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