A Cloud Detection Neural Network Approach for the Next Generation Microwave Sounder Aboard EPS MetOp-SG A1

This work presents an algorithm based on a neural network (NN) for cloud detection to detect clouds and their thermodynamic phase using spectral observations from spaceborne microwave radiometers. A standalone over the ocean land has been developed distinguish clear sky versus ice liquid sounder (MWS) observations. The MWS instrument—scheduled be onboard first satellite of Eumetsat Polar System Second-Generation (EPS-SG) series, MetOp-SG A1—has direct inheritance advanced sounding unit (AMSU-A) humidity (MHS) instruments. Real sensor are not currently available as its launch is foreseen in 2024. Thus, simulated dataset atmospheric states associated synthetic have produced through radiative transfer calculations with ERA5 real profiles surface conditions. validated AMSU-A MHS sounders. While serve references model development validation, AVHRR mask products provide AMSU-A/MHS evaluation. results clearly show NN algorithm’s high skills clear, conditions against benchmark. In terms overall accuracy, features 92% (88%) 87% (85%) land, (AMSU-A/MHS)-simulated dataset, respectively.