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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU145918" target="_blank" >RIV/00216305:26230/22:PU145918 - isvavai.cz</a>

Výsledek na webu

<a href="http://ceur-ws.org/Vol-3207/paper10.pdf" target="_blank" >http://ceur-ws.org/Vol-3207/paper10.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the Second Workshop on Complex Data Challenges in Earth Observation (CDCEO 2022)

ISBN

—

ISSN

1613-0073

e-ISSN

—

Počet stran výsledku

7

Strana od-do

65-72

Název nakladatele

CEUR-WS.org

Místo vydání

Vienna

Místo konání akce

Vienna

Datum konání akce

23. 7. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—