Articles | Volume 16, issue 23
https://doi.org/10.5194/amt-16-5863-2023
https://doi.org/10.5194/amt-16-5863-2023
Research article
 | 
07 Dec 2023
Research article |  | 07 Dec 2023

Simultaneous retrieval of aerosol and ocean properties from PACE HARP2 with uncertainty assessment using cascading neural network radiative transfer models

Meng Gao, Bryan A. Franz, Peng-Wang Zhai, Kirk Knobelspiesse, Andrew M. Sayer, Xiaoguang Xu, J. Vanderlei Martins, Brian Cairns, Patricia Castellanos, Guangliang Fu, Neranga Hannadige, Otto Hasekamp, Yongxiang Hu, Amir Ibrahim, Frederick Patt, Anin Puthukkudy, and P. Jeremy Werdell
Short summary
This study evaluated the retrievability and uncertainty of aerosol and ocean properties from PACE's HARP2 instrument using enhanced neural network models with the FastMAPOL algorithm. A cascading retrieval method is developed to improve retrieval performance. A global set of simulated HARP2 data is generated and used for uncertainty evaluations.  The performance assessment demonstrates that the FastMAPOL algorithm is a viable approach for operational application to HARP2 data after PACE launch.