Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Deep Rainrate Estimation from Highly Attenuated Downlink Signals of Ground-Based Communications Satellite Terminals
Mishra, K. V.; R., B. S. M.; Ottersten, Björn
2020In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Deep Rainrate Estimation from Highly Attenuated Downlink Signals of Ground-Based Communications Satellite Terminals
Peer reviewed
 

Files


Full Text
09054729_4_deep rainrate.pdf
Publisher postprint (939.03 kB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
atmospheric techniques;convolutional neural nets;meteorological radar;rain;deep rainrate estimation;highly attenuated downlink signals;ground-based communications satellite terminals;densely located ground-based terminals;interactive satellite services;weather sensors;rain-attenuated power;downlink signal;millimeter-wave regime;linear relationship;specific attenuation;weather radar observables;rainfall rate;highly attenuated signals;deep convolutional neural network;signal attenuation;rain gauges;downlink attenuation;rain intensity;appropriate rainfall estimator;severe attenuation;CNN-based downlink rainfall accumulations;nearest C-band German weather service Deutscher Wetterdienst radar;Convolutional neural network;rainfall estimation;signal attenuation;satellite communication;weather radar
Abstract :
[en] While the use of weather radars to continuously monitor the spatiotemporal dynamics of precipitation has grown in recent years, these systems are expensive and sparsely deployed across the world. In this context, densely located ground-based terminals for interactive satellite services have the potential for dual-use as weather sensors because they measure rain-attenuated power of the downlink signal. Although in the millimeter-wave regime, the rain rate has almost a linear relationship with specific attenuation, lack of other weather radar observables at satellite terminals imposes a daunting task of extracting rainfall rate from these highly attenuated signals. We address this problem by designing a deep convolutional neural network (CNN) that learns the relationship between the signal attenuation and rainfall rate observed by weather radars and rain gauges at a given location. During the prediction stage, the CNN accepts downlink attenuation as input and classifies the rain intensity which is then used to apply an appropriate rainfall estimator. Our experiments with real data show that, despite severe attenuation, CNN-based downlink rainfall accumulations closely follow the nearest C-band German weather service Deutscher Wetterdienst (DWD) radar.
Disciplines :
Computer science
Author, co-author :
Mishra, K. V.
R., B. S. M.
Ottersten, Björn ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
External co-authors :
yes
Language :
English
Title :
Deep Rainrate Estimation from Highly Attenuated Downlink Signals of Ground-Based Communications Satellite Terminals
Publication date :
14 May 2020
Event name :
Deep Rainrate Estimation from Highly Attenuated Downlink Signals of Ground-Based Communications Satellite Terminals
Event place :
Barcelona, Spain
Event date :
from 04-05-20 to 08-05-20
Main work title :
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Deep Rainrate Estimation from Highly Attenuated Downlink Signals of Ground-Based Communications Satellite Terminals
Pages :
9021-9025
Peer reviewed :
Peer reviewed
FnR Project :
FNR11648950 - Rainfall Estimation Using Signalling Data Of Satellite Communication Network, 2017 (01/07/2017-31/01/2019) - Bhavani Shankar Mysore Rama Rao
Commentary :
2379-190X
Available on ORBilu :
since 12 January 2021

Statistics


Number of views
94 (0 by Unilu)
Number of downloads
125 (2 by Unilu)

Scopus citations®
 
8
Scopus citations®
without self-citations
7

Bibliography


Similar publications



Contact ORBilu