Introduction Suspended sediment concentration (SSC) is a crucial parameter in surface water resource and riverine stability. However, traditional SSC prediction methods, such as sediment rating curves (SRCs), lack accuracy due to their inability to consider all influential factors. Consequently, hybrid models incorporating SRCs and artificial neural networks (ANNs) have emerged as a promising approach for enhancing SSC prediction accuracy. These models, with their ability to use complex nonlinear patterns, outperform traditional methods. This study aims to develop and implement an SRC-ANN hybrid model for SSC prediction. The proposed model is anticipated to significantly improve prediction accuracy by combining the strengths of both methods, aiding in optimal water resource management and the proper functioning of hydraulic structures.
Materials and methods This research introduces a novel hybrid model that integrates sediment rating curves (SRCs) and artificial neural networks (ANNs) to enhance the accuracy of suspended sediment prediction in the Naroun (Afejeh) hydrometric station. For this purpose, data on flow rate and suspended sediment for 222 samples was collected over a 50-years period (1971 to 2021). Fourteen different methods, including six sediment rating curve methods, six artificial neural network methods, and two hybrid methods, were used to simulate suspended sediment. The performance of each method was evaluated using statistical criteria such as coefficient of determination (R2), efficiency coefficient (ME), and mean relative error percentage (RME).
Results and discussion The results showed that among the sediment rating curve methods, the Median Segment Method with a coefficient of determination (R2) of 0.840, a modeling efficiency (ME) of 0.820, and a mean relative error (RME) of 0.211, and among the artificial neural network methods, the CANFIS method with a modeling efficiency (ME) of 0.8123 and a mean relative error (RME) of 0.248 provided a much more accurate simulation of the observed sediment flow status than other methods. Finally, in order to improve the prediction results, hybrid models 1 and 2 were used. The results showed that hybrid method 1, with a modeling efficiency (ME) of 0.8761 and a mean relative error (RME) of 0.06359 provided the best estimate of suspended sediment, accurately estimating both peak and base flow values, and this was identified as the most accurate method for suspended sediment prediction. These results highlight the potential of using hybrid model 1 to significantly improve prediction accuracy and to better fit the observed data.
Conclusion The Median Segment Method (MSM) was identified as the most accurate method for predicting suspended sediment due to its consideration of data distribution and flexibility. Artificial neural networks (ANNs) also performed well in simulating sediment for base and normal flows but were weaker in predicting sediment during flood events. Hybrid model 1, which combined the MSM and ANN methods, was found to be the most accurate method for suspended sediment prediction. Improper selection of a sediment prediction method can lead to inaccurate results. Researchers emphasize the need for further research and collecting simultaneous sediment concentration and flow data at different stations to improve modeling accuracy. Additionally, investigating the influence of variables other than flow on sediment is necessary. Utilizing hybrid models like the one presented in this study can significantly enhance the accuracy of suspended sediment prediction and serve as an effective tool for managing and predicting suspended sediment, ultimately leading to improved water resource management. Further development and optimization of hybrid methods, along with the utilization of more and more diverse data, are among the actions that can be taken to enhance model accuracy and improve outcomes. The Median Segment Method (MSM) was identified as the most accurate method for predicting suspended sediment due to its consideration of data distribution and flexibility. Artificial neural networks (ANNs) also performed well in simulating sediment for base and normal flows but were weaker in predicting sediment during flood events. Hybrid model 1, which combined the MSM and ANN methods, was found to be the most accurate method for suspended sediment prediction. Improper selection of a sediment prediction method can lead to inaccurate results. Researchers emphasize the need for further research and collecting simultaneous sediment concentration and flow data at different stations to improve modeling accuracy. Additionally, investigating the influence of variables other than flow on sediment is necessary. Utilizing hybrid models like the one presented in this study can significantly enhance the accuracy of suspended sediment prediction and serve as an effective tool for managing and predicting suspended sediment, ultimately leading to improved water resource management. Further development and optimization of hybrid methods, along with the utilization of more and more diverse data, are among the actions that can be taken to enhance model accuracy and improve outcomes. |