16 Aug 2023
 | 16 Aug 2023
Status: this preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).

AI-derived 3D cloud tomography from geostationary 2D satellite data

Sarah Brüning, Stefan Niebler, and Holger Tost

Abstract. Satellite instruments provide spatially extended data with a high temporal resolution on almost global scales. However, nowadays, it is still a challenge to extract fully three-dimensional data from the current generation of satellite instruments, which either provide horizontal patterns or vertical profiles along the orbit track. Following this, we train a neural network in this study to generate three-dimensional cloud structures from MSG SEVIRI satellite data in high spatio-temporal resolution. We evaluate the derived artificial intelligence-based predictions against the along-track radar reflectivity from the CloudSat satellite. By inferring the pixel-wise cloud column to the satellite’s full disk, our results emphasize that spatio-temporal dynamics can be delineated for the whole domain. Robust reflectivities are derived for different cloud types with a clear distinction regarding the cloud's intensity, height, and shape. Cloud-free pixels tend to be over-represented because of the high imbalance between cloudy and clear-sky samples. The average error (RMSE) spans about 7.5 % (3.41 dBZ) of the total value range enabling the advanced analysis of vertical cloud properties. Although we receive high accordance between radar data and our predictions, the quality of the results varies with the complexity of the cloud structure. The representation of multi-level and mesoscale clouds is often simplified. Despite current limitations, the obtained results can help close current data gaps and exhibit the potential to be applied to various climate science questions, like the further investigation of deep convection through time and space.

Sarah Brüning et al.

Status: open (until 12 Oct 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2023-1834', Anonymous Referee #1, 08 Sep 2023 reply

Sarah Brüning et al.

Sarah Brüning et al.


Total article views: 330 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
197 124 9 330 6 4
  • HTML: 197
  • PDF: 124
  • XML: 9
  • Total: 330
  • BibTeX: 6
  • EndNote: 4
Views and downloads (calculated since 16 Aug 2023)
Cumulative views and downloads (calculated since 16 Aug 2023)

Viewed (geographical distribution)

Total article views: 319 (including HTML, PDF, and XML) Thereof 319 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 30 Sep 2023
Short summary
This study applies a Res-UNet to derive a comprehensive 3D cloud tomography from 2D satellite data over heterogeneous landscapes. We combine observational data from passive and active remote sensing sensors by an automated matching algorithm. This data is fed into a neural network to predict cloud reflectivities on the whole satellite domain between 5–24 km height. With an average RMSE of 3.41 dBZ, we contribute to closing existing data gaps in the representation of real-world cloud structures.