Publications

Liu, JJ (). Generating 250 m-resolution regional NO2 concentration products first from MODIS retrievals using extreme gradient boosting. AIR QUALITY ATMOSPHERE AND HEALTH.

Abstract
Surface Nitrogen dioxide (NO2) is highly related to multiple adverse human health and environmental effects. The current satellite-derived surface NO2 products generally have a coarse spatial resolution, limiting their applications in evaluating the spatial characteristics of NO2 in urbans and their central districts, where the NO2 pollution and population density are relatively high. This study proposes an approach to produce the 250 m surface NO2 concentrations using an ensemble learning model based on MODIS-derived surface PM2.5 concentrations. It is the first time to produce such high spatial resolution of NO2 products from the satellite retrievals with high frequency. The approach was tested over the Yangtze River Delta (YRD) urban agglomeration of China. The model has high accuracy on instantaneous NO2 estimations with a cross-validated coefficient of determination of 0.82, a root-mean-square error of 8.5 mu g/m(3), and a mean prediction error of 6.2 mu g/m(3), and a mean relative prediction error of 20.8%, respectively. The model accurately captures the fine-detailed distribution of NO2 concentrations over the YRD region, urbans, and their central districts in YRD under different atmospheric pollutant levels. The ultrahigh spatial resolution NO2 products have an obvious advantage for producing finer NO2 distribution, possibly offering a way for locating NO2 emission sources and monitoring the local NO2 episodes. The products are useful for air pollution monitoring, controlling, and epidemiological- and environmental-related studies, especially in urbans and their districts. The study enriches the applications of MODIS in environmental studies.

DOI:
10.1007/s11869-022-01285-x

ISSN:
1873-9326