open access publication

Article, 2024

U-Net Segmentation for the Detection of Convective Cold Pools From Cloud and Rainfall Fields

JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES, ISSN 2169-897X, 2169-897X, Volume 129, 1, 10.1029/2023JD040126

Contributors

Hoeller, Jannik 0000-0001-7406-3205 (Corresponding author) [1] [2] [3] Fievet, Romain [1] [2] Engelbrecht, Edward [3] [4] Haerter, Jan O 0000-0002-8617-3847 [1] [2] [3] [4] [5]

Affiliations

  1. [1] Univ Copenhagen, Niels Bohr Inst, Copenhagen, Denmark
    2. [NORA names: KU University of Copenhagen; University; Denmark; Europe, EU; Nordic; OECD];
  2. [2] Univ Copenhagen, Niels Bohr Inst, Copenhagen, Denmark
    3. [NORA names: KU University of Copenhagen; University; Denmark; Europe, EU; Nordic; OECD];
  3. [3] Leibniz Ctr Trop Marine Res, Integrated Modeling, Bremen, Germany
    4. [NORA names: Germany; Europe, EU; OECD];
  4. [4] Constructor Univ Bremen, Phys & Earth Sci, Bremen, Germany
    5. [NORA names: Germany; Europe, EU; OECD];
  5. [5] Univ Potsdam, Dept Phys & Astron, Potsdam, Germany
    6. [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

Data Provider: Clarivate

LINKS
-

Matching Records in NORA

SUBJECTS
+

METRICS
+