_version_ 1852021181115269120
author Songsong Wang (8088293)
author2 Ouguan XU (21156224)
author2_role author
author_facet Songsong Wang (8088293)
Ouguan XU (21156224)
author_role author
dc.creator.none.fl_str_mv Songsong Wang (8088293)
Ouguan XU (21156224)
dc.date.none.fl_str_mv 2025-04-21T17:44:06Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0321583.g009
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Phases_of_RNN_models_train_validation_and_prediction_/28833383
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Medicine
Neuroscience
Biotechnology
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
gated recurrent unit
extreme water level
water level forecasting
traditional probability forecasting
forecasting hourly streamflow
achieved reasonable balance
compound rnn could
bayesian </ p
reasonable reliability
zhejiang province
weight training
time windows
term memory
small watersheds
small watershed
qixi reservoir
often unbalanced
long short
including hydrology
good alternative
comparative analysis
best method
bayesian structure
base rnn
5 days
31 %,
15 %,
dc.title.none.fl_str_mv Phases of RNN models’ train, validation and prediction.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p>Phases of RNN models’ train, validation and prediction.</p>
eu_rights_str_mv openAccess
id Manara_20faeb8fb32b8831eb5b8a2c1e95bdac
identifier_str_mv 10.1371/journal.pone.0321583.g009
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/28833383
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Phases of RNN models’ train, validation and prediction.Songsong Wang (8088293)Ouguan XU (21156224)MedicineNeuroscienceBiotechnologyEnvironmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedgated recurrent unitextreme water levelwater level forecastingtraditional probability forecastingforecasting hourly streamflowachieved reasonable balancecompound rnn couldbayesian </ preasonable reliabilityzhejiang provinceweight trainingtime windowsterm memorysmall watershedssmall watershedqixi reservoiroften unbalancedlong shortincluding hydrologygood alternativecomparative analysisbest methodbayesian structurebase rnn5 days31 %,15 %,<p>Phases of RNN models’ train, validation and prediction.</p>2025-04-21T17:44:06ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0321583.g009https://figshare.com/articles/figure/Phases_of_RNN_models_train_validation_and_prediction_/28833383CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/288333832025-04-21T17:44:06Z
spellingShingle Phases of RNN models’ train, validation and prediction.
Songsong Wang (8088293)
Medicine
Neuroscience
Biotechnology
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
gated recurrent unit
extreme water level
water level forecasting
traditional probability forecasting
forecasting hourly streamflow
achieved reasonable balance
compound rnn could
bayesian </ p
reasonable reliability
zhejiang province
weight training
time windows
term memory
small watersheds
small watershed
qixi reservoir
often unbalanced
long short
including hydrology
good alternative
comparative analysis
best method
bayesian structure
base rnn
5 days
31 %,
15 %,
status_str publishedVersion
title Phases of RNN models’ train, validation and prediction.
title_full Phases of RNN models’ train, validation and prediction.
title_fullStr Phases of RNN models’ train, validation and prediction.
title_full_unstemmed Phases of RNN models’ train, validation and prediction.
title_short Phases of RNN models’ train, validation and prediction.
title_sort Phases of RNN models’ train, validation and prediction.
topic Medicine
Neuroscience
Biotechnology
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
gated recurrent unit
extreme water level
water level forecasting
traditional probability forecasting
forecasting hourly streamflow
achieved reasonable balance
compound rnn could
bayesian </ p
reasonable reliability
zhejiang province
weight training
time windows
term memory
small watersheds
small watershed
qixi reservoir
often unbalanced
long short
including hydrology
good alternative
comparative analysis
best method
bayesian structure
base rnn
5 days
31 %,
15 %,