AUTHOR=Karami Hojat , DadrasAjirlou Yashar , Jun Changhyun , Bateni Sayed M. , Band Shahab S. , Mosavi Amir , Moslehpour Massoud , Chau Kwok-Wing 

TITLE=A Novel Approach for Estimation of Sediment Load in Dam Reservoir With Hybrid Intelligent Algorithms

JOURNAL=Frontiers in Environmental Science

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2022.821079

DOI=10.3389/fenvs.2022.821079

ISSN=2296-665X

ABSTRACT=Predicting the amount of sediment in water resources projects is one of the most important measures to be taken, while sediments have an unknown nature in their behavior. In this research, using the data recorded at the Mazrae station between 2002 and 2013, the amount of sediment in the catchment area of Maku Dam has been predicted using different models of intelligent algorithms. Recorded data including river flow (Q) (m3/s), sediment concentration (CM) (mg/l), and temperature (T) (C°) were considered as input data and sediment load (SL) (ton/day) were considered as output data. Initially, using correlation test, the relationship between each input data with output data was considered. The results show high correlation of CM data, and discharge with sediment rate and low correlation of T (C°) data with these data. In order to find the best combination of data for prediction, the combination of single, binary and triple data was considered as sensitivity analysis. In order to achieve the purpose of this study, first with the classical Adaptive Neuro-Fuzzy Inference System (ANFIS), the amount of sediment was predicted, and then using evolutionary algorithms in ANFIS training, their performance was examined. The intelligent algorithms used in this study were Ant Colony Optimization extended to continuous domain (ACOr), Particle Swarm Optimization (PSO), Differential Evolution (DE), and Genetic Algorithm (GA), respectively. The results showed that ANFIS-ACOr, ANFIS-PSO, ANFIS-GA, ANFIS-DE and Classic ANFIS had the best performance in predicting the amount of SL, respectively. In the meantime, it was observed that the coefficient of determination (R2), root mean square error (RMSE) and Scatter index (SI) in the test mode for the ANFIS-ACOr algorithm with the best prediction dataset (CM+Q) are equal to 0.991, 13.001(ton/day), 0.112 and the ANFIS with the weakest prediction (T+Q) are equal to 0.490, 107.383 (ton/day), and 0.929, respectively. The present study showed that the use of intelligent algorithms in ANFIS training has been able to improve its performance in predicting the amount of sediment in the catchment area of Maku Dam.