A quantile-based encoder-decoder framework for multi-step ahead runoff forecasting

•Quantile-based encoder-decoder models proposed for probabilistic runoff forecasting.•Proposed models more accurate and reliable than benchmarks for 3 test catchments.•Wavelet selection can be used to improve forecast accuracy and reliability.•Model performance sensitive to precipitation forecast ac...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of hydrology (Amsterdam) Ročník 619; s. 129269
Hlavní autoři: Jahangir, Mohammad Sina, You, John, Quilty, John
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.04.2023
Témata:
ISSN:0022-1694, 1879-2707
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract •Quantile-based encoder-decoder models proposed for probabilistic runoff forecasting.•Proposed models more accurate and reliable than benchmarks for 3 test catchments.•Wavelet selection can be used to improve forecast accuracy and reliability.•Model performance sensitive to precipitation forecast accuracy. Deep neural network (DNN) models have become increasingly popular in the hydrology community. However, most studies are related to (rainfall-) runoff simulation and comparatively fewer studies have focused on runoff forecasting. In this study, quantile-based (q = 0.05, 0.5, 0.95) encoder-decoder (ED) models that use long short-term memory network (LSTM) and dense network (DN) blocks were developed for three and five days ahead runoff forecasting. Through linear (LW) and non-linear (NLW) wavelet selection, hybrid models LSTM-DN, LSTM-DN-LW, LSTM-DN-NLW, ED, ED-LW, and ED-NLW were developed. For each lead time (LT = 3, 5) and value of q, different model configurations were created using different input lag lengths (IL = 15, 45, 180). The developed models were tested for runoff forecasting using three basins (with different characteristics) from the Catchment Attributes and MEteorology for Large-sample Studies (CAMELS) dataset. The models were compared using deterministic (e.g., the Kling-Gupta efficiency [KGE] metric) and probabilistic (e.g., reliability) statistical metrics. While the models showed high variability in performance across the three basins (KGE = 0.308–0.979 for the q = 0.5 models), very high accuracy (up to KGE = 0.979) was achieved for one of the basins with high snowmelt. The ED-NLW model was found to generally outperform the other models. Although the LSTM-DN model had the highest median KGE (0.434 across all configurations), the ED and ED-NLW models had higher reliability than LSTM-DN (90% and 91%, respectively, considering a 90% confidence level). Models coupled with NLW performed superior to those that used LW. All ED models had high reliability despite two of the basins achieving median KGE values of ∼ 0.390, highlighting that quantile-based models can generate reliable forecast intervals even when the KGE of the median forecast (q = 0.5) is low. An additional experiment generated synthetic precipitation forecasts with varying degrees of accuracy. The models were trained using accurate precipitation forecasts and tested using both accurate and inaccurate precipitation forecasts. While up to a 120% improvement in KGE was found when accurate precipitation forecasts were used as input to the models, using inaccurate precipitation forecasts resulted in a substantial decrease in reliability. Overall, the results of this study can serve as a benchmark for future studies developing probabilistic DNN models for runoff forecasting.
