Prediction of Dissolved Oxygen in Water Quality Based on Time Series Decomposition Characteristics
In order to improve the stability of the water ecosystem,a mixed prediction model of dissolved oxygen based on variational mode decomposition(VMD)was proposed.Dissolved oxygen was decomposed by VMD to obtain multiple IMFs,and different models were established according to the characteristics of different IMFs.Principal component analysis(PCA)and particle swarm optimization(PSO)to optimize the least squares vector machine model(LSSVM)was uesed in the nonlinear sequence part autoregressive integrated moving average model(ARIMA)was used in the linear sequence part.The prediction results of dissolved oxygen were obtained by combining the prediction results of each part.The model in this paper was applied to a monitoring point in the Changzhou section of the Bei-jing-Hangzhou Grand Canal.The results show that the average absolute error is 0.168,the root mean square error is 0.211,and the average absolute percentage error is 4.576.The mixed model can predict dissolved oxygen well and has certain practical significance for the management of water quality environment.
water quality dissolved oxygen predictiontime series decompositionvariational mode decompositionleast square support vector machineautoregressive integrated moving average model
万方数据
维普
