Articles | Volume 14, issue 6
https://doi.org/10.5194/amt-14-4083-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-14-4083-2021
© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Efficient multi-angle polarimetric inversion of aerosols and ocean color powered by a deep neural network forward model
Ocean Ecology Laboratory – Code 616, NASA Goddard Space Flight Center, Greenbelt, Maryland 20771, USA
Science Systems and Applications, Inc., Greenbelt, MD, USA
Bryan A. Franz
Ocean Ecology Laboratory – Code 616, NASA Goddard Space Flight Center, Greenbelt, Maryland 20771, USA
Kirk Knobelspiesse
Ocean Ecology Laboratory – Code 616, NASA Goddard Space Flight Center, Greenbelt, Maryland 20771, USA
Peng-Wang Zhai
JCET and Physics Department, University of Maryland, Baltimore County, Baltimore, MD 21250, USA
Vanderlei Martins
JCET and Physics Department, University of Maryland, Baltimore County, Baltimore, MD 21250, USA
Sharon Burton
MS 475, NASA Langley Research Center, Hampton, VA 23681-2199, USA
Brian Cairns
NASA Goddard Institute for Space Studies, New York, NY 10025, USA
Richard Ferrare
MS 475, NASA Langley Research Center, Hampton, VA 23681-2199, USA
Joel Gales
Ocean Ecology Laboratory – Code 616, NASA Goddard Space Flight Center, Greenbelt, Maryland 20771, USA
Science Applications International Corp., Greenbelt, MD, USA
Otto Hasekamp
Netherlands Institute for Space Research (SRON, NWO-I), Utrecht, the Netherlands
Yongxiang Hu
MS 475, NASA Langley Research Center, Hampton, VA 23681-2199, USA
Amir Ibrahim
Ocean Ecology Laboratory – Code 616, NASA Goddard Space Flight Center, Greenbelt, Maryland 20771, USA
Science Systems and Applications, Inc., Greenbelt, MD, USA
Brent McBride
JCET and Physics Department, University of Maryland, Baltimore County, Baltimore, MD 21250, USA
Science Systems and Applications, Inc., Greenbelt, MD, USA
Anin Puthukkudy
JCET and Physics Department, University of Maryland, Baltimore County, Baltimore, MD 21250, USA
P. Jeremy Werdell
Ocean Ecology Laboratory – Code 616, NASA Goddard Space Flight Center, Greenbelt, Maryland 20771, USA
Xiaoguang Xu
JCET and Physics Department, University of Maryland, Baltimore County, Baltimore, MD 21250, USA
Data sets
Aerosol Characterization from Polarimeter and Lidar ACEPOL Science Team https://doi.org/10.5067/SUBORBITAL/ACEPOL2017/DATA001
FastMAPOL AirHARP Level 2 data product M. Gao https://data.nasa.gov/Earth-Science/FastMAPOL_ACEPOL_AIRHARP_L2/8b9y-7rgh
Download
- Article
(7812 KB) - Full-text XML
Short summary
Multi-angle polarimetric measurements can retrieve accurate aerosol properties over complex atmosphere and ocean systems; however, most retrieval algorithms require high computational costs. We propose a deep neural network (NN) forward model to represent the radiative transfer simulation of coupled atmosphere and ocean systems and then conduct simultaneous aerosol and ocean color retrievals on AirHARP measurements. The computational acceleration is 103 times with CPU or 104 times with GPU.
Multi-angle polarimetric measurements can retrieve accurate aerosol properties over complex...