AbstractList Deep neural network (DNN) models have become increasingly popular in the hydrology community. However, most studies are related to (rainfall-) runoff simulation and comparatively fewer studies have focused on runoff forecasting. In this study, quantile-based (q=0.05, 0.5, 0.95) encoder-decoder (ED) models that use long short-term memory networks (LSTMs) and dense networks (DNs) blocks were developed for three and five days ahead runoff forecasting. Through linear (LW) and non-linear (NLW) wavelet selection, hybrid models LSTM-DN, LSTM-DN-LW, LSTM-DN-NLW, ED, ED-LW, and ED-NLW were developed. For each lead time (LT=3, 5) and value of q, different model configurations were created using different input lag lengths (IL=15, 45, 180). The developed models were tested for runoff forecasting using three basins (with different characteristics) from the Catchment Attributes and MEteorology for Large-sample Studies (CAMELS) dataset. The models were compared using deterministic (e.g., the Kling-Gupta Efficiency [KGE] metric) and probabilistic (e.g., reliability) performance metrics. While the models showed high variability in performance across the three basins (KGE=0.308-0.979 for the q=0.5 models), very high accuracy (up to KGE=0.979) was achieved for one of the basins with high snowmelt. The ED-NLW model was found to generally outperform the other models. Although the LSTM-DN model had the highest median KGE (0.434 across all configurations), the ED and ED-NLW models had higher reliability than LSTM-DN (90% and 91%, respectively, considering a 90 % confidence level). Models coupled with NLW performed superior to those that used LW. All ED models had high reliability despite two of the basins achieving median KGE values of ∼ 0.390, highlighting that quantile-based models can generate reliable forecast intervals even when the KGE of the median forecast (q=0.5) is low. An additional experiment generated synthetic precipitation forecasts with varying degrees of accuracy. The models were trained using “accurate” precipitation forecasts and tested using both “accurate” and “inaccurate” precipitation forecasts. While up to a 120% improvement in KGE was found when “accurate” precipitation forecasts were used as input to the models, using “inaccurate” precipitation forecasts resulted in a substantial decrease in reliability. Overall, the results of this study can serve as a benchmark for future studies developing probabilistic DNN models for runoff forecasting.
•Quantile-based encoder-decoder models proposed for probabilistic runoff forecasting.•Proposed models more accurate and reliable than benchmarks for 3 test catchments.•Wavelet selection can be used to improve forecast accuracy and reliability.•Model performance sensitive to precipitation forecast accuracy. Deep neural network (DNN) models have become increasingly popular in the hydrology community. However, most studies are related to (rainfall-) runoff simulation and comparatively fewer studies have focused on runoff forecasting. In this study, quantile-based (q = 0.05, 0.5, 0.95) encoder-decoder (ED) models that use long short-term memory network (LSTM) and dense network (DN) blocks were developed for three and five days ahead runoff forecasting. Through linear (LW) and non-linear (NLW) wavelet selection, hybrid models LSTM-DN, LSTM-DN-LW, LSTM-DN-NLW, ED, ED-LW, and ED-NLW were developed. For each lead time (LT = 3, 5) and value of q, different model configurations were created using different input lag lengths (IL = 15, 45, 180). The developed models were tested for runoff forecasting using three basins (with different characteristics) from the Catchment Attributes and MEteorology for Large-sample Studies (CAMELS) dataset. The models were compared using deterministic (e.g., the Kling-Gupta efficiency [KGE] metric) and probabilistic (e.g., reliability) statistical metrics. While the models showed high variability in performance across the three basins (KGE = 0.308–0.979 for the q = 0.5 models), very high accuracy (up to KGE = 0.979) was achieved for one of the basins with high snowmelt. The ED-NLW model was found to generally outperform the other models. Although the LSTM-DN model had the highest median KGE (0.434 across all configurations), the ED and ED-NLW models had higher reliability than LSTM-DN (90% and 91%, respectively, considering a 90% confidence level). Models coupled with NLW performed superior to those that used LW. All ED models had high reliability despite two of the basins achieving median KGE values of ∼ 0.390, highlighting that quantile-based models can generate reliable forecast intervals even when the KGE of the median forecast (q = 0.5) is low. An additional experiment generated synthetic precipitation forecasts with varying degrees of accuracy. The models were trained using accurate precipitation forecasts and tested using both accurate and inaccurate precipitation forecasts. While up to a 120% improvement in KGE was found when accurate precipitation forecasts were used as input to the models, using inaccurate precipitation forecasts resulted in a substantial decrease in reliability. Overall, the results of this study can serve as a benchmark for future studies developing probabilistic DNN models for runoff forecasting.
