Prediction of daily PM2.5 concentration in China using data-driven ordinary differential equations

Yufang Wang; Haiyan Wang; Shuhua Zhang

doi:10.1016/j.amc.2020.125088

Prediction of daily PM_2.5 concentration in China using data-driven ordinary differential equations

Yufang Wang, Haiyan Wang, Shuhua Zhang

Mathematical and Natural Sciences, School of (SMNS)

Research output: Contribution to journal › Article › peer-review

15 Scopus citations

Abstract

Accurate reporting and forecasting of PM_2.5 concentration are important for improving public health. In this paper, we propose a daily prediction method of PM_2.5 concentration by using data-driven ordinary differential equation (ODE) models. Specifically, based on the historical PM_2.5 concentration, this method combines genetic programming and orthogonal least square method to evolve the ODE models, which describe the transport of PM_2.5 and then uses the data-driven ODEs to predict the air quality in the future. Experiment results show that the ODE models obtain similar prediction results as the typical statistical model, and the prediction results from this method are relatively good. To our knowledge, this is the first attempt to evolve data-driven ODE models to study PM_2.5 prediction.

Original language	English (US)
Article number	125088
Journal	Applied Mathematics and Computation
Volume	375
DOIs	https://doi.org/10.1016/j.amc.2020.125088
State	Published - Jun 15 2020

Keywords

Concentration data
Genetic programming
Least square method
ODE models
PM prediction

ASJC Scopus subject areas

Computational Mathematics
Applied Mathematics

Access to Document

10.1016/j.amc.2020.125088

Cite this

@article{5ba3fd75dee34595a1bdbce6adda3a18,

title = "Prediction of daily PM2.5 concentration in China using data-driven ordinary differential equations",

abstract = "Accurate reporting and forecasting of PM2.5 concentration are important for improving public health. In this paper, we propose a daily prediction method of PM2.5 concentration by using data-driven ordinary differential equation (ODE) models. Specifically, based on the historical PM2.5 concentration, this method combines genetic programming and orthogonal least square method to evolve the ODE models, which describe the transport of PM2.5 and then uses the data-driven ODEs to predict the air quality in the future. Experiment results show that the ODE models obtain similar prediction results as the typical statistical model, and the prediction results from this method are relatively good. To our knowledge, this is the first attempt to evolve data-driven ODE models to study PM2.5 prediction.",

keywords = "Concentration data, Genetic programming, Least square method, ODE models, PM prediction",

author = "Yufang Wang and Haiyan Wang and Shuhua Zhang",

note = "Funding Information: The authors would like to thank the editor and referees for their helpful comments which improve the paper. This work is supported by Humanities and Social Sciences Research of the Humanities and Social Sciences Research of the Ministry of Education of China ( 18YJCZH184 ), Natural Science Foundation of Tianjin City ( 19JCQNJC14800 ), Postdoctoral Science Foundation of China ( 2018M640232 ) and National Social Science Fund of China (19CGL002). Publisher Copyright: {\textcopyright} 2020 Elsevier Inc.",

year = "2020",

month = jun,

day = "15",

doi = "10.1016/j.amc.2020.125088",

language = "English (US)",

volume = "375",

journal = "Applied Mathematics and Computation",

issn = "0096-3003",

publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Prediction of daily PM2.5 concentration in China using data-driven ordinary differential equations

AU - Wang, Yufang

AU - Wang, Haiyan

AU - Zhang, Shuhua

N1 - Funding Information: The authors would like to thank the editor and referees for their helpful comments which improve the paper. This work is supported by Humanities and Social Sciences Research of the Humanities and Social Sciences Research of the Ministry of Education of China ( 18YJCZH184 ), Natural Science Foundation of Tianjin City ( 19JCQNJC14800 ), Postdoctoral Science Foundation of China ( 2018M640232 ) and National Social Science Fund of China (19CGL002). Publisher Copyright: © 2020 Elsevier Inc.

PY - 2020/6/15

Y1 - 2020/6/15

N2 - Accurate reporting and forecasting of PM2.5 concentration are important for improving public health. In this paper, we propose a daily prediction method of PM2.5 concentration by using data-driven ordinary differential equation (ODE) models. Specifically, based on the historical PM2.5 concentration, this method combines genetic programming and orthogonal least square method to evolve the ODE models, which describe the transport of PM2.5 and then uses the data-driven ODEs to predict the air quality in the future. Experiment results show that the ODE models obtain similar prediction results as the typical statistical model, and the prediction results from this method are relatively good. To our knowledge, this is the first attempt to evolve data-driven ODE models to study PM2.5 prediction.

AB - Accurate reporting and forecasting of PM2.5 concentration are important for improving public health. In this paper, we propose a daily prediction method of PM2.5 concentration by using data-driven ordinary differential equation (ODE) models. Specifically, based on the historical PM2.5 concentration, this method combines genetic programming and orthogonal least square method to evolve the ODE models, which describe the transport of PM2.5 and then uses the data-driven ODEs to predict the air quality in the future. Experiment results show that the ODE models obtain similar prediction results as the typical statistical model, and the prediction results from this method are relatively good. To our knowledge, this is the first attempt to evolve data-driven ODE models to study PM2.5 prediction.

KW - Concentration data

KW - Genetic programming

KW - Least square method

KW - ODE models

KW - PM prediction

UR - http://www.scopus.com/inward/record.url?scp=85079277293&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85079277293&partnerID=8YFLogxK

U2 - 10.1016/j.amc.2020.125088

DO - 10.1016/j.amc.2020.125088

M3 - Article

AN - SCOPUS:85079277293

SN - 0096-3003

VL - 375

JO - Applied Mathematics and Computation

JF - Applied Mathematics and Computation

M1 - 125088

ER -