Mohammad Ansari Ghojghar; Masoud Pourgholam-Amiji; Shahab Araghinejad; Banafsheh Zahraie; Saman Razavi; Ali Salajegheh
Abstract
Due to the growing development of meta-models and their combination with optimization algorithms for modeling and predicting meteorological variables, in this research four metaheuristic optimization algorithms of Particle Swarm Optimization (PSO), Genetics Algorithms (GA), Ant Colony Optimization for ...
Read More
Due to the growing development of meta-models and their combination with optimization algorithms for modeling and predicting meteorological variables, in this research four metaheuristic optimization algorithms of Particle Swarm Optimization (PSO), Genetics Algorithms (GA), Ant Colony Optimization for Continuous Domains (ACOR) and Differential Evolutionary (DE) were combined with the adaptive neural-fuzzy inference system (ANFIS) model. The performance of four combined models developed with ANFIS model to predict the Frequency variables of Dust Stormy Days (FDSD) on a seasonal scale in Khuzestan province in the southwest of Iran was evaluated. For this purpose, hourly dust data and codes of the Word Meteorological Organization were used on a seasonal scale with a statistical period of 40 years (1980-2019) in seven synoptic stations of Khuzestan province. The results of good fit indices in the training and testing phase showed that there is no significant difference between the ANFIS method and other combined models used. R and RMSE values of the best combined model (ANFIS-PSO) from 0.88 to 0.97 and 0.10 to 0.19, respectively, and in the ANFIS model from 0.83 to 0.94 and 0.11 to 21, respectively, were variable. The results also showed that the combination of optimization algorithms used with the ANFIS model does not significantly improve the results of the model compared to the individual ANFIS model.
Ali Fazlollahi; Ali Salajegheh; Sadat Feiznia; Hassan Ahmadi
Abstract
Sediment fingerprinting is a method for identifying sediment sources and determining the rate of contribution of each source. In this method, the natural tracer technology is used, that combined from samples collection, laboratory analyzing and statistical modeling. The natural tracers are measured in ...
Read More
Sediment fingerprinting is a method for identifying sediment sources and determining the rate of contribution of each source. In this method, the natural tracer technology is used, that combined from samples collection, laboratory analyzing and statistical modeling. The natural tracers are measured in both the sources and suspended sediment to determine the rate of contribution each sources. The suspended sediment traps were constructed and used for the first time in country. In this research sediment fingerprinting was used in the loess area. 27 tracers were measured in all samples. Data were evaluated about outlier. The capability of each tracer in separating the sources was evaluated with kruskal-wallis test. All tracers were accepted. Then the best combination of tracers was determined with discriminate analysis. This combination is total carbon, Na, organic carbon, Pb, Co, Sr, Al, C/N and Rb. Then, the rate of contribution of each source was determined with normal method and optimized method. Among all the sediment sources, Gully and forest have the highest and lowest rates, respectively. The field observations were confirmed the results. The use of genetic algorithm increased the accuracy of determination of contribution of each source in comparison to normal method
Hamed Rouhani; Mohsen Farahi Moghadam
Abstract
In the past decades, much effort has been devoted to simulation of the rainfall-runoff process. Hydrological models are simplified representations of the natural hydrologic system. In each case, the choice of the model to be applied depends mainly on the objective of the modeling but also on the available ...
Read More
In the past decades, much effort has been devoted to simulation of the rainfall-runoff process. Hydrological models are simplified representations of the natural hydrologic system. In each case, the choice of the model to be applied depends mainly on the objective of the modeling but also on the available information. The relative performances of two lumped conceptual-based hydrology models (Tank and SYMHYD) were compared based on daily data of Chehel_Chay catchment in the northeast region of Golestan province. As in Tank and SIMHYD models, parameter spaces are high dimensional, it is difficult to obtain optimal parameters using manual trial and error procedure. These parameters need to be estimated through an inverse method by calibration. Therefore, an automatic optimization procedure based on the Genetic Algorithm (GA) was tested for parameter calibration of two models. For testing the applicability of the model in gauged basin, the model was calibrated for a period of 1992–1996 and validated for a period of 2002–2005. The result showed that RMSE of discharge predictions were as low as 0.821 for a Nash-Sutcliffe coefficient of 0.599 for the Tank model, against 0.819 for a Nash-Sutcliffe coefficient of 0.602 for the SYMHYD model in calibration period. When evaluating the model performance in validation period, SYMHYD model is performing most accurately with RMSE=0.490 and E=0617. It was found the RMSE for Tank model is 0.522, which is slightly higher than SIMHYD (RMSE=0.490). SIMHYD is performing most accurately with E equal to 0.602 and 0.607 in calibration and validation periods, respectively.