ArticleNumber 129269
Author Quilty, John
Jahangir, Mohammad Sina
You, John
Author_xml – sequence: 1
  givenname: Mohammad Sina
  surname: Jahangir
  fullname: Jahangir, Mohammad Sina
– sequence: 2
  givenname: John
  orcidid: 0000-0002-3509-0312
  surname: You
  fullname: You, John
– sequence: 3
  givenname: John
  orcidid: 0000-0002-0207-8077
  surname: Quilty
  fullname: Quilty, John
  email: john.quilty@uwaterloo.ca
BookMark eNqFkE1LAzEQhoNUsK3-BGGPXnZNstkvPEgpfkFBED2HbDKxWbebNskq_fdu3Z68dC7vYd5nBp4ZmnS2A4SuCU4IJvltkzTrvXK2TSimaUJoRfPqDE1JWVQxLXAxQVOMKY1JXrELNPO-wcOkKZuit0W060UXTAtxLTyoCDppFbhYwV9G2okN_Fj3FWnrok3fBhP7ANtIrEGoyPWd1fqwAyl8MN3nJTrXovVwdcw5-nh8eF8-x6vXp5flYhXLlNEQy0wWhaJ1yWqMC6JKwbSWdVbkda5TYEBVpipCBWR1SiqJgegKcJoJUgHLdDpHN-PdrbO7HnzgG-MltK3owPae03L4Q2jO6FC9G6vSWe8daC5NEMHYLjhhWk4wP5jkDT-a5AeTfDQ50Nk_euvMRrj9Se5-5GCw8G3AcS_NoBeUGWQFrqw5ceEX9-mUTQ
CitedBy_id crossref_primary_10_1016_j_jhydrol_2024_131737
crossref_primary_10_1016_j_eswa_2024_126004
crossref_primary_10_1016_j_jhydrol_2025_132906
crossref_primary_10_3390_w15223947
crossref_primary_10_1029_2025GL116707
crossref_primary_10_1016_j_jhydrol_2024_131434
crossref_primary_10_1016_j_ejrh_2025_102365
crossref_primary_10_1016_j_jhydrol_2025_132769
crossref_primary_10_1016_j_jhydrol_2025_132701
crossref_primary_10_1029_2023WR035139
crossref_primary_10_2166_hydro_2024_205
crossref_primary_10_1109_ACCESS_2024_3384066
crossref_primary_10_1016_j_jhydrol_2024_131494
crossref_primary_10_1029_2024WR039659
crossref_primary_10_2166_nh_2024_124
crossref_primary_10_1016_j_jhydrol_2025_134004
crossref_primary_10_1007_s10489_024_05345_w
crossref_primary_10_2166_nh_2025_160
crossref_primary_10_1109_TGRS_2025_3605332
crossref_primary_10_1007_s00477_024_02780_6
crossref_primary_10_2166_hydro_2025_029
crossref_primary_10_1016_j_jhydrol_2023_130138
crossref_primary_10_1016_j_jhydrol_2023_130498
crossref_primary_10_1038_s41598_025_17207_7
crossref_primary_10_5194_hess_29_841_2025
crossref_primary_10_1007_s12145_025_01907_9
crossref_primary_10_1007_s12145_024_01569_z
crossref_primary_10_1016_j_jhydrol_2024_131301
crossref_primary_10_1029_2024WR038105
crossref_primary_10_1109_ACCESS_2024_3412948
crossref_primary_10_1016_j_jhydrol_2025_132879
crossref_primary_10_1371_journal_pone_0321583
crossref_primary_10_1016_j_jhydrol_2025_132935
crossref_primary_10_1016_j_jhydrol_2025_133308
crossref_primary_10_1016_j_asoc_2024_112352
crossref_primary_10_1186_s43093_025_00532_8
crossref_primary_10_1038_s41598_024_81779_z
crossref_primary_10_1016_j_jhydrol_2023_130076
Cites_doi 10.1016/j.jhydrol.2019.03.099
10.1016/j.jpowsour.2019.227558
10.3390/w13040437
10.1016/j.engappai.2022.105545
10.1016/j.jhydrol.2012.06.029
10.2166/hydro.2008.015
10.1098/rspa.2003.1199
10.1016/j.envsoft.2021.105094
10.1007/s00477-020-01874-1
