University of Birjand-Research Group of Drought and Climate Change Journal of Drought and Climate change Research 3092-6076 4 1 2025 03 09 Estimation of Suspended Sediment in Coastal Areas of the Caspian Sea Using Machine Learning Techniques Estimation of Suspended Sediment in Coastal Areas of the Caspian Sea Using Machine Learning Techniques 1 18 3365 10.22077/jdcr.2025.8983.1121 FA Ebrahim Nohani Department of Civil Engineering, Materials and Energy Research Center, Dez.C., Islamic Azad University, Dezful, Iran. 0000-0002-2692-6253 Hamidreza Babaali Associate Professor, Department of Civil Engineering, Islamic Azad University, Khorramabad branch, Khorramabad, Iran 0000-0001-9410-879X Reza Dehghani PhD in Water Sciences and Engineering, Department of Soil Conservation and Watershed Management, Lorestan Province Agriculture and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization, Khorramab 0009-0008-3309-2286 Journal Article 2025 02 19 Modeling suspended sediment is a crucial subject for decision-makers at the watershed level. Accurate and reliable modeling of suspended sediment load is essential for planning, managing, and designing water resource structures and river systems. In this research, a new hybrid intelligent approach based on the Support Vector Regression (SVR) model has been developed for estimating river sediment. For this purpose, two optimization algorithms, namely Whale Optimization Algorithm (WOA) and Particle Swarm Optimization (PSO), were employed to model the amount of suspended river sediment. For modeling, statistical data from the Babolroud River hydrometric station, located in Mazandaran province, were used as a case study. Data from 19 input parameter combinations were used in the years 1382 to 1402 (solar calendar years) which is 2003-2023 Gregorian calendar. To evaluate the performance of the models, the evaluation criteria of correlation coefficient, root mean square error, mean absolute error, and Nash-Sutcliffe efficiency coefficient were used. The results showed that combined scenarios in the investigated models improve the performance of the model. The results obtained from the evaluation criteria also showed that the Wavelet-SVR model has a correlation coefficient of 0.962, a root mean square error of 0.344 ton/day, a mean absolute error of 0.158 ton/day, and a Nash-Sutcliffe efficiency coefficient of 0.970 in the validation phase. Overall, the results showed that the use of intelligent models based on the SVR approach can be an effective approach in river engineering stability. Modeling suspended sediment is a crucial subject for decision-makers at the watershed level. Accurate and reliable modeling of suspended sediment load is essential for planning, managing, and designing water resource structures and river systems. In this research, a new hybrid intelligent approach based on the Support Vector Regression (SVR) model has been developed for estimating river sediment. For this purpose, two optimization algorithms, namely Whale Optimization Algorithm (WOA) and Particle Swarm Optimization (PSO), were employed to model the amount of suspended river sediment. For modeling, statistical data from the Babolroud River hydrometric station, located in Mazandaran province, were used as a case study. Data from 19 input parameter combinations were used in the years 1382 to 1402 (solar calendar years) which is 2003-2023 Gregorian calendar. To evaluate the performance of the models, the evaluation criteria of correlation coefficient, root mean square error, mean absolute error, and Nash-Sutcliffe efficiency coefficient were used. The results showed that combined scenarios in the investigated models improve the performance of the model. The results obtained from the evaluation criteria also showed that the Wavelet-SVR model has a correlation coefficient of 0.962, a root mean square error of 0.344 ton/day, a mean absolute error of 0.158 ton/day, and a Nash-Sutcliffe efficiency coefficient of 0.970 in the validation phase. Overall, the results showed that the use of intelligent models based on the SVR approach can be an effective approach in river engineering stability. https://jdcr.birjand.ac.ir/article_3365_b445e314138101eecc58503e98aa2b2d.pdf