Analysis and prediction of air quality in Nanjing from autumn 2018 to summer 2019 using PCR\u2013SVR\u2013ARMA combined model

Bing Liu,Chaoyang Li,Yueqiang Jin

doi:10.1038/s41598-020-79462-0

Abstract

In order to correct the monitoring data of the miniature air quality detector, an air quality prediction model fusing Principal Component Regression (PCR), Support Vector Regression (SVR) machine, and Autoregressive Moving Average (ARMA) model was proposed to improve the prediction accuracy of the six types of pollutants in the air. First, the main information of factors affecting air quality is extracted by principal component analysis, and then principal component regression is used to give the predicted values of six types of pollutants. Second, the support vector regression machine is used to regress the predicted value of principal component regression and various influencing factors. Finally, the autoregressive moving average model is used to correct the residual items, and finally the predicted values of six types of pollutants are obtained. The experimental results showed that the proposed combination prediction model of PCR–SVR–ARMA had a better prediction effect than the artificial neural network, the standard support vector regression machine, the principal component regression, and PCR–SVR method. The Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and relative Mean Absolute Percent Error (MAPE) are used as evaluation indicators to evaluate the PCR–SVR–ARMA model. This model can increase the accuracy of self-built points by 72.6% to 93.2%, and the model has excellent prediction effects in the training set and detection set, indicating that the model has good generalization ability. This model can play an active role scientific arrangement and promotion of miniature air quality detectors and grid-based monitoring of the concentration of various pollutants.

Highlights

Introduction to air quality prediction modelMany scholars have conducted research on air quality prediction models
We first averaged the concentration of NO2 in a one-week period, and plotted the national control point data, Principal Component Regression (PCR)–Support Vector Regression (SVR)–Autoregressive Moving Average (ARMA) model fitting value, and self-built point data into a line chart
The air quality index (AQI) is a dimensionless index that quantitatively describes the condition of air quality

Summary

Introduction

Many scholars have conducted research on air quality prediction models. Air quality forecasting models mainly include statistical models based on machine learning and mechanism models based on atmospheric chemical analysis. The mechanism model of atmospheric chemical analysis is based on human scientific understanding of atmospheric physics and chemical processes. It uses mathematical methods combined with meteorological principles to simulate the physical and chemical processes of pollutants, simulate the processes of pollutants transport, reaction, and removal in the atmosphere, and uses the generated gridded data of pollutants to achieve air quality monitoring[6]. The mechanism model has high accuracy in weather forecasting, but it is not accurate in predicting the concentration of pollutants. Statistical models based on machine learning use statistical methods to analyze and model the collected pollutant data, and use mathematical algorithms to mine the internal relationships between variables from the data set

Methods

Findings

Discussion

Conclusion