Direct retrieval of NO2 vertical columns from UV-Vis (390-495 nm) spectral radiances using a neural network

Li, C., Xu, X., Liu, X., Wang, J., Sun, K., van Geffen, J., Zhu, Q., Ma, J., Jin, J., Qin, K., He, Q., Xie, P., Ren, B. and Cohen, R. C.: 2022,
J. Remote Sensing 2022, article ID 9817134, 17~pp.


Satellite retrievals of columnar nitrogen dioxide (NO2) are essential for the characterization of nitrogen oxides (NOx) processes and impacts. The requirements of modeled a priori profiles present an outstanding bottleneck in operational satellite NO2 retrievals. In this work, we instead use a neural network (NN) trained from over 360,000 radiative transfer (RT) simulations to translate TROPOMI radiances across 390-495 nm to total NO2 vertical column (NO2C). Despite the wide variability of the many input parameters in the RT simulations, only a small number of key variables were found essential to the accurate prediction of NO2C, including observing angles, surface reflectivity and altitude, and several key principal component scores of the radiances. In addition to the NO2C, the NN training and cross validation experiments show the wider retrieval window allows some information about the vertical distribution to be retrieved.
Applying the trained NN model to four months of TROPOMI data, the retrieved NO2C shows strong ability to reproduce the ground-based NO2C of the Pandonia Global Network. The R^2 (0.75) and normalized mean bias (NMB, -33%) are competitive with the level 2 operational TROPOMI product (R^2=0.81, NMB=-36%) over clear (geometric cloud fraction (geometric cloud fraction < 0.2) and polluted (NO2C ≥ 7.5 x 10^15 molecules/cm^2) regions. The NN retrieval approach is ~12 times faster than predictions using high spatial resolution (~3 km) a priori profiles, which is especially attractive to the handling of large-volume geostationary satellite data.

===> On-line paper  |  PDF file of the paper (17 pages; 2.0MB)

<=== Publications page
<=== Post-doc. research at KNMI page

Jos van Geffen -- Home  |  Site Map  |  Contact Me

created: 11 January 2021
last modified: 9 May 2022