Streamflow prediction in ungauged basins: benchmarking the efficiency of deep learning
Streamflow prediction is a vital public service that helps to establish flash-flood early warning systems or assess the impact of projected climate change on water management. However, the availability of streamflow observations limits the utilization of the state-of-the-art streamflow prediction te...
Published in: | E3S Web of Conferences |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English French |
Published: |
EDP Sciences
2020
|
Subjects: | |
Online Access: | https://doi.org/10.1051/e3sconf/202016301001 https://www.e3s-conferences.org/articles/e3sconf/pdf/2020/23/e3sconf_vc2020_01001.pdf https://doaj.org/article/a65b16135d1f4b36a851896dc39349a5 |
id |
fttriple:oai:gotriple.eu:oai:doaj.org/article:a65b16135d1f4b36a851896dc39349a5 |
---|---|
record_format |
openpolar |
spelling |
fttriple:oai:gotriple.eu:oai:doaj.org/article:a65b16135d1f4b36a851896dc39349a5 2023-05-15T17:46:05+02:00 Streamflow prediction in ungauged basins: benchmarking the efficiency of deep learning Ayzel Georgy Kurochkina Liubov Kazakov Eduard Zhuravlev Sergei 2020-01-01 https://doi.org/10.1051/e3sconf/202016301001 https://www.e3s-conferences.org/articles/e3sconf/pdf/2020/23/e3sconf_vc2020_01001.pdf https://doaj.org/article/a65b16135d1f4b36a851896dc39349a5 en fr eng fre EDP Sciences 2267-1242 doi:10.1051/e3sconf/202016301001 https://www.e3s-conferences.org/articles/e3sconf/pdf/2020/23/e3sconf_vc2020_01001.pdf https://doaj.org/article/a65b16135d1f4b36a851896dc39349a5 undefined E3S Web of Conferences, Vol 163, p 01001 (2020) envir geo Journal Article https://vocabularies.coar-repositories.org/resource_types/c_6501/ 2020 fttriple https://doi.org/10.1051/e3sconf/202016301001 2023-01-22T17:37:35Z Streamflow prediction is a vital public service that helps to establish flash-flood early warning systems or assess the impact of projected climate change on water management. However, the availability of streamflow observations limits the utilization of the state-of-the-art streamflow prediction techniques to the basins where hydrometric gauging stations exist. Since the most river basins in the world are ungauged, the development of the specialized techniques for the reliable streamflow prediction in ungauged basins (PUB) is of crucial importance. In recent years, the emerging field of deep learning provides a myriad of new models that can breathe new life into the stagnating PUB methods. In the presented study, we benchmark the streamflow prediction efficiency of Long Short-Term Memory (LSTM) networks against the standard technique of GR4J hydrological model parameters regionalization (HMREG) at 200 basins in Northwest Russia. Results show that the LSTM-based regional hydrological model significantly outperforms the HMREG scheme in terms of median Nash-Sutcliffe efficiency (NSE), which is 0.73 and 0.61 for LSTM and HMREG, respectively. Moreover, LSTM demonstrates the comparable median NSE with that for basin-scale calibration of GR4J (0.75). Therefore, this study underlines the high utilization potential of deep learning for the PUB by demonstrating the new state-of-the-art performance in this field. Article in Journal/Newspaper Northwest Russia Unknown Nash ENVELOPE(-62.350,-62.350,-74.233,-74.233) Sutcliffe ENVELOPE(-81.383,-81.383,50.683,50.683) E3S Web of Conferences 163 01001 |
institution |
Open Polar |
collection |
Unknown |
op_collection_id |
fttriple |
language |
English French |
topic |
envir geo |
spellingShingle |
envir geo Ayzel Georgy Kurochkina Liubov Kazakov Eduard Zhuravlev Sergei Streamflow prediction in ungauged basins: benchmarking the efficiency of deep learning |
topic_facet |
envir geo |
description |
Streamflow prediction is a vital public service that helps to establish flash-flood early warning systems or assess the impact of projected climate change on water management. However, the availability of streamflow observations limits the utilization of the state-of-the-art streamflow prediction techniques to the basins where hydrometric gauging stations exist. Since the most river basins in the world are ungauged, the development of the specialized techniques for the reliable streamflow prediction in ungauged basins (PUB) is of crucial importance. In recent years, the emerging field of deep learning provides a myriad of new models that can breathe new life into the stagnating PUB methods. In the presented study, we benchmark the streamflow prediction efficiency of Long Short-Term Memory (LSTM) networks against the standard technique of GR4J hydrological model parameters regionalization (HMREG) at 200 basins in Northwest Russia. Results show that the LSTM-based regional hydrological model significantly outperforms the HMREG scheme in terms of median Nash-Sutcliffe efficiency (NSE), which is 0.73 and 0.61 for LSTM and HMREG, respectively. Moreover, LSTM demonstrates the comparable median NSE with that for basin-scale calibration of GR4J (0.75). Therefore, this study underlines the high utilization potential of deep learning for the PUB by demonstrating the new state-of-the-art performance in this field. |
format |
Article in Journal/Newspaper |
author |
Ayzel Georgy Kurochkina Liubov Kazakov Eduard Zhuravlev Sergei |
author_facet |
Ayzel Georgy Kurochkina Liubov Kazakov Eduard Zhuravlev Sergei |
author_sort |
Ayzel Georgy |
title |
Streamflow prediction in ungauged basins: benchmarking the efficiency of deep learning |
title_short |
Streamflow prediction in ungauged basins: benchmarking the efficiency of deep learning |
title_full |
Streamflow prediction in ungauged basins: benchmarking the efficiency of deep learning |
title_fullStr |
Streamflow prediction in ungauged basins: benchmarking the efficiency of deep learning |
title_full_unstemmed |
Streamflow prediction in ungauged basins: benchmarking the efficiency of deep learning |
title_sort |
streamflow prediction in ungauged basins: benchmarking the efficiency of deep learning |
publisher |
EDP Sciences |
publishDate |
2020 |
url |
https://doi.org/10.1051/e3sconf/202016301001 https://www.e3s-conferences.org/articles/e3sconf/pdf/2020/23/e3sconf_vc2020_01001.pdf https://doaj.org/article/a65b16135d1f4b36a851896dc39349a5 |
long_lat |
ENVELOPE(-62.350,-62.350,-74.233,-74.233) ENVELOPE(-81.383,-81.383,50.683,50.683) |
geographic |
Nash Sutcliffe |
geographic_facet |
Nash Sutcliffe |
genre |
Northwest Russia |
genre_facet |
Northwest Russia |
op_source |
E3S Web of Conferences, Vol 163, p 01001 (2020) |
op_relation |
2267-1242 doi:10.1051/e3sconf/202016301001 https://www.e3s-conferences.org/articles/e3sconf/pdf/2020/23/e3sconf_vc2020_01001.pdf https://doaj.org/article/a65b16135d1f4b36a851896dc39349a5 |
op_rights |
undefined |
op_doi |
https://doi.org/10.1051/e3sconf/202016301001 |
container_title |
E3S Web of Conferences |
container_volume |
163 |
container_start_page |
01001 |
_version_ |
1766149443275456512 |