TY - JOUR

T1 - Long-Term Forecasting of Air Pollution Particulate Matter (PM2. 5) and Analysis of Influencing Factors

AU - Zhang, Yuyi

AU - Sun, Qiushi

AU - Liu, Jing

AU - Petrosian, Ovanes

N1 - Zhang, Y.; Sun, Q.; Liu, J.; Petrosian, O. Long-Term Forecasting of Air Pollution Particulate Matter (PM2.5) and Analysis of Influencing Factors. Sustainability 2024, 16, 19. https://doi.org/10.3390/su16010019

PY - 2023/12/19

Y1 - 2023/12/19

N2 - Long-term forecasting and analysis of PM2.5, a significant air pollution source, is vital for environmental governance and sustainable development. We evaluated 10 machine learning and deep learning models using PM2.5 concentration data along with environmental variables. Employing explainable AI (XAI) technology facilitated explainability and formed the basis for factor analysis. At a 30-day forecasting horizon, ensemble learning surpassed deep learning in performance, with CatBoost emerging as the top-performing model. For forecasting horizons of 90 and 180 days, Bi-SLTM and Bi-GRU, respectively, exhibited the highest performance. Through an analysis of influencing factors by SHAP, it was observed that PM10 exerted the greatest impact on PM2.5 forecasting. However, this effect was particularly pronounced at higher concentrations of CO. Conversely, at lower CO concentrations, the impact of increased PM10 concentrations on PM2.5 was limited. Hence, it can be inferred that CO plays a pivotal role in driving these effects. Following CO, factors such as “dew point” and “temperature” were identified as influential. These factors exhibited varying levels of linear correlation with PM2.5, with temperature showing a negative correlation, while PM10, CO, and dew point generally demonstrated positive correlations with PM2.5.

AB - Long-term forecasting and analysis of PM2.5, a significant air pollution source, is vital for environmental governance and sustainable development. We evaluated 10 machine learning and deep learning models using PM2.5 concentration data along with environmental variables. Employing explainable AI (XAI) technology facilitated explainability and formed the basis for factor analysis. At a 30-day forecasting horizon, ensemble learning surpassed deep learning in performance, with CatBoost emerging as the top-performing model. For forecasting horizons of 90 and 180 days, Bi-SLTM and Bi-GRU, respectively, exhibited the highest performance. Through an analysis of influencing factors by SHAP, it was observed that PM10 exerted the greatest impact on PM2.5 forecasting. However, this effect was particularly pronounced at higher concentrations of CO. Conversely, at lower CO concentrations, the impact of increased PM10 concentrations on PM2.5 was limited. Hence, it can be inferred that CO plays a pivotal role in driving these effects. Following CO, factors such as “dew point” and “temperature” were identified as influential. These factors exhibited varying levels of linear correlation with PM2.5, with temperature showing a negative correlation, while PM10, CO, and dew point generally demonstrated positive correlations with PM2.5.

U2 - 10.3390/su16010019

DO - 10.3390/su16010019

M3 - Article

VL - 16

JO - Sustainability

JF - Sustainability

SN - 1937-0695

IS - 1

M1 - 19

ER -