A Simple and Effective Random Forest Refit to Map the Spatial Distribution of NO2 Concentrations

Abstract

This study proposes a random forest–random pixel ID (RF–RID) method, which could reduce local anomalies in the simulation of NO2 spatial distribution and significantly improve prediction accuracy in rural areas. First, the 470 nm MAIAC AOD and OMI NO2 total and tropospheric vertical column were packed using the two-step method (TWS). Second, using RID, the filled data and auxiliary variables were combined with random forest (RF) to build an RF–RID model to predict the 1 km/d NO2 spatial distribution in southwestern Fujian (SWFJ) in 2018. The results show that the RF–RID achieves enhanced performance in the CV of the observed sample (R = 0.9117, RMSE = 3.895). Meanwhile, RF–RID has a higher correlation with the road length (RL) in remote areas, and the proposed method solves the issue related to strips or patches of NO2 spatial distribution. This model offers insights into the related research on air pollutants in large areas.