Preprints
https://doi.org/10.5194/egusphere-2024-1075
https://doi.org/10.5194/egusphere-2024-1075
12 Apr 2024
 | 12 Apr 2024
Status: this preprint is open for discussion.

Ensemble reconstruction of missing satellite data using a denoising diffusion model: application to chlorophyll a concentration in the Black Sea

Alexander Barth, Julien Brajard, Aida Alvera-Azcárate, Bayoumy Mohamed, Charles Troupin, and Jean-Marie Beckers

Abstract. Satellite observations provide a global or near-global coverage of the World Ocean. They are however affected by clouds (among others), which severely reduce their spatial coverage. Different methods have been proposed in the literature to reconstruct missing data in satellite observations. For many applications of satellite observations, it has been increasingly important to accurately reflect the underlying uncertainty of the reconstructed observations. In this paper, we investigate the use of a denoising diffusion model to reconstruct missing observations. Such methods can naturally provide an ensemble of reconstructions where each member is spatially coherent with the scales of variability and with the available data. Rather than providing a single reconstruction, an ensemble of possible reconstructions can be computed, and the ensemble spread reflects the underlying uncertainty. We show how this method can be trained from a collection of satellite data without requiring a prior interpolation of missing data and without resorting to data from a numerical model. The reconstruction method is tested with chlorophyll a concentration from the Ocean and Land Color Instrument (OLCI) sensor (onboard the satellites Sentinel- 3A and Sentinel-3B) on a small area of the Black Sea and compared with the neural network DINCAE (Data-Interpolating Convolutional Auto-Encoder). The spatial scales of the reconstructed data are assessed via a variogram, and the accuracy and statistical validity of the produced ensemble reconstructed are quantified using the continuous ranked probability score and its decomposition into reliability, resolution and uncertainty.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Alexander Barth, Julien Brajard, Aida Alvera-Azcárate, Bayoumy Mohamed, Charles Troupin, and Jean-Marie Beckers

Status: open (until 07 Jun 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-1075', Anonymous Referee #1, 22 May 2024 reply
Alexander Barth, Julien Brajard, Aida Alvera-Azcárate, Bayoumy Mohamed, Charles Troupin, and Jean-Marie Beckers
Alexander Barth, Julien Brajard, Aida Alvera-Azcárate, Bayoumy Mohamed, Charles Troupin, and Jean-Marie Beckers

Viewed

Total article views: 181 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
134 38 9 181 7 6
  • HTML: 134
  • PDF: 38
  • XML: 9
  • Total: 181
  • BibTeX: 7
  • EndNote: 6
Views and downloads (calculated since 12 Apr 2024)
Cumulative views and downloads (calculated since 12 Apr 2024)

Viewed (geographical distribution)

Total article views: 182 (including HTML, PDF, and XML) Thereof 182 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 22 May 2024
Download
Short summary
Most satellite observations have gaps, for example, due to clouds. This paper presents a method to reconstruct missing data in satellite observation of the chlorophyll a concentration in the Black Sea. Rather than giving a single possible reconstructed field, the discussed method provides an ensemble of possible reconstructions using a generative neural network. The resulting ensemble is validated using techniques from numerical weather prediction and ocean modelling.