Application of Bayesian Optimized Random Forest Model in Drinking Water Quality Prediction

Abstract

With the increasing pressure on water resources, the drinkability of water has become a global concern. This paper presents a Random Forest (RF) model for water quality drinkability prediction, which integrates boxplot detection, Pearson correlation analysis, and Bayesian optimization. The method identifies outliers using boxplot detection, selects key water quality parameters through Pearson correlation analysis, and optimizes RF model hyperparameters using Bayesian optimization. Experimental results show that the proposed model significantly outperforms traditional machine learning models in terms of prediction accuracy and generalization ability, providing a more efficient tool and method for sustainable water resource management and water quality assessment.