Pezhman Allahbakhshian Farsani

The machine learning models (MLMs), including support vector regression (SVR), multivariate adaptive regression spline (MARS), boosted regression trees (BRT), and projection pursuit regression (PPR) are compared to traditional method i.e. nonlinear regression (NLR) in regional flood frequency analysis (RFFA). In this study, the Karun and Karkheh watersheds, which is located in the southwestern of Iran, with the same climatic and physiographic conditions are considered. Fifty-four hydrometric stations with a period of 21 years (1993–2013) are selected based on the instructions of U.S. Federal Agencies Bulletin 17 B were applied for RFFA. The generalized normal (GNO) probability distribution function (PDF) is selected by the L-moment method among five PDFs, including the GNO, generalized Pareto (GP), generalized logistic (GL), generalized extreme value (GEV) and Pearson type 3 (P ІІІ) to estimate flood discharge for the expected return periods. Twenty-five predictor variables, such as physiographic, climatologic, geologic, soil and land use variables are extracted. Follow land, maximum 24-h rainfall, mean watershed slope, compactness coefficient, mean and maximum watershed elevation variables are recognized as the appropriate combination of input using gamma test (GT). The overall results indicate that the SVR, PPR, and MARS models in comparison to the NLR and BRT models have a better performance to estimate flood discharge with the expected return periods. Future, the SVR model based on radial basis function (RBF) kernel is chosen as the best model in terms of the mean of the Nash-Sutcliff coefficient (M-Ef) and the mean of relative root mean squared error (M-RMSEr) (i.e. 0.94 and 63.93, respectively) for different return periods.

The machine learning models (MLMs), including support vector regression (SVR),
multivariate adaptive regression spline (MARS), boosted regression trees (BRT), and
projection pursuit regression (PPR) are compared to traditional method i.e. nonlinear
regression (NLR) in regional flood frequency analysis (RFFA). In this study, the Karun
and Karkheh watersheds, which is located in the southwestern of Iran, with the same
climatic and physiographic conditions are considered. Fifty-four hydrometric stations
with a period of 21 years (1993–2013) are selected based on the instructions of U.S.
Federal Agencies Bulletin 17 B were applied for RFFA. The generalized normal (GNO)
probability distribution function (PDF) is selected by the L-moment method among five
PDFs, including the GNO, generalized Pareto (GP), generalized logistic (GL), generalized
extreme value (GEV) and Pearson type 3 (P ІІІ) to estimate flood discharge for the
expected return periods. Twenty-five predictor variables, such as physiographic,
climatologic, geologic, soil and land use variables are extracted. Follow land, maximum
24-h rainfall, mean watershed slope, compactness coefficient, mean and maximum
watershed elevation variables are recognized as the appropriate combination of input
using gamma test (GT). The overall results indicate that the SVR, PPR, and MARS
models in comparison to the NLR and BRT models have a better performance to estimate
flood discharge with the expected return periods. Future, the SVR model based on radial
basis function (RBF) kernel is chosen as the best model in terms of the mean of the Nash-
Sutcliff coefficient (M-Ef) and the mean of relative root mean squared error (M-RMSEr)
(i.e. 0.94 and 63.93, respectively) for different return periods.

The hydrological parameters of rainfall, evaporation and runoff are influenced by the global warming as a new challenge in the world which affects on natural resources especially water sources. Climate change has many effects on hydrological cycle and consequently water resources and frequency and intensity if drought and flood in natural environment, society and economic. So, evaluating the variations in spatial and temporal pattern of precipitation is necessary to manage water resource in a region. The objective of this research was to assess the trend of the precipitation variations using Mann-kendall and Sen test in monthly, seasonal and annual scale and determine the variations and its direction using CUMSUM chart in last 50 year in northen Karoon watershed. Results showed that the annual precipitation of watershed has increased, but this increasing was not significant. As, 90%of stations shows the increasing trend in annual precipitation, but only 18% of stations has significa...

The calculation of energy loss in the design of water networks is a important factor, so that the original foundation of almost all the, water network construction design, studies and estimation of loss along the pipe lines has been made by empirical and theoretical formulae such as Darcy-Wisbakh, Hazen-williams and so on. In this research work first of all a comparison among the loss calculation empirical formulae including Darcy-Wisbakh and Hazen-Williams was made which it shows that regression analysis between the actual loss and calculated loss in Darcy-wisbakh’s formula is having the higher regression coefficient almost (R2=0.80) and on the other hand this comparison was made between the output of artificial neural network and the actual loss , that shows by far the higher regression coefficient almost (R2=0.87).The artificial neural networks technique was used for prediction of losses and the results showed that the neural network of multi-layers along with one hidden layer tan transfer function is having the significant capability to estimate and prediction of losses in the pipes.

The hydrological parameters of rainfall, evaporation and runoff are influenced by the global warming as a new challenge in the world which affects on natural resources especially water sources. Climate change has many effects on hydrological cycle and consequently water resources and frequency and intensity if drought and flood in natural environment, society and economic. So, evaluating the variations in spatial and temporal pattern of precipitation is necessary to manage water resource in a region. The objective of this research was to assess the trend of the precipitation variations using Mann-kendall and Sen test in monthly, seasonal and annual scale and determine the variations and its direction using CUMSUM chart in last 50 year in northern Karoon watershed. Results showed that the annual precipitation of watershed has increased, but this increasing was not significant. As, 90%of stations shows the increasing trend in annual precipitation, but only 18% of stations has significant trend. In seasonal scale the maximum increasing in precipitation was observed in autumn and the maximum decreasing trend in precipitation was recorded in spring. The maximum increasing trend in precipitation was recorded in December, whereas the maximum decreasing trend in precipitation was recorded in October and March. Annual variations in precipitation have been only occurred in Hana, Masjed¬Soleiman and Poul¬Zaman¬khan stations which is for the end of the forth decade to the prime of sixth decade. The results of this study are used to predicting and locating the future drought and scheduling and managing water resources of region.