Deep Temporal Interpolation of Radar-Based Precipitation

When providing the boundary conditions for hydrological flood models and estimating the associated risk, interpolating precipitation at very high temporal resolutions (e.g. 5 minutes) is essential not to miss the cause of flooding in local regions. In this paper, we study optical flow-based interpol...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 1685 - 1689
Main Authors Tatsubori, Michiaki, Moriyama, Takao, Ishikawa, Tatsuya, Fraccaro, Paolo, Jones, Anne, Edwards, Blair, Kuehnert, Julian, Remy, Sekou L.
Format Conference Proceeding
LanguageEnglish
Published IEEE 23.05.2022
Subjects
Climate & sustainability
Floods
Interpolation
Laser radar
physics-informed neural networks
Radar imaging
satellite remote sensing
Satellites
spatio-temporal interpolation
Speech processing
Training
Online AccessGet full text

Cover

More Information
Summary:When providing the boundary conditions for hydrological flood models and estimating the associated risk, interpolating precipitation at very high temporal resolutions (e.g. 5 minutes) is essential not to miss the cause of flooding in local regions. In this paper, we study optical flow-based interpolation of globally available weather radar images from satellites. The proposed approach uses deep neural networks for the interpolation of multiple video frames, while terrain information is combined with temporarily coarse-grained precipitation radar observation as inputs for self-supervised training. An experiment with the Meteonet radar precipitation dataset for the flood risk simulation in Aude, a department in Southern France (2018), demonstrated the advantage of the proposed method over a linear interpolation baseline, with up to 20% error reduction.
ISSN:2379-190X
DOI:10.1109/ICASSP43922.2022.9747829