Study on Water Quality Prediction of Fuxian Lake Based on Elman Network

In this paper, a water quality prediction model based on Elman neural network is established to predict the concentration of NH3-N in Gushan monitoring station of Fuxian Lake. First, by analyzing the correlation coefficient, the input is divided into two categories: confirmation and to be verified. Secondly, the Elman model with different inputs is established, and the influence of variables on the prediction results is analyzed. Finally, the extreme value and mutation rate of prediction are improved. The results show that the meteorological factors pre, Rhu, win, SSD and time factor month can be used to predict the change of NH3-N, the MSE value of the model is less than 0.001, the RMSE value is less than 0.1, and the RMSE value of the optimized model is reduced to 0.019. Elman water quality prediction model has high prediction accuracy.