Global air quality index prediction using integrated spatial observation data and geographics machine learning

Abstract

Air pollution can occur in the whole world, with each region having its unique driving factors that contribute to human's health. However, effective mitigation of air pollution is often hindered by the uneven distribution of air quality monitoring stations, which tend to be concentrated in potential hotspots like major cities. This study aims to detect and improve the accuracy of the Global Air Quality Index from Remote Sensing (AQI-RS) by integrating AQI from ground-based stations with driving factors such as meteorological, environmental, sources of air pollution, and air pollution magnitude from satellite observation parameters as independent variables using Geographics Machine Learning (GML). This study utilizes 425 air pollution stations and the driving factors data globally from 2013 to 2024. The GML considers geographical characteristics in the analysis by calculating the optimal bandwidth area in its algorithm. The study employs nine scenarios to identify which parameters significantly contribute to the model and determine the best parameter combinations. In determining the best scenario, this study considers the R² value, Root Mean Square Error (RMSE), and uncertainty in each of the scenarios. This study produced an AQI-RS model with an average R², RMSE, and uncertainty in the best scenario of 0.89, 5.58, and 5.69 (AQI unit), respectively. The results indicate that GML significantly improves the accuracy of global AQI-RS over previous studies. By considering geographical characteristics using GML, this research is expected to gain an accurate prediction of AQI globally especially in regions without ground-based air pollution stations for the worldwide mitigation.