Publication Date:
2024-05-22
Description:
〈title xmlns:mml="http://www.w3.org/1998/Math/MathML"〉Abstract〈/title〉〈p xmlns:mml="http://www.w3.org/1998/Math/MathML" xml:lang="en"〉Mineral dust is one of the most abundant atmospheric aerosol species and has various far‐reaching effects on the climate system and adverse impacts on air quality. Satellite observations can provide spatio‐temporal information on dust emission and transport pathways. However, satellite observations of dust plumes are frequently obscured by clouds. We use a method based on established, machine‐learning‐based image in‐painting techniques to restore the spatial extent of dust plumes for the first time. We train an artificial neural net (ANN) on modern reanalysis data paired with satellite‐derived cloud masks. The trained ANN is applied to cloud‐masked, gray‐scaled images, which were derived from false color images indicating elevated dust plumes in bright magenta. The images were obtained from the Spinning Enhanced Visible and Infrared Imager instrument onboard the Meteosat Second Generation satellite. We find up to 15% of summertime observations in West Africa and 10% of summertime observations in Nubia by satellite images miss dust plumes due to cloud cover. We use the new dust‐plume data to demonstrate a novel approach for validating spatial patterns of the operational forecasts provided by the World Meteorological Organization Dust Regional Center in Barcelona. The comparison elucidates often similar dust plume patterns in the forecasts and the satellite‐based reconstruction, but once trained, the reconstruction is computationally inexpensive. Our proposed reconstruction provides a new opportunity for validating dust aerosol transport in numerical weather models and Earth system models. It can be adapted to other aerosol species and trace gases.〈/p〉
Description:
Plain Language Summary: Most dust and sand particles in the atmosphere originate from North Africa. Since ground‐based observations of dust plumes in North Africa are sparse, investigations often rely on satellite observations. Dust plumes are frequently obscured by clouds, making it difficult to study the full extent. We use machine‐learning methods to restore information about the extent of dust plumes beneath clouds in 2021 and 2022 at 9, 12, and 15 UTC. We use the reconstructed dust patterns to demonstrate a new way to validate the dust forecast ensemble provided by the World Meteorological Organization Dust Regional Center in Barcelona, Spain. Our proposed method is computationally inexpensive and provides new opportunities for assessing the quality of dust transport simulations. The method can be transferred to reconstruct other aerosol and trace gas plumes.〈/p〉
Description:
Key Points:
〈list list-type="bullet"〉
〈list-item〉
〈p xml:lang="en"〉We present the first fast reconstruction of cloud‐obscured Saharan dust plumes through novel machine learning applied to satellite images〈/p〉〈/list-item〉
〈list-item〉
〈p xml:lang="en"〉The reconstruction algorithm utilizes partial convolutions to restore cloud‐induced gaps in gray‐scaled Meteosat Second Generation‐Spinning Enhanced Visible and Infrared Imager Dust RGB images〈/p〉〈/list-item〉
〈list-item〉
〈p xml:lang="en"〉World Meteorological Organization dust forecasts for North Africa mostly agree with the satellite‐based reconstruction of the dust plume extent〈/p〉〈/list-item〉
〈/list〉
〈/p〉
Description:
GEOMAR Helmholtz Centre for Ocean Research Kiel
Description:
University of Cologne
Description:
https://doi.org/10.5281/zenodo.6475858
Description:
https://github.com/tobihose/Masterarbeit
Description:
https://dust.aemet.es/
Description:
https://ads.atmosphere.copernicus.eu/cdsapp#!/dataset/cams-global-reanalysis-eac4?tab=overview
Description:
https://navigator.eumetsat.int/product/EO:EUM:DAT:MSG:DUST
Description:
https://navigator.eumetsat.int/product/EO:EUM:DAT:MSG:CLM
Description:
https://doi.org/10.5067/KLICLTZ8EM9D
Description:
https://disc.gsfc.nasa.gov/datasets?project=MERRA-2
Description:
https://doi.org/10.5067/MODIS/MOD08_D3.061
Description:
https://doi.org/10.5067/MODIS/MYD08_D3.061
Description:
https://doi.org/10.5281/ZENODO.8278518
Keywords:
ddc:551.5
;
mineral dust
;
North Africa
;
MSG SEVIRI
;
machine learning
;
cloud removal
;
satellite remote sensing
Language:
English
Type:
doc-type:article
Permalink
