Ali Danandeh Mehr

Linear genetic programming application for successive-station monthly streamflow prediction

In recent decades, artificial intelligence (AI) techniques have been pronounced as a branch of computer science to model wide range of hydrological phenomena. A number of researches have been still comparing these techniques in order to find more effective approaches in terms of accuracy and applicability. In this study, we examined the ability of linear genetic programming (LGP) technique to model successive-station monthly streamflow process, as an applied alternative for streamflow prediction. A comparative efficiency study between LGP and three different artificial neural network algorithms, namely feed forward back propagation (FFBP), generalized regression neural networks (GRNN), and radial basis function (RBF), has also been presented in this study. For this aim, firstly, we put forward six different successive-station monthly streamflow prediction scenarios subjected to training by LGP and FFBP using the field data recorded at two gauging stations on Coruh River, Turkey. Based on Nash-Sutcliffe and root mean squared error measures, we then compared the efficiency of these techniques and selected the best prediction scenario. Eventually, GRNN and RBF algorithms were utilized to restructure the selected scenario and to compare with corresponding FFBP and LGP. Our results indicated the promising role of LGP for successive-station monthly streamflow prediction providing more accurate results than those of all the ANN algorithms. We found an explicit LGP-based expression evolved by only the basic arithmetic functions as the best prediction model for the river, which uses the records of the both target and upstream stations. We compared FFBP, GRNN, RBF neural networks and LGP for successive-station monthly streamflow prediction.Both ANNs and LGP models are more reliable in low and medium flow prediction.LGP is more capable of capturing extreme values than ANNs.LGP is superior to ANN in terms of overall accuracy and practical applicability.In contrast with implicit ANNs, LGP provided explicit equation for streamflow prediction.

Successive-station monthly streamflow prediction using neuro-wavelet technique

This study investigates the effect of discrete wavelet transform data pre-processing method on neural network-based successive-station monthly streamflow prediction models. For this aim, using data from two successive gauging stations on Çoruh River, Turkey, we initially developed eight different single-step-ahead neural monthly streamflow prediction models. Typical three-layer feed-forward (FFNN) topology, trained with Levenberg-Marquardt (LM) algorithm, has been employed to develop the best structure of each model. Then, the input time series of each model were decomposed into subseries at different resolution modes using Daubechies (db4) wavelet function. At the next step, eight hybrid neuro-wavelet (NW) models were generated using the subseries of each model. Ultimately, root mean square error and Nash-Sutcliffe efficiency measures have been used to compare the performance of both FFNN and NW models. The results indicated that the successive-station prediction strategy using a pair of upstream-downstream records tends to decrease the lagged prediction effect of single-station runoff-runoff models. Higher performances of NW models compared to those of FFNN in all combinations demonstrated that the db4 wavelet transform function is a powerful tool to capture the non-stationary feature of the successive-station streamflow process. The comparative performance analysis among different combinations showed that the highest improvement for FFNN occurs when simultaneous lag-time is considered for both stations.

Season Algorithm-Multigene Genetic Programming: A New Approach for Rainfall-Runoff Modelling

Genetic programming (GP) is recognized as a robust machine learning method for rainfall-runoff modelling. However, it may produce lagged forecasts if autocorrelation feature of runoff series is not taken carefully into account. To enhance timing accuracy of GP-based rainfall-runoff models, the paper proposes a new rainfall-runoff model that integrates season algorithm (SA) with multigene-GP (MGGP). The proposed SA-MGGP model was trained and validated for single- and two- and three-day ahead streamflow forecasts at Haldizen Catchment, Trabzon, Turkey. Timing and prediction accuracy of the proposed model were assessed in terms of different efficiency criteria. In addition, the efficiency results were compared to those of monolithic GP, MGGP, and SA-GP forecasting models developed in the present study as the benchmarks. The outcomes indicated that SA augments timing accuracy of GP-based models in the range 250% to 500%. It is also found that MGGP may identify underlying structure of the rainfall-runoff process slightly better than monolithic GP at the study catchment.

Climate Change Impacts on Catchment-Scale Extreme Rainfall Variability: Case Study of Rize Province, Turkey

AbstractThis paper conducts a catchment-scale analysis of extreme rainfall events of the reference (1961–1990) and three future climate periods (2013–2039, 2040–2070, and 2071–2100) for Rize Province, Turkey. The extreme value theory (EVT) is applied to analyze observational and projected extreme rainfall data including regional climate model (RCM) outputs guided by two general circulation models (GCM) under SRES-A2 and RCP8.5 greenhouse gas scenarios. A new rapid and effective bias correction method is also developed and applied to adjust the climate models simulations. The EVT analysis results demonstrated significant differences between the model runs for both the reference and future periods with considerable spatial variability in rainfall extremes. Based upon the assembled mean results, approximately a 30% decrease in the median value of extreme rainfall events is projected over the study region for the near future, 2013–2039, and middle of the century. This change dramatically decreases to 15% of i...