Authors: TianJun CHANG*, East China Normal University, Zhongyang GUO, East China Normal University
Topics: Geography and Urban Health, Environment, Quantitative Methods
Keywords: Prophet; Random Forest; Time series prediction; Optimization model.
Session Type: Poster
Start / End Time: 9:55 AM / 11:35 AM
Room: Lincoln 2, Marriott, Exhibition Level
Presentation File: Download
The long-term scale prediction helps to analyze the development trend and law of things from a macroscopic perspective.In order to solve this problem, Prophet-RF combination pattern was established on the analysis of the Shanghai daily air quality index (AQI) for nearly four years. The Prophet model decomposes the AQI time series trend into growth items, seasonal and holiday effects. The Random Forest model is used to make up for the defect that the Prophet model cannot predict the stochastic nonlinear part, and to optimize the Prophet model. The optimization model is applied to forecast the scale of the AQI. The experimental results show: compared to the single Prophet model, the prediction results of the optimization model were more accurate, among them, the root mean square error and mean absolute error of fitting values decreased by 0.161 and 0.161 respectively, root mean square error and mean absolute error of predictive value decreased by 0.434 and 0.399 respectively; The optimization model has higher precision than time series prediction algorithm, and it’s very explanatory and has obvious advantages to predict the scale of time series .