Advanced hybrid frameworks for water quality index prediction
Mohammad Ehteram, Somayeh Soltani-Gerdefaramarzi
Abstract
The water quality index (WQI) is a critical parameter that must be accurately predicted to ensure the sustainable management of water resources. Thus, our study develops the sine cosine optimization algorithm (SCOA)- long short-term memory (LSTM) − Extreme gradient boosting (XGBoost), SCOA- LSTM − least square support vector machine (LSSVM), crow optimization algorithm (COA)- LSTM-XGBoost, and COA-LSTM-LSSVM models to predict WQI in Aidoghmoush river, Iran. First, COA and SCOA adjust the parameters of LSTM, LSSVM, and XGBoost. Then, LSTM captures temporal patterns in the time series data, which include water quality parameters. Finally, the LSSVM and XGBoost models use the captured patterns to make final predictions. Our results demonstrate that the SCOA-LSTM-XGBoost model achieves a Willmott’s index (WI) of 0.96, an explained variance score (EVS) of 0.95, and a t-statistic (TS) of 0.021. The results of our paper show that SCOA-LSTM-XGBoost is a reliable model for predicting WQI.