Project: IceCloudNet: 3D reconstruction of tropical cloud ice from Meteosat SEVIRI - IceCloudNet (https://arxiv.org/abs/2410.04135) is a deep learning model that maps between geostationary data and vertically resolved DARDAR and DARDAR-Nice data. IceCloudNet is able to adequately reconstruct the vertical cloud structure and predict ice water content and ice crystal number concentration of clouds containing ice with high precision. The data set produced by IceCloudNet combines the spatio-temporal coverage and resolution of Meteosat SEVIRI with the vertical resolution of DARDAR-Nice, increasing the availability of vertically resolved cirrus and mixed-phase cloud profiles by over six orders of magnitude compared to the DARDAR-Nice data set. IceCloudNet data enables many possiblities for new research on cloud formation and development. For instance, by tracking any long-lasting cloud system such as mesoscale convective systems and tropical cyclones in all spatial and temporal dimensions. Additionally, IceCloudNet data can be utilized as an observational constraint for the validation of high-resolution climate models. This research was supported by grants from the European Union’s Horizon 2020 research and innovation program iMIRACLI under Marie Skłodowska-Curie grant agreement No 860100. Summary: IceCloudNet is a novel method based on machine learning able to obtain high- quality vertically resolved predictions for ice water content and ice crystal number concentration of clouds containing ice. The predictions come at the spatio-temporal coverage and resolution of Meteosat SEVIRI and the vertical resolution of 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, macrophysical shape, and microphysical properties with high precision. We release 10 years of vertically resolved ice water content (IWC) and ice crystal number concentration (Nice) of clouds containing ice with a 3 km×3 km×240 m×15 minute resolution on a spatial domain of 30°W to 30°E and 30°S to 30°N. The resulting data set increases the availability of vertical cloud profiles for the period when DARDAR is available by more than six orders of magnitude and moreover, is able to provide vertical cloud profiles beyond the lifetime of the recently ended satellite missions underlying DARDAR.
