Binary Coati Optimization Algorithm- Multi- Kernel Least Square Support Vector Machine-Extreme Learning Machine Model (BCOA-MKLSSVM-ELM): A New Hybrid Machine Learning Model for Predicting Reservoir Water Level

Predicting reservoir water levels helps manage droughts and floods. level is complex because it depends on factors such as climate parameters human intervention. Therefore, predicting needs robust models. Our study introduces a new model for levels. An extreme learning machine, the multi-kernel least square support vector machine (MKLSSVM), developed to predict of in Malaysia. The also novel optimization algorithm selecting inputs. While LSSVM may not capture nonlinear components time series data, (ELM) model—MKLSSVM can linear data. A coati introduced select input scenarios. MKLSSVM takes advantage multiple kernel functions. model—multi-kernel benefit both ELM models This paper’s novelty includes introducing method inputs developing For prediction, lagged rainfall are used. In this study, we used (ELM)-multi-kernel (ELM-MKLSSVM), (ELM)-LSSVM-polynomial function (PKF) (ELM-LSSVM-PKF), ELM-LSSVM-radial basis (RBF) (ELM-LSSVM-RBF), ELM-LSSVM-Linear Kernel (LKF), ELM, level. testing means absolute same was 0.710, 0.742, 0.832, 0.871, 0.912, 0.919, respectively. Nash–Sutcliff efficiency (NSE) 0.97, 0.94, 0.90, 0.87, 0.83, 0.18, ELM-MKLSSVM tool