JWSS - Journal of Water and Soil Science

Regional flood frequency studies are initialized by the delineation of the homogeneous catchments. This study was based on "Region of Influence" concept, aiming to find the similar catchments in the south of Caspian Sea. The methodology utilized the Particle Swarm Optimization Algorithm, PSO, to optimize the fuzzy system over a dataset of catchment properties. The main catchment variables in relation to flood were determined by the principle component analysis method and employed as the inputs in the fuzzy system. Catchments grouping was performed over these fuzzy input variables by the iterative process. The optimum similar groups were obtained by PSO, and the heterogeneous L-moment index was used as the termination criterion for the optimization process. A total of 61 hydrometric stations located in the study area were selected and their relevant catchments' physical, climatic and hydrologic properties in relation to flood were studied. Principle Component Analysis by Variomax Rotation Factor over the catchments datasets tended to four out of 16 physical variables, including area, mean elevation, Gravelious Factor and Form Factor, as the main parameters in terms of homogeneity with 84 percent of accumulative variance. These variables, as well as mean annual rainfall, were used as the input data to define the fuzzy system. PSO algorithm was then employed to optimize the developed fuzzy system. The developed algorithm tended to yield the best result in the 9th iteration with 26 and 22 for the minimum average and the optimum values of cost function, respectively. The topology of the resulting algorithm included inertia weight, local and acceleration rates, the number of generations and population size, with the values of 0.7298, 1.4962, 1.4962, 10 and 5, respectively. This study tended to a total of 61 regions of influence, proportional to the relevant 61 sites. According to the geographical location of the catchments in the region, it could be concluded that the geographical proximity doesn't necessarily involve homogeneity. The obtained results indicated the efficient potential of PSO-FES in the delineation of the homogenous catchments in the study area.

The river flow prediction is a key aspect of hydrology that plays a significant role in water resources management, flood risk reduction, and agricultural planning. This study simulates the monthly flow of the Razavar River, located in western Iran, using an extreme learning machine (ELM) model enhanced by the Whale (WOA) Optimization Algorithm and Grasshopper Optimization Algorithm (GOA) metaheuristic optimization algorithms. The data used include river flow, precipitation, evaporation, and temperature, which were collected for 10 years with a monthly time step and normalized in the numerical range of zero to one. 80% of the data is used for training, and the remaining 20% for model evaluation. The performance of the models is measured with the statistical indices RMSE, NSE, and R². First, the basic ELM model is developed using the trial-and-error method to adjust the weights between the hidden and output layers. Then, the WOA and GOA algorithms are used to optimize the weights. The results show that the basic ELM model performs worse than the optimized models (Train: RMSE=0.1427, NSE=0.7795, R²=0.7911, Test: RMSE=0.1406, NSE=0.7811, R2=0.7916). While the WOA-ELM and GOA-ELM models provide similar results, the WOA-ELM model shows better performance in complex conditions (Train: RMSE=0.1215, NSE=0.7869, R2=0.7932, Test: RMSE=0.1165, NSE=0.7872, R2=0.7933). The results of this research show that meta-heuristic optimization algorithms play an important role in improving the performance of river flow prediction models due to their ability to search comprehensively and avoid getting stuck in local optima. The findings of this study emphasize the importance of applying these techniques in water resources management and sustainable planning and will pave the way for future research in this area.