جستجوی مقالات مرتبط با کلیدواژه « daily evaporation » در نشریات گروه « آبخیزداری، بیابان، محیط زیست، مرتع »

This research uses the multilayer perceptron (MLP) model to predict daily evaporation at two synoptic stations located in Rasht and Manjil, Guilan province, in north-west of Iran. Initially the most important combinations of climatic parameters for both of the stations were identified using the gamma test; and daily evaporation were modeled based on the obtained optimal combination. The results of the artificial neural network- Gamma Test (ANN-GT) model are evaluated using the root mean square errors (RMSE), correlation coefficient and Nash-Sutcliffe (NS) criteria. The results showed that the ANN-GT model for Rasht station with a correlation coefficient 0.86, root mean square error 0.95 and Nash-Sutcliffe criteria 0.74 and for Manjil station with correlation coefficient 0.94, root mean square error1.58 and Nash-Sutcliffe criteria 0.89 has an acceptable performance in predicting daily evaporation. To evaluate the uncertainty, we considered a percentage of data which were included in 95 percent of uncertainty (p-factor) and the average width of the 95ppu band (d-factor). Regarding the uncertainty results, the average with of 95PPU bound were obtained as 0.33 and 0.3 for the Manjil and Rasht stations, respectively. This shows the low uncertainty level of the ANN-GT model for predicting daily evaporation at both of the stations. Furthermore, the percentage of the observed data at 95PPU band was low and equal to %25 and %45 for the Rasht and Manjil stations, respectively. The reason for these low values can be due to low uncertainty in the parameters.

Using empirical models for estimating evaporation requires a lot of variables that some of them can not be measured in the stations. Therefore, this study aimed to simulate the daily evaporation of Tabriz synoptic satation using meteorological data including average temperature of air (úc), wind velocity mean (m/s), relative humidity (%) and sun light hours by Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Multivariate Regression (MR) in the different architectures and input variables. After standardization of data, 85% of the data was used for network training and the efficiency of models (with indicators RMSE and R2 indicators) was coducted on testing data that included 15% of data.The results illustrated that the optimal model of ANFIS were obtained grid method (with three Gaussian membership functions) when one and two variables used as inputs and gained cluster method when three and four variables used as inputs. Adding relative humidity variable to the multivariate regression model didnot cause a significant changes in validation criterias of the training and testing data and also sun light hour's variable was excluded from the multivariate regression model. The results showed that ANFIS simulation compared to multivariate regression can increase the coefficient of determination of model to more than 10 percent, which requires using of cluster method and four input variables (avearage temperature of air, wind velocity mean, relative humidity and sun light hours).