Publication Details

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

PAVLÍK Peter, ROZINAJOVÁ Viera and BOU Ezzeddine Anna. Radar-Based Volumetric Precipitation Nowcasting: A 3D Convolutional Neural Network with U-Net Architecture. In: Proceedings of the Second Workshop on Complex Data Challenges in Earth Observation (CDCEO 2022). Vienna: CEUR-WS.org, 2022, pp. 65-72. ISSN 1613-0073. Available from: http://ceur-ws.org/Vol-3207/paper10.pdf
Czech title
Volumetrické srážky založené na radaru Nowcasting: 3D konvoluční neuronová síť s architekturou UNet
Type
conference paper
Language
english
Authors
Pavlík Peter, Ing. (FIT BUT)
Rozinajová Viera, doc. Ing., Ph.D. (KInIT)
Bou Ezzeddine Anna, doc. RNDr., Ph.D. (KInIT)
URL
Keywords

precipitation nowcasting, radar imaging, U-Net

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.

Published
2022
Pages
65-72
Journal
CEUR Workshop Proceedings, vol. 3207, no. 2022, ISSN 1613-0073
Proceedings
Proceedings of the Second Workshop on Complex Data Challenges in Earth Observation (CDCEO 2022)
Conference
Workshop on Complex Data Challenges in Earth Observation 2022, Vienna, AT
Publisher
CEUR-WS.org
Place
Vienna, AT
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB12755,
   author = "Peter Pavl\'{i}k and Viera Rozinajov\'{a} and Anna Ezzeddine Bou",
   title = "Radar-Based Volumetric Precipitation Nowcasting: A 3D Convolutional Neural Network with U-Net Architecture",
   pages = "65--72",
   booktitle = "Proceedings of the Second Workshop on Complex Data Challenges in Earth Observation (CDCEO 2022)",
   journal = "CEUR Workshop Proceedings",
   volume = 3207,
   number = 2022,
   year = 2022,
   location = "Vienna, AT",
   publisher = "CEUR-WS.org",
   ISSN = "1613-0073",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12755"
}
Back to top