیده‌ها در چرخه هیدرولوژی بوده و در مدل‌سازی آن، دیدگاه‌های متفاوتی برای توسعه و بهبود مدل‌های پیش‌بینی‌کننده ارائه شده است. لذا، بر حسب استفاده از روش‌های گوناگون، انواع مدل‌ها توسعه یافته‌اند. در این تحقیق فرآیند بارش-رواناب در حوضه صوفی‌چای با استفاده از شبکه عصبی مصنوعی (ann) و هیبرید موجک -شبکۀ عصبی (wann) مورد مطالعه قرارگرفته است. داده‌های بارش-رواناب در طول دوره آماری (981380) برای آموزش و صحت‌سنجی مدل‌ها مورد استفاده قرار گرفت و شش سناریو برای هر مدل در نظر گرفته شد. نتایج این سناریو‌ها نشان داد که بهترین ورودی‌ها برای مدل‌ها، مربوط به سناریوی پنج است که در آن از دبی با یک تاخیر، بارش ماه مورد نظر و بارش با یک تاخیر استفاده شده است. در حالت کلی نتایج حاکی از دقت قابل قبول هر دو مدل است. از لحاظ اولویت نیز مدل wann با بیش‌ترین دقت ضریب همبستگی (r)، جذر میانگین مربع خطاها (rmse) و ضریب نشساتکلیف (nse) به‌ترتیب برابر 0.97، 23.99 و 0.95 برای مرحله آموزش و 0.82، 62.33 و 0.68 برای مرحله آزمون کمترین خطا در اولویت اول و مدل ann در اولویت بعدی با مقادیر ضریب همبستگی (r)، جذر میانگین مربع خطاها (rmse) و ضریب نشساتکلیف (nse) به‌ترتیب برابر 0.93، 40.41 و 0.87 برای بخش آموزش و 0.81، 73.40 و 0.56 برای بخش آزمون قرار گرفتند و نتایج گویای این بود که موجک باعث بهبود نتایج و پیش‌بینی در مدل‌سازی بارش-رواناب شده است.

Impact of wavelet on accuracy of estimated models in rainfall-runoff modeling (Case study: Sufi Chay)

Introduction In recent decades, accurate modeling of runoff has always been one of the hottest topics for researchers in the field of hydrology, as it plays an important role in water resources management, hydropower development, urban planning, irrigation and other hydrological/meteorological activity programs. Conceptbased and physical models require huge amounts of data and environmental calculations. The nonlinear nature of the rainfallrunoff process and the complexity of physical models are some of the reasons why researchers have turned to intelligent models. However, these models may not provide logical results for nonlinear hydrological processes. To overcome this shortcoming, nonlinear artificial neural networks (ANNs) have depicted a real success in predicting hydrological time series.Materials and MethodsThe usefulness of wavelet transforms in noise reduction and multiresolution analysis along with the ability of ANNs to optimize and predict hydrological processes has recently been introduced as a neural network wavelet hybrid model (WANN) and is widely used by hydrologists not only for rainfallrunoff modeling. It has been used to simulate some other components of the hydrological cycle such as river flow, groundwater, precipitation and sediment. In this study, precipitation and discharge data on a monthly scale have been used. For modeling in this research, ANN and WANN have been used. Data were used for Sufi Chay Basin for period 20012019.Results and Discussion In this study, for modeling rainfallrunoff by neural network in MATLAB 2018 Software and investigating the effect of using wavelet transform on the accuracy of rainfallrunoff model has been done. First, the existence of autocorrelation and its significance in runoff data were investigated using the partial autocorrelation function (PACF). In the hybrid model, Daubechies mother wavelets 3 and 4 are used. Six scenarios were examined for modeling. Among the selected scenarios, scenarios 4 and 5 had the best results in comparison between the two models. The poor accuracy of the first three scenarios (Scenarios 13) indicates that using rainfall data alone are not sufficient to model runoff, thus employing the last monthly runoff data into the model made a significant change in the results. In the ANN model, scenario 4 has more acceptable results with correlation coefficient (r), square root mean square error (RMSE) and Nash Sutcliffe coefficient (NSE) of 0.889, 51.574 and 0.788, respectively for the training section, and 0.779, 70.625, and 0.595, respectively for the test section. In the hybrid model WANN, scenario 5 has the best results with the values of r, RMSE and NSE of 0.997, 23.99 and 0.954, respectively for the training section, and 0.829, 62.334 and 0.684, respectively for the test section.Conclusion In the present study, the performance of ANN and WANN models for rainfallrunoff modeling in Sufi Chay Basin using different parameters of rainfall and discharge delays during the statistical period (20012019) was evaluated. The highest accuracy of the models was provided in combining runoff input with a time delay and monthly precipitation. The purpose of this study is the effect of wavelet on increasing the accuracy of estimation in rainfallrunoff modeling. The results of the present study showed that the hybrid model will increase the accuracy of a model.