Publication detail

Radar-Based Volumetric Precipitation Nowcasting: A 3D Convolutional Neural Network with U-Net Architecture

PAVLÍK, P. ROZINAJOVÁ, V. BOU EZZEDDINE, A.

Original Title

Radar-Based Volumetric Precipitation Nowcasting: A 3D Convolutional Neural Network with U-Net Architecture

Type

conference paper

Language

English

Original Abstract

In recent years like in many other domains deep learning models have found their place in the domain of precipitation nowcasting. Many of these models are based on the U-Net architecture, which was originally developed for biomedical segmentation, but is also useful for the generation of short-term forecasts and therefore applicable in the weather nowcasting domain. The existing U-Net-based models use sequential radar data mapped into a 2-dimensional Cartesian grid as input and output. We propose to incorporate a third - vertical - dimension to better predict precipitation phenomena such as convective rainfall and present our results here. We compare the nowcasting performance of two comparable U-Net models trained on two-dimensional and three-dimensional radar observation data. We show that using volumetric data results in a small, but significant reduction in prediction error.

Keywords

precipitation nowcasting, radar imaging, U-Net

Authors

PAVLÍK, P.; ROZINAJOVÁ, V.; BOU EZZEDDINE, A.

Released

25. 7. 2022

Publisher

CEUR-WS.org

Location

Vienna

ISBN

1613-0073

Periodical

CEUR Workshop Proceedings

Year of study

3207

Number

2022

State

Federal Republic of Germany

Pages from

65

Pages to

72

Pages count

7

URL

http://ceur-ws.org/Vol-3207/paper10.pdf

BibTex

@inproceedings{BUT179604,
  author="Peter {Pavlík} and Věra {Rozinajová} and Anna {Bou Ezzeddine}",
  title="Radar-Based Volumetric Precipitation Nowcasting: A 3D Convolutional Neural Network with U-Net Architecture",
  booktitle="Proceedings of the Second Workshop on Complex Data Challenges in Earth Observation (CDCEO 2022)",
  year="2022",
  journal="CEUR Workshop Proceedings",
  volume="3207",
  number="2022",
  pages="65--72",
  publisher="CEUR-WS.org",
  address="Vienna",
  issn="1613-0073",
  url="http://ceur-ws.org/Vol-3207/paper10.pdf"
}