Article,
U-Net Segmentation for the Detection of Convective Cold Pools From Cloud and Rainfall Fields
Affiliations
- [1] Univ Copenhagen, Niels Bohr Inst, Copenhagen, Denmark [NORA names: KU University of Copenhagen; University; Denmark; Europe, EU; Nordic; OECD];
- [2] Univ Copenhagen, Niels Bohr Inst, Copenhagen, Denmark [NORA names: KU University of Copenhagen; University; Denmark; Europe, EU; Nordic; OECD];
- [3] Leibniz Ctr Trop Marine Res, Integrated Modeling, Bremen, Germany [NORA names: Germany; Europe, EU; OECD];
- [4] Constructor Univ Bremen, Phys & Earth Sci, Bremen, Germany [NORA names: Germany; Europe, EU; OECD];
- [5] Univ Potsdam, Dept Phys & Astron, Potsdam, Germany [NORA names: Germany; Europe, EU; OECD]
Abstract
A neural network is trained to detect cold pools from cloud top temperature and precipitationThe method works reliably and a pseudo-3D approach, which includes dynamic cold pool evolution, performs bestThe method offers new perspectives for the cold pool detection from geostationary satellite observations over tropical land
Keywords
U-Net,
cloud and rainfall fields,
cold pool detection,
convective organization,
neural network,
segmentation