A Novel LSSVM Model Integrated with GBO Algorithm to Assessment of Water Quality Parameters

In this study, a novel least square support vector machine (LSSVM) model integrated with gradient-based optimizer (GBO) algorithm is introduced for the assessment of water quality (WQ) parameters. For purpose, three stations, including Ahvaz, Armand, and Gotvand in Karun river basin, have been selected to electrical conductivity (EC) total dissolved solids (TDS). First, prove superiority LSSVM-GBO algorithm, performance evaluated benchmark datasets (Housing, LVST, Servo). Then, results new hybrid were compared those artificial neural network (ANN), adaptive neuro-fuzzy interface system (ANFIS), LSSVM algorithms. Input combination WQ parameters EC TDS consists Ca+2, Cl−1, Mg+2, Na+1, SO4, HCO3, sodium absorption ratio (SAR), sum cation (Sum.C), anion (Sum.A), pH, Q. The modeling based on evaluation criteria showed significant among all Other that Ahvaz station, Sum.C, Sum.A, Na+1 parameters, Armand Cl−1 greatest impact was performed best input different time delays. highest accuracy station C1 delay.