Optimization of Land Use Regression Modelling of PM2.5 Spatial Variations in Different Seasons across China

Abstract

Fine particulate matter (PM2.5), one of the main components of haze, is of wide concern for its potential negative health effects. In order to further improve ambient air quality, it is essential to conclude the spatial variability of pollutants by investigating air pollution exposure. We divide China into two parts, north and south, and use a Land Use Regression (LUR) model to extract data including meteorological data, land use factors, and AOD retrievals, and use the machine learning algorithm to optimize the model to achieve predictions of the spatial distribution of near-surface PM2.5 mass concentrations in southern and northern China. We evaluated the seasonal consistency of the models in southern and northern China, and in northern China, we found a better fit with better seasonal consistency for the heating season and annual average model, while in southern China, we did not find a more fitted seasonal phase. The study illustrates that it is feasible to simulate the spatial distribution of PM2.5 mass concentration in large-scale areas based on the LUR model, and the seasonal consistency of the LUR model has been done to some extent.

Weather and the City: Machine Learning for Predicting and Attributing Fine Scale Air Quality to Meteorological and Urban Determinants

“…Some of the recent applications of ML to urban air quality include the work of Song et al 24 who used machine learning, in particular, Gradient Boosting, to produce city-scale PM 2.5 maps from mobile sensing and urban big data. Chai et al 25 employed XGBoost to predict the spatial distribution of PM 2.5 using meteorological and land use data. Li et al 26 used Random Forest to predict the concentration of PM 2.5 and coupled it with permutation importance and partial dependence plots to quantify the contribution of various chemical and elemental composition to air pollution events.…”