جستجوی مقالات مرتبط با کلیدواژه « Hybrid Model » در نشریات گروه « اکولوژی »

Dez dam has an essential role in controlling the floods and water supply in Khouzestan. Accurate and reliable prediction of the flow input to the reservoir is crucial to make decisions about the exploitation and management of this reservoir. In this research, a novel WAVELET-ARIMA-NARX model was developed to predict the monthly inflow to Dez dam reservoir. The WAVELET method was used to break down the time series into sub-series and better analyzing, the ARIMA model was used to model the linear component of the analyzed series, and the NARX model used to model the error resulting from WAVELET-ARIMA model. The NDVI index was also used to measure the accuracy change of the WAVELET-ARIMA-NARX hybrid model. The results showed that the prediction performance of the WAVELET-ARIMA-NARX hybrid model has improved significantly compared to the ARIMA model. In such a way according to the RMSE criterion, the prediction accuracy in the verification and training stages has decreased by 74% and 82%, compared to the ARIMA and WAVELET-ARIMA model, respectively. The NDVI parameter with average temperature and rainfall of the basin as an input of the NARX model has increased the accuracy of the model. In the model with 10 neurons in the hidden layer, compared to the two-parameter model of rainfall and NDVI with 15 neurons, in evaluation section, the MAE values have decreased from 27.2 to 18.5 and the RMSE from 0.45 to 0.26. These values indicate the importance and impact of simultaneous consideration of three parameters on forecasting accuracy.

Water is one of the most essential elements in nature that forms the basis of human life and contributes to the economic growth and development of societies. Healthy water is closely related to environmental health and activities. The life of all animals on Earth depends on water and oxygen. In addition, adequate dissolved oxygen (DO) is essential for the survival of aquatic animals. Therefore, in this study, to simulate the dissolved oxygen of the Cumberland River in the United States from the combined artificial neural network (ANN) model with wavelet and meta-heuristic algorithms of gray wolf (GWO) and bat (BA) on a monthly time scale during the statistical period. Used 2020-2010. The criteria of correlation coefficient (R2), squared mean square error (RMSE), absolute mean error (MAE) and Nash-Sutcliffe productivity coefficient (NSE) were used to evaluate and compare the performance of the models. The results showed that all three hybrid models have better results in hybrid models than the other designated models. Also, according to the evaluation criteria, it was found that among the models used in the simulation of dissolved oxygen in river water, the model of artificial neural network-wavelet with coefficient of determination (R2 = 0.958), the root mean square error (RMSE = 0.651), The mean absolute value of error (MAE = 0.334) and Nash Sutcliffe coefficient (NS = 0.962) in the validation stage showed better performance than other models.