JWSS - Journal of Water and Soil Science

The rapid and complex movement of sediments in rivers and coastal areas with highly erosive and unsteady flows presents river engineers with numerous problems in the geomorphology of alluvial rivers. Accurately predicting these complex processes in the water-sediment system (a multiphase, dense, granular flow system) is still a major challenge for mesh-based models. Due to the ability of meshless Lagrangian methods to model large deformations and discontinuities, meshless Lagrangian methods can provide a unique way to deal with this complexity. In the current research, the capabilities of the weakly compressibility moving particle semi-implicit (WC-MPS) model in soil-fluid interaction modeling are developed to enable the modeling of sediment transport and erosion effects behind coastal walls. In this method, granular material is considered a non-Newtonian and viscoplastic fluid. The 𝜇(I) rheological model has been used to predict the non-Newtonian behavior of the granular phase. To verify the application of the present model in simulating the interaction of liquid and solid phases, first, the widely used problem of dam break on an erodible bed was modeled. The NRMSE model was calculated to be approximately 6%, which indicates the efficiency and accuracy of the target model in this problem. At the end, the scouring of coastal walls was simulated by the WC-MPS method using 𝜇(I) rheology model. Investigations show that the processes related to erosion and scouring can be well modeled using the current Lagrangian method. The numerical results show excellent agreement with the laboratory measurements. It should be noted that the mean error of the mentioned model is estimated to be 10%.

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.