PM_2.5 Inversion Based on XGBoost And LightGBM Integrated Models

School of Electronic Information Engineering, Hebei University of Technology, Tianjin 300401, China

^* Corresponding author’s email: zhangyan@hebut.edu.cn

Abstract

Accurate inversion of PM2.5 concentration is crucial for haze management. Currently commonly used inversion methods cannot accurately invert the concentration in non-site areas, so this paper proposes a PM2.5 concentration inversion method based on an integrated learning model. The method utilises the Top Atmospheric Reflectance (TOAR), observation angle and meteorological element data as input features, and screens the important features by Random Forest, and constructs an integrated inversion model using XGBoost and LightGBM. The results show that the model built by TOAR improves R2 by 2.9% and reduces RMSE and MAE by 2.67 and 1.45, respectively, compared with the AOD-based model, and our model has an inversion accuracy of 0.95, which is better than other models. We used the model to estimate and analyse the historical PM2.5 concentration changes at Huaihe station in Tianjin, China, and the results were consistent with the trend of the actual PM2.5 concentration distribution, and it is clear that the proposed model has a high inversion accuracy.