Articles | Volume 15, issue 2
Atmos. Meas. Tech., 15, 365–381, 2022
https://doi.org/10.5194/amt-15-365-2022

Special issue: Fusion of radar polarimetry and numerical atmospheric modelling...

Atmos. Meas. Tech., 15, 365–381, 2022
https://doi.org/10.5194/amt-15-365-2022

Research article 24 Jan 2022

Research article | 24 Jan 2022

Using artificial neural networks to predict riming from Doppler cloud radar observations

Teresa Vogl et al.

Data sets

rime fraction training data set extracted from BAECC Teresa Vogl https://doi.org/10.5281/zenodo.5751820

Ka ARM Zenith Radar (KAZRSPECCMASKMDCOPOL) Atmospheric Radiation Measurement (ARM) user facility https://doi.org/10.5439/1095603

: Microwave Radiometer (MWRLOS) Atmospheric Radiation Measurement (ARM) user facility https://doi.org/10.5439/1046211

Balloon-Borne Sounding System (SONDEWNPN) Atmospheric Radiation Measurement (ARM) user facility https://doi.org/10.5439/1021460

Snow microphysical properties retrieved from PIP observations collected in Hyytiala on 2014-2015 D. Moisseev https://github.com/dmoisseev/Snow-Retrievals-2014-2015

Video supplement

3D animation of a training data set to predict rime mass fraction Teresa Vogl https://doi.org/10.5446/52957

Download
Short summary
We are using machine learning techniques, a type of artificial intelligence, to detect graupel formation in clouds. The measurements used as input to the machine learning framework were performed by cloud radars. Cloud radars are instruments located at the ground, emitting radiation with wavelenghts of a few millimeters vertically into the cloud and measuring the back-scattered signal. Our novel technique can be applied to different radar systems and different weather conditions.