Prediction of daily PM2.5 concentration in China using data-driven ordinary differential equations
作者：
Highlights：
• A data-driven prediction method is proposed for the daily PM2.5 concentration prediction.
• This method combines genetic programming and orthogonal least square method to evolve ODE models.
• Results show that the ODE models obtain similar prediction results as the typical statistical model.
• The prediction results from this method are relatively good.
• It is the first attempt to evolve data-driven ODE models to study PM2.5 prediction.
摘要
•A data-driven prediction method is proposed for the daily PM2.5 concentration prediction.•This method combines genetic programming and orthogonal least square method to evolve ODE models.•Results show that the ODE models obtain similar prediction results as the typical statistical model.•The prediction results from this method are relatively good.•It is the first attempt to evolve data-driven ODE models to study PM2.5 prediction.
论文关键词：Concentration data,Genetic programming,Least square method,ODE models,PM2.5 prediction
论文评审过程：Received 18 September 2018, Revised 24 December 2019, Accepted 25 January 2020, Available online 14 February 2020, Version of Record 14 February 2020.
论文官网地址：https://doi.org/10.1016/j.amc.2020.125088
