Analysis and prediction of air quality in Nanjing from autumn 2018 to summer 2019 using PCR–SVR–ARMA combined model

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.

Application of RR-XGBoost combined model in data calibration of micro air quality detector

“…For the data whose self-built point cannot correspond to the national control point, this article directly deletes them. After preprocessing, a total of 4135 samples were obtained 13 , 24 . Table 1 describes the variables contained in the samples.…”

“…The artificial neural network model combined with an effective training algorithm can detect the complex and potentially non-linear relationship between the predictor variable and the response variable, and this model has become the current mainstream 13 , 16 – 18 . In addition, prediction methods such as Markov chain 19 – 21 , support vector machine 22 – 24 , and random forest 25 – 27 are also commonly used to predict the concentration of air pollutants. Because Extreme Gradient Boosting (XGBoost) has excellent computing efficiency and prediction accuracy, it has also been widely used in the prediction of air pollutant concentration in recent years.…”

Research on Data Correction Method of Micro Air Quality Detector Based on Combination of Partial Least Squares and Random Forest Regression

“…It has a total of 234,717 sets of data, and the interval between each set of data does not exceed 5 minutes. The self-built site not only provides data on the concentration of six types of pollutants (pollutant concentration refers to the mass concentration, that is, the mass of pollutants per unit volume of air), but it also provides five meteorological parameters [16]. Because the data detected by the electrochemical sensor in the micro air quality detector has errors, it needs to be corrected by the data of the national monitoring station.…”

Research on data correction method of micro air quality detector based on combination of partial least squares and random forest regression

“…It has a total of 234,717 sets of data, and the interval between each set of data does not exceed 5 minutes. The self-built site not only provides data on the concentration of six types of pollutants, but it also provides five meteorological parameters [16]. Because the data detected by the electrochemical sensor in the micro air quality detector has errors, it needs to be corrected by the data of the national monitoring station.…”

“…Traditional methods such as linear regression [10,11], time series [12,13], gray model [14], support vector machine [15][16][17][18], etc. are often used to predict the concentration of pollutants.…”