Predicting Total Phosphorus Variation in Fengshan River Downstream Station of Taiwan Using Seven Types of Gm (1, 1) Model
If nutrients, such as nitrogen or phosphorus, are discharged into river, negative environmental effects will occur. Therefore, in this study, seven types of first-order and one-variable grey differential equation model (abbreviated as GM (1, 1) model) were established for predicting total phosphorus (TP) at Fengshan River downstream water quality monitoring station. The prediction performance of seven types of GM (1, 1) model was also compared. The results indicated that the values of grey parameter a and b were -0.00052983 and 6.929, respectively. In order to evaluate the prediction accuracy of GM (1, 1), the root mean squared error (RMSE) was adopted. The training RMSE values of 0.5587 – 0.5781 obtained from GM (1, 1, W), GM (1, 1, C), and GM (1, 1, x (1)) were lower than those of 0.6903 – 0.9406 from other GMs. The predicting RMSE values of 0.3060 – 0.3078 from GM (1, 1, x(0)), GM (1, 1, a), and GM (1, 1, b) were lower than those of 0.3115 – 0.4114 from other GMs.
Keywords- Fengshan River, Grey Model, Total Phosphorus, Water Quality