Estimation of Daily Suspended Sediment Load Using a Novel Hybrid Support Vector Regression Model Incorporated with Observer-Teacher-Learner-Based Optimization Method

Predicting suspended sediment load (SSL) in water resource management requires efficient and reliable predicted models. This study considers the support vector regression (SVR) method to predict daily suspended sediment load. Since the SVR has unknown parameters, the observer-teacher-learner-based Optimization (OTLBO) method is integrated with the SVR model to provide a novel hybrid predictive model. The SVR combined with the genetic algorithm (SVR-GA) is used as an alternative model. To explore the performance and application of the proposed models, five input combinations of rainfall and discharge data of Cham Siah River catchment are provided. The predictive models are assessed using various numerical and visual indicators. The results indicate that the SVR-OTLBO model offers a higher prediction performance than other models employed in the current study. Specifically, SVR-OTLBO model offers highest Pearson correlation coefficient (R = 0.9768), Willmott's Index (WI = 0.9812), ratio of performance to IQ (RPIQ = 0.9201), and modified index of agreement (md = 0.7411) and the lowest relative root mean square error (RRMSE = 0.5371) in comparison with SVR-GA (R = 0.9704, WI = 0.9794, RPIQ = 0.8521, and md = 0.7323, 0.5617) and SVR (R = 0.9501, WI = 0.9734, RPIQ = 0.3229, md = 0.4338, and RRMSE = 1.0829) models, respectively.

Automated summary

In water resource management, predicting suspended sediment load is crucial. This study introduces a novel hybrid predictive model combining SVR with OTLBO, outperforming other models by achieving the highest prediction performance.