Utility of coactive neuro-fuzzy inference system for pan evaporation modeling in comparison with multilayer perceptron

Estimation of pan evaporation (E _pan) using black-box models has received a great deal of attention in developing countries where measurements of E _pan are spatially and temporally limited. Multilayer perceptron (MLP) and coactive neuro-fuzzy inference system (CANFIS) models were used to predict daily E _pan for a semi-arid region of Iran. Six MLP and CANFIS models comprising various combinations of daily meteorological parameters were developed. The performances of the models were tested using correlation coefficient (r), root mean square error (RMSE), mean absolute error (MAE) and percentage error of estimate (PE). It was found that the MLP6 model with the Momentum learning algorithm and the Tanh activation function, which requires all input parameters, presented the most accurate E _pan predictions (r?=?0.97, RMSE?=?0.81?mm?day^?1, MAE?=?0.63?mm?day^?1 and PE?=?0.58?%). The results also showed that the most accurate E _pan predictions with a CANFIS model can be achieved with the Takagi–Sugeno–Kang (TSK) fuzzy model and the Gaussian membership function. Overall performances revealed that the MLP method was better suited than CANFIS method for modeling the E _pan process.     

Shift changes and monotonic trends in autocorrelated temperature series over Iran

Temperature data from 29 synoptic stations in Iran for a period of 40?years (1966–2005) were analyzed to test for the existence of monotonic trends and shift changes in the annual, seasonal, and monthly mean air temperature series using the Mann–Kendall and Mann–Whitney tests. The influences of significant lag-1 serial correlation were eliminated from data by the trend-free pre-whitening method prior to the trend analysis. The magnitude of the temperature trends was derived from the Theil–Sen’s slope estimator. It was found that annual mean air temperature increased at 25 out of the 29 stations, of which 17 stations showed significant monotonic trends. The magnitude of the annual mean air temperature trends averagely was (+)0.224°C per decade. Most of the stations with the significant positive monotonic trends had a significant upward shift change. The analysis indicated that the change point year of the significant upward shift changes was 1972 for the whole stations except the coastal ones. Moreover, the strongest monotonic increasing trends and upward shift changes were observed in summer especially in August and September. The spatial analysis of the mean air temperature trends revealed the highest numbers of significant monotonic trends in the big cities of Iran. These findings provide more insights for better understanding of regional temperature behavior in the study area.     

Homogeneity analysis of precipitation series in Iran

Assessment of the reliability and quality of historical precipitation data is required in the modeling of hydrology and water resource processes and for climate change studies. The homogeneity of the annual and monthly precipitation data sets throughout Iran was tested using the Bayesian, Cumulative Deviations, and von Neumann tests at a significance level of 0.05. The precipitation records from 41 meteorological stations covering the years between 1966 and 2005 were considered. The annual series of Iranian precipitation were found to be homogeneous by applying the Bayesian and Cumulative Deviations tests, while the von Neumann test detected inhomogeneities at seven stations. Almost all the monthly precipitation data sets are homogeneous and considered as “useful.” The outputs of the statistical tests for the homogeneity analysis of the precipitation time series had discrepancies in some cases which are related to different sensitivities of the tests to break in the time series. It was found that the von Neumann test is more sensitive than the Bayesian and Cumulative Deviations tests in the determination of inhomogeneity in the precipitation series.