RAIN-F+: The Data-Driven Precipitation Prediction Model for Integrated Weather Observations

Quantitative precipitation prediction is essential for managing water-related disasters, including floods, landslides, tsunamis, and droughts. Recent advances in data-driven approaches using deep learning techniques provide improved precipitation nowcasting performance. Moreover, it has been known t...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Switzerland), 2021-09, Vol.13 (18), p.3627
Main Authors: Choi, Yeji, Cha, Keumgang, Back, Minyoung, Choi, Hyunguk, Jeon, Taegyun
Format: Article
Language:English
Subjects:
Benchmarks
Clouds
Datasets
Deep learning
deep learning approach
Disaster management
Drought
Earth science
Flood management
Flood predictions
Humidity
Land area
Landslides
Meteorological satellites
Neural networks
Nowcasting
Precipitation
precipitation prediction
Prediction models
Radar
Radar systems
Rain
Rainfall
Remote sensing
Satellite observation
Sea level
Skills
Water management
Weather forecasting
weather observations
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Quantitative precipitation prediction is essential for managing water-related disasters, including floods, landslides, tsunamis, and droughts. Recent advances in data-driven approaches using deep learning techniques provide improved precipitation nowcasting performance. Moreover, it has been known that multi-modal information from various sources could improve deep learning performance. This study introduces the RAIN-F+ dataset, which is the fusion dataset for rainfall prediction, and proposes the benchmark models for precipitation prediction using the RAIN-F+ dataset. The RAIN-F+ dataset is an integrated weather observation dataset including radar, surface station, and satellite observations covering the land area over the Korean Peninsula. The benchmark model is developed based on the U-Net architecture with residual upsampling and downsampling blocks. We examine the results depending on the number of the integrated dataset for training. Overall, the results show that the fusion dataset outperforms the radar-only dataset over time. Moreover, the results with the radar-only dataset show the limitations in predicting heavy rainfall over 10 mm/h. This suggests that the various information from multi-modality is crucial for precipitation nowcasting when applying the deep learning method.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs13183627