Prediction of daily PM2.5 concentration in China using partial differential equations

Accurate reporting and forecasting of PM2.5 concentration are important for improving public health. In this paper, we propose a partial differential equation (PDE) model, specially, a linear diffusive equation, to describe the spatial-temporal characteristics of PM2.5 in order to make short-term pr...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2018-06, Vol.13 (6), p.e0197666
Main Authors: Wang, Yufang, Wang, Haiyan, Chang, Shuhua, Avram, Adrian
Format: Article
Language:English
Subjects:
Air Pollutants - toxicity
Air Pollution - adverse effects
Airborne particulates
Applied mathematics
Biology
China
Cities
Computer and Information Sciences
Computer viruses
Differential equations
Distributed processing
Earth Sciences
Ecology and Environmental Sciences
Engineering and Technology
Environmental Monitoring
Epidemiology
Forecasting
Humans
International conferences
Mathematical models
Methods
Model accuracy
Navier-Stokes equations
Neural networks
Ordinary differential equations
Partial differential equations
Particle Size
Particulate matter
Particulate Matter - toxicity
People and Places
Physical Sciences
Physics
Pollution
Predictions
Public health
Remote sensing
Research and Analysis Methods
Social Networking
Social networks
Social Sciences
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate reporting and forecasting of PM2.5 concentration are important for improving public health. In this paper, we propose a partial differential equation (PDE) model, specially, a linear diffusive equation, to describe the spatial-temporal characteristics of PM2.5 in order to make short-term prediction. We analyze the temporal and spatial patterns of a real dataset from China's National Environmental Monitoring and validate the PDE-based model in terms of predicting the PM2.5 concentration of the next day by the former days' history data. Our experiment results show that the PDE model is able to characterize and predict the process of PM2.5 transport. For example, for 300 continuous days of 2016, the average prediction accuracy of the PDE model over all city-regions is 93% or 83% based on different accuracy definitions. To our knowledge, this is the first attempt to use PDE-based model to study PM2.5 prediction in both temporal and spatial dimensions.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0197666