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

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

doi:https://doi.org/10.5194/amt-12-1697-2019

Articles | Volume 12, issue 3

https://doi.org/10.5194/amt-12-1697-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-12-1697-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 12, issue 3

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

Download

Final revised paper (published on 18 Mar 2019)
Preprint (discussion started on 02 Nov 2018)
Supplement to the preprint

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'Review of Di Noia et al “Retrieval of liquid water cloud properties from POLDER-3 measurements using a neural network ensemble approach”', Anonymous Referee #1, 30 Nov 2018
- AC1: 'Reply', Antonio Di Noia, 20 Feb 2019
RC2: 'Review on “ Retrieval of liquid water cloud properties from POLDER-3 measurements using a neural network ensemble approach” by Di Noia et al.', Anonymous Referee #2, 16 Jan 2019
- AC2: 'Reply', Antonio Di Noia, 20 Feb 2019

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision

AR by Antonio Di Noia on behalf of the Authors (20 Feb 2019) Author's response Manuscript

ED: Publish as is (21 Feb 2019) by Alexander Kokhanovsky

AR by Antonio Di Noia on behalf of the Authors (24 Feb 2019)

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.