Preprints
https://doi.org/10.5194/amt-2023-145
https://doi.org/10.5194/amt-2023-145
04 Oct 2023
 | 04 Oct 2023
Status: this preprint is currently under review for the journal AMT.

Cloud Detection from Multi-Angular Polarimetric Satellite Measurements using a Neural Network Ensemble Approach

Zihao Yuan, Guangliang Fu, Bastiaan van Diedenhoven, Hai Xiang Lin, Jan Willem Erisman, and Otto P. Hasekamp

Abstract. This paper describes a neural network cloud masking scheme from PARASOL (Polarisation and Anisotropy of Reflectances for Atmospheric Science coupled with Observations from a Lidar) Multi-Angle Polarimetric measurements. The algorithm has been trained on synthetic measurements and has been applied to the processing of one year of PARASOL data. Comparisons of the retrieved cloud fraction with MODIS (Moderate Resolution Imaging Spectroradiometer) products show overall agreement in spatial and temporal patterns but the PARASOL-NN retrieves lower cloud fractions. Comparisons with a goodness-of-fit mask from aerosol retrievals suggest that the NN cloud mask flags less clear pixels as cloudy than MODIS (∼3 % of the clear pixels, versus ∼15 % by MODIS). On the other hand the NN classifies more pixels incorrectly as clear than MODIS (∼19 % by NN, versus ∼15 % by MODIS). Additionally, the NN and MODIS cloud mask have been applied to the aerosol retrievals from PARASOL using the Remote Sensing of Trace Gas and Aerosol Products (RemoTAP) algorithm. Validation with AERONET shows that the NN cloud mask performs comparably with MODIS in screening residual cloud contamination in retrieved aerosol properties. Our study demonstrates that cloud masking from MAP aerosol retrievals can be performed based on the MAP measurements themselves, making the retrievals independent of the availability of a cloud imager.

Zihao Yuan et al.

Status: open (extended)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Zihao Yuan et al.

Zihao Yuan et al.

Viewed

Total article views: 244 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
184 57 3 244 3 3
  • HTML: 184
  • PDF: 57
  • XML: 3
  • Total: 244
  • BibTeX: 3
  • EndNote: 3
Views and downloads (calculated since 04 Oct 2023)
Cumulative views and downloads (calculated since 04 Oct 2023)

Viewed (geographical distribution)

Total article views: 240 (including HTML, PDF, and XML) Thereof 240 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 05 Dec 2023
Download
Short summary
Currently, aerosol properties from spaceborne Multi-Angle Polarimeter (MAP) instruments can only be retrieved in cloud-free areas, or for areas where an aerosol layer is located above a cloud. Therefore, it is important to be able to identify cloud-free pixels for which an aerosol retrieval algorithm can provide meaningful output. The developed Neural Network cloud screening demonstrates that cloud masking for MAP aerosol retrieval can be based on the MAP measurements themselves.