Fusion of Rain Radar Images and Wind Forecasts in a Deep Learning Model Applied to Rain Nowcasting
Short- or mid-term rainfall forecasting is a major task with several environmental applications such as agricultural management or flood risk monitoring. Existing data-driven approaches, especially deep learning models, have shown significant skill at this task, using only rainfall radar images as i...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/2/246 |
id |
doaj-ba6d38a0f3d04de58c91531766702d86 |
---|---|
record_format |
Article |
spelling |
doaj-ba6d38a0f3d04de58c91531766702d862021-01-14T00:00:59ZengMDPI AGRemote Sensing2072-42922021-01-011324624610.3390/rs13020246Fusion of Rain Radar Images and Wind Forecasts in a Deep Learning Model Applied to Rain NowcastingVincent Bouget0Dominique Béréziat1Julien Brajard2Anastase Charantonis3Arthur Filoche4Sorbonne Université, CNRS, Laboratoire d’Informatique de Paris 6, 75005 Paris, FranceSorbonne Université, CNRS, Laboratoire d’Informatique de Paris 6, 75005 Paris, FranceNansen Environmental and Remote Sensing Center (NERSC), 5009 Bergen, NorwayLaboratoire d’Océanographie et du Climat (LOCEAN), 75005 Paris, FranceSorbonne Université, CNRS, Laboratoire d’Informatique de Paris 6, 75005 Paris, FranceShort- or mid-term rainfall forecasting is a major task with several environmental applications such as agricultural management or flood risk monitoring. Existing data-driven approaches, especially deep learning models, have shown significant skill at this task, using only rainfall radar images as inputs. In order to determine whether using other meteorological parameters such as wind would improve forecasts, we trained a deep learning model on a fusion of rainfall radar images and wind velocity produced by a weather forecast model. The network was compared to a similar architecture trained only on radar data, to a basic persistence model and to an approach based on optical flow. Our network outperforms by 8% the <i>F1</i>-score calculated for the optical flow on moderate and higher rain events for forecasts at a horizon time of 30 min. Furthermore, it outperforms by 7% the same architecture trained using only rainfall radar images. Merging rain and wind data has also proven to stabilize the training process and enabled significant improvement especially on the difficult-to-predict high precipitation rainfalls.https://www.mdpi.com/2072-4292/13/2/246radar datarain nowcastingdeep learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Vincent Bouget Dominique Béréziat Julien Brajard Anastase Charantonis Arthur Filoche |
spellingShingle |
Vincent Bouget Dominique Béréziat Julien Brajard Anastase Charantonis Arthur Filoche Fusion of Rain Radar Images and Wind Forecasts in a Deep Learning Model Applied to Rain Nowcasting Remote Sensing radar data rain nowcasting deep learning |
author_facet |
Vincent Bouget Dominique Béréziat Julien Brajard Anastase Charantonis Arthur Filoche |
author_sort |
Vincent Bouget |
title |
Fusion of Rain Radar Images and Wind Forecasts in a Deep Learning Model Applied to Rain Nowcasting |
title_short |
Fusion of Rain Radar Images and Wind Forecasts in a Deep Learning Model Applied to Rain Nowcasting |
title_full |
Fusion of Rain Radar Images and Wind Forecasts in a Deep Learning Model Applied to Rain Nowcasting |
title_fullStr |
Fusion of Rain Radar Images and Wind Forecasts in a Deep Learning Model Applied to Rain Nowcasting |
title_full_unstemmed |
Fusion of Rain Radar Images and Wind Forecasts in a Deep Learning Model Applied to Rain Nowcasting |
title_sort |
fusion of rain radar images and wind forecasts in a deep learning model applied to rain nowcasting |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2021-01-01 |
description |
Short- or mid-term rainfall forecasting is a major task with several environmental applications such as agricultural management or flood risk monitoring. Existing data-driven approaches, especially deep learning models, have shown significant skill at this task, using only rainfall radar images as inputs. In order to determine whether using other meteorological parameters such as wind would improve forecasts, we trained a deep learning model on a fusion of rainfall radar images and wind velocity produced by a weather forecast model. The network was compared to a similar architecture trained only on radar data, to a basic persistence model and to an approach based on optical flow. Our network outperforms by 8% the <i>F1</i>-score calculated for the optical flow on moderate and higher rain events for forecasts at a horizon time of 30 min. Furthermore, it outperforms by 7% the same architecture trained using only rainfall radar images. Merging rain and wind data has also proven to stabilize the training process and enabled significant improvement especially on the difficult-to-predict high precipitation rainfalls. |
topic |
radar data rain nowcasting deep learning |
url |
https://www.mdpi.com/2072-4292/13/2/246 |
work_keys_str_mv |
AT vincentbouget fusionofrainradarimagesandwindforecastsinadeeplearningmodelappliedtorainnowcasting AT dominiquebereziat fusionofrainradarimagesandwindforecastsinadeeplearningmodelappliedtorainnowcasting AT julienbrajard fusionofrainradarimagesandwindforecastsinadeeplearningmodelappliedtorainnowcasting AT anastasecharantonis fusionofrainradarimagesandwindforecastsinadeeplearningmodelappliedtorainnowcasting AT arthurfiloche fusionofrainradarimagesandwindforecastsinadeeplearningmodelappliedtorainnowcasting |
_version_ |
1724338845784211456 |