Comparison between Regression Models, Support Vector Machine (SVM), and Artificial Neural Network (ANN) in River Water Quality Prediction

Both anthropogenic and natural sources of pollution are regionally significant. Therefore, in order to monitor protect the quality Langat River from deterioration, we use Artificial Intelligence (AI) model river water quality. This study has applied several machine learning models (two support vector machines (SVMs), six regression models, artificial neural network (ANN)) predict total suspended solids (TSS), (TS), dissolved (DS)) River, Malaysia. All have been assessed using root mean square error (RMSE), (MSE) as well determination coefficient (R2). Based on performance metrics, ANN outperformed all while GPR SVM exhibited characteristic over-fitting. The remaining fair poor performances. Although there a few researches conducted TDS ANN, however, less no research TS TSS River. this is first evaluate (TSS, TS, DS) aforementioned (especially models).