Ensemble reconstruction of missing satellite data using a denoising diffusion model: application to chlorophyll <i>a</i> concentration in the Black Sea
<p>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....
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2024-12-01
|
| Series: | Ocean Science |
| Online Access: | https://os.copernicus.org/articles/20/1567/2024/os-20-1567-2024.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850058101792702464 |
|---|---|
| author | A. Barth J. Brajard A. Alvera-Azcárate B. Mohamed C. Troupin J.-M. Beckers |
| author_facet | A. Barth J. Brajard A. Alvera-Azcárate B. Mohamed C. Troupin J.-M. Beckers |
| author_sort | A. Barth |
| collection | DOAJ |
| description | <p>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 <span class="inline-formula"><i>a</i></span> concentration from the Ocean and Land Colour Instrument (OLCI) sensor (aboard 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 reconstructed ensemble are quantified using the continuous ranked probability score and its decomposition into reliability, resolution, and uncertainty.</p> |
| format | Article |
| id | doaj-art-3ade75df387e476285e60ea1d1382893 |
| institution | DOAJ |
| issn | 1812-0784 1812-0792 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Ocean Science |
| spelling | doaj-art-3ade75df387e476285e60ea1d13828932025-08-20T02:51:15ZengCopernicus PublicationsOcean Science1812-07841812-07922024-12-01201567158410.5194/os-20-1567-2024Ensemble reconstruction of missing satellite data using a denoising diffusion model: application to chlorophyll <i>a</i> concentration in the Black SeaA. Barth0J. Brajard1A. Alvera-Azcárate2B. Mohamed3C. Troupin4J.-M. Beckers5GeoHydrodynamics and Environment Research (GHER), FOCUS, University of Liège, Liège, BelgiumNansen Environmental and Remote Sensing Center and Bjerknes Centre for Climate Research, Bergen 5007, NorwayGeoHydrodynamics and Environment Research (GHER), FOCUS, University of Liège, Liège, BelgiumGeoHydrodynamics and Environment Research (GHER), FOCUS, University of Liège, Liège, BelgiumGeoHydrodynamics and Environment Research (GHER), FOCUS, University of Liège, Liège, BelgiumGeoHydrodynamics and Environment Research (GHER), FOCUS, University of Liège, Liège, Belgium<p>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 <span class="inline-formula"><i>a</i></span> concentration from the Ocean and Land Colour Instrument (OLCI) sensor (aboard 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 reconstructed ensemble are quantified using the continuous ranked probability score and its decomposition into reliability, resolution, and uncertainty.</p>https://os.copernicus.org/articles/20/1567/2024/os-20-1567-2024.pdf |
| spellingShingle | A. Barth J. Brajard A. Alvera-Azcárate B. Mohamed C. Troupin J.-M. Beckers Ensemble reconstruction of missing satellite data using a denoising diffusion model: application to chlorophyll <i>a</i> concentration in the Black Sea Ocean Science |
| title | Ensemble reconstruction of missing satellite data using a denoising diffusion model: application to chlorophyll <i>a</i> concentration in the Black Sea |
| title_full | Ensemble reconstruction of missing satellite data using a denoising diffusion model: application to chlorophyll <i>a</i> concentration in the Black Sea |
| title_fullStr | Ensemble reconstruction of missing satellite data using a denoising diffusion model: application to chlorophyll <i>a</i> concentration in the Black Sea |
| title_full_unstemmed | Ensemble reconstruction of missing satellite data using a denoising diffusion model: application to chlorophyll <i>a</i> concentration in the Black Sea |
| title_short | Ensemble reconstruction of missing satellite data using a denoising diffusion model: application to chlorophyll <i>a</i> concentration in the Black Sea |
| title_sort | ensemble reconstruction of missing satellite data using a denoising diffusion model application to chlorophyll i a i concentration in the black sea |
| url | https://os.copernicus.org/articles/20/1567/2024/os-20-1567-2024.pdf |
| work_keys_str_mv | AT abarth ensemblereconstructionofmissingsatellitedatausingadenoisingdiffusionmodelapplicationtochlorophylliaiconcentrationintheblacksea AT jbrajard ensemblereconstructionofmissingsatellitedatausingadenoisingdiffusionmodelapplicationtochlorophylliaiconcentrationintheblacksea AT aalveraazcarate ensemblereconstructionofmissingsatellitedatausingadenoisingdiffusionmodelapplicationtochlorophylliaiconcentrationintheblacksea AT bmohamed ensemblereconstructionofmissingsatellitedatausingadenoisingdiffusionmodelapplicationtochlorophylliaiconcentrationintheblacksea AT ctroupin ensemblereconstructionofmissingsatellitedatausingadenoisingdiffusionmodelapplicationtochlorophylliaiconcentrationintheblacksea AT jmbeckers ensemblereconstructionofmissingsatellitedatausingadenoisingdiffusionmodelapplicationtochlorophylliaiconcentrationintheblacksea |