Articles | Volume 12, issue 3
https://doi.org/10.5194/amt-12-1697-2019
https://doi.org/10.5194/amt-12-1697-2019
Research article
 | 
18 Mar 2019
Research article |  | 18 Mar 2019

Retrieval of liquid water cloud properties from POLDER-3 measurements using a neural network ensemble approach

Antonio Di Noia, Otto P. Hasekamp, Bastiaan van Diedenhoven, and Zhibo Zhang

Data sets

MODIS Atmosphere {L3} Daily Product S. Platnick et~al. https://doi.org/10.5067/MODIS/MOD08_D3.006

Download
Short summary
We present a neural network algorithm for the retrieval of cloud physical properties from multi-angle polarimetric measurements. We have trained the algorithm on a large dataset of synthetic measurements and applied it to a year of POLDER-3 data. A comparison against MODIS cloud products reveals that our algorithm is capable of performing cloud property retrievals on a global scale and possibly improves the estimates of cloud effective radius over land with respect to existing POLDER-3 products.