IceCloudNet: 3D reconstruction of cloud ice from Meteosat SEVIRI

TL;DR

IceCloudNet is a machine learning method that reconstructs high-resolution 3D cloud ice profiles from geostationary satellite data, significantly expanding the available vertical cloud microphysical information.

Contribution

It introduces a novel ConvNeXt-based U-Net and 3D PatchGAN discriminator model trained to predict detailed cloud ice properties from satellite imagery, extending the temporal coverage beyond existing datasets.

Findings

High-precision predictions of cloud occurrence and microphysics.

Produced a ten-year dataset of 3 km resolution cloud ice profiles.

Extended vertical cloud profile data beyond current satellite missions.

Abstract

IceCloudNet is a novel method based on machine learning able to predict high-quality vertically resolved cloud ice water contents (IWC) and ice crystal number concentrations (N$_\textrm{ice}$). The predictions come at the spatio-temporal coverage and resolution of geostationary satellite observations (SEVIRI) and the vertical resolution of active satellite retrievals (DARDAR). IceCloudNet consists of a ConvNeXt-based U-Net and a 3D PatchGAN discriminator model and is trained by predicting DARDAR profiles from co-located SEVIRI images. Despite the sparse availability of DARDAR data due to its narrow overpass, IceCloudNet is able to predict cloud occurrence, spatial structure, and microphysical properties with high precision. The model has been applied to ten years of SEVIRI data, producing a dataset of vertically resolved IWC and N$_\textrm{ice}$ of clouds containing ice with a 3 kmx3 kmx240 mx15 minute resolution in a spatial domain of 30{\deg}W to 30{\deg}E and 30{\deg}S to 30{\deg}N. The produced dataset increases the availability of vertical cloud profiles, for the period when DARDAR is available, by more than six orders of magnitude and moreover, IceCloudNet is able to produce vertical cloud profiles beyond the lifetime of the recently ended satellite missions underlying DARDAR.