Long-Term Air Quality Evaluation System Prediction In China Based On Multinomial Logistic Regression Method

Abstract

The aim of this article evaluate the long-term air quality in China based on the air quality index (AQI) and the air quality composite index (AQCI) though the multinomial logistic regression method. The two developed models employ different dependent variables, AQI and AQCI, while maintaining the same controlled variables gross domestic product (GDP), and a primary pollutant. Explicitly, the primary impurity is associated with one or more contaminants among six pollutant factors: O3, PM2.5, PM10, NO2, SO2, and CO. Model quality verification is an integral part of our analysis. The results are illustrate d using real air quality data from China. The developed models were applied to predict AQI and ACQI for the 31 capital cities in China from 2013 to 2019 annually. All calculations and tests are conducted using R-studio. In summary, both models are able to predict China’s long-term air quality. A comparison of the AQI and AQCI models using the ROC curve reveals that the AQCI model exhibits greater significance than the AQI model.

Keywords

• multinomial logistic regression
• air quality index
• air quality composite index
• roc curve