Environmental Factors Assisted the Evaluation of Entropy Water Quality Indices with Efficient Machine Learning Technique

Water is an indispensable resource for human production and life. The evaluation of water quality by scientific methods provides sufficient support the regeneration recycling resources. In this study, entropy theory was used to evaluate overcomes limitations traditional assessment, which does not consider impact different environmental factors on quality. Considering complexity process, two typical machine learning (ML) – generalized regression neural network (GRNN) vector (SVM) were predict index (EWQI). Correlation analysis applied divide into combinations that subsequently acted as input ML model. According results root mean squared error (RMSE), SVM selected better prediction Then, four types optimization algorithms optimize calculate nonlinear predictions classifications After analyzing with indicators, algorithm differential gray wolf (DE-GWO) achieved markedly performance than other three algorithms, has important advantages in avoiding model falling a local optimal solution. study have significant guidance could make further contributions rational use protection