جستجوی مقالات مرتبط با کلیدواژه « Wavelet Neural Network » در نشریات گروه « آبخیزداری، بیابان، محیط زیست، مرتع »

Simulation and evaluation of river sediment is one of the important issues in water resources management. Measuring the amount of sediment in conventional methods generally involves a lot of time and cost and sometimes does not have sufficient accuracy. In this study, a wavelet neural network was used to estimate the sediments of the Kashkan River in Lorestan Province, and its results were compared with conventional smart methods such as artificial neural network. Parameters of discharge, temperature, water soluble solids content and precipitation as input and sediment discharge were selected as output during the monthly statistical period (1984-2013). Correlation coefficient, root mean squared error, and Nash Sutcliff coefficient were used to evaluate and compare the performance of the models. Results showed that the combined structure has been able to provide acceptable results in estimating sediment yield using two intelligent methods. However, in terms of accuracy, the wavelet neural network model with the highest correlation coefficient (0.850), the lowest root mean square error (0.151 tonday-1), and the Nash-Sutcliff criterion (0.758) were prioritized in the validation stage. Results also showed that the wavelet neural network model has a high ability to estimate the minimum and maximum values.

Electrical conductivity (EC) is an important factor in river engineering, especially studying of river water quality. In this study we studied and evaluated wavelet neural network to predict the electrical conductivity of the Kakareza river (in lorestan), and the results were compared with results of artificial neural network model. For this purpose, hydrogen carbonate, chloride, sulfate, calcium, magnesium, sodium and flow rate at monthly scale during the period (1969-2015) as input and output parameters were selected as electrical conductivity. The criteria of correlation coefficient, root mean square error and of Nash Sutcliff coefficient were used to evaluate and performance compare of models. The results showed that wavelet neural network model has the highest correlation coefficient (0.977), the lowest root mean square error (0.032 ds/m) and the highest standards Nash Sutcliffe (0.847) became a priority in the validation phase. The results indicate acceptable capability of wavelet neural network models to estimate the electrical conductivity of river water.

Prediction of wind components (like wind speed) is considered one of the important factor، especially in relation to evaporation in a watershed. In this paper، in order to increase the efficiency of artificial intelligence models، for predicting wind speed، two neural network and neuro-fuzzy models combined with wavelet and two new hybrid models were presented. This research was carried out by some climatic parameters in Yazd synoptic station including wind speed، mean temperature، maximum temperature، relative humidity and evaporation. Then، efficiency of wavelet neural network and wavelet neural –fuzzy models were compared with the neural network and neuro-fuzzy to predict the wind speed for next 12 months. Finally، in order to confirm the efficiency of the best model، wind speed in 2005 was predicted using effective climatic parameters in 2004. The obtained results showed higher efficiency of the wavelet neural network and wavelet neural – fuzzy than the neural network and neuro-fuzzy. Verification of hybrid models confirmed the efficiency of wavelet neural – fuzzy in comparing to the other models.