10.1016/j.apenergy.2018.10.078
10.1016/j.jhydrol.2021.127043
10.1016/j.envsoft.2020.104718
10.1016/j.jhydrol.2020.125127
10.1198/016214506000001437
10.5194/gmd-12-2463-2019
10.5194/hess-21-5293-2017
10.1016/j.jhydrol.2021.126067
10.1029/2020WR029229
10.5194/hess-22-6005-2018
10.1029/2019WR025326
10.1016/j.jhydrol.2018.05.003
10.1207/s15516709cog1402_1
10.1016/j.ifacol.2022.11.015
10.13031/2013.23153
10.1016/j.agrformet.2019.107647
10.1016/j.asoc.2021.107083
10.1007/s00477-021-02013-0
10.2166/hydro.2013.075
10.5194/hess-19-209-2015
10.1016/j.jhydrol.2022.127653
10.1007/s11269-021-03002-2
10.1016/j.jhydrol.2015.01.042
10.21105/joss.01903
10.1016/j.jhydrol.2019.124296
10.1175/JCLI-D-12-00249.1
10.1061/(ASCE)1084-0699(2006)11:6(597)
10.1016/j.pce.2018.07.003
10.1006/jath.2000.3514
10.3390/w11071387
10.1016/j.jhydrol.2021.126888
10.1016/j.envsoft.2022.105326
10.1016/j.jhydrol.2015.05.051
10.1016/j.jhydrol.2013.10.003
10.5194/hess-24-5491-2020
10.1016/j.scitotenv.2022.161035
10.1111/jfr3.12585
10.1016/j.neucom.2013.05.023
10.1016/j.jhydrol.2020.125376
10.3390/en14061596
10.1029/2019WR026226
10.3390/w11102126
10.1016/j.jhydrol.2018.07.035
10.1016/j.jhydrol.2021.126378
10.1016/j.jhydrol.2004.10.008
10.5194/hess-25-2685-2021
10.1016/j.jhydrol.2020.124631
10.5194/hess-26-2387-2022
10.3390/w10111543
10.1371/journal.pone.0157243
10.1016/j.jhydrol.2019.123957
10.1016/j.envsoft.2020.104926
10.1016/j.jhydrol.2021.126831
10.1029/2019WR026933
10.1111/j.1467-6419.2006.00502.x
10.1016/j.jhydrol.2021.126196
10.1016/j.jhydrol.2022.127764
10.1002/2015JD023787
10.5194/hess-26-4013-2022
10.1007/s10040-021-02403-2
10.2166/nh.2021.161
10.1016/j.envsoft.2021.105119
10.1007/s00521-022-07523-8
10.3390/w13010028
10.1016/j.neucom.2020.04.110
10.1142/S0129065704001899
10.1016/j.jhydrol.2019.06.036
10.18653/v1/D15-1166
10.1016/j.jhydrol.2013.09.025
10.1016/j.advwatres.2020.103622
10.1016/j.advwatres.2009.10.013
10.3390/app11115029
10.1016/j.jhydrol.2021.126526
10.3390/su13031336
10.5194/hess-23-5089-2019
10.1007/978-3-0348-8266-8_56
10.1002/met.1491
10.1029/2019WR026793
10.1016/j.envsoft.2022.105474
10.1016/j.jhydrol.2015.09.047
10.1029/2021WR030216
10.1016/j.jhydrol.2009.08.003
10.1016/j.jhydrol.2011.11.042
10.1016/j.cageo.2010.07.005
10.1162/neco.1997.9.8.1735
10.1016/j.asoc.2019.03.046
10.1029/2021WR029772
ContentType Journal Article
Copyright 2023 Elsevier B.V.
Copyright_xml – notice: 2023 Elsevier B.V.
DBID AAYXX
CITATION
7S9
L.6
DOI 10.1016/j.jhydrol.2023.129269
DatabaseName CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitle CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList AGRICOLA

DeliveryMethod fulltext_linktorsrc
Discipline Geography
EISSN 1879-2707
ExternalDocumentID 10_1016_j_jhydrol_2023_129269
S0022169423002111
GroupedDBID --K
--M
-~X
.~1
0R~
1B1
1RT
1~.
1~5
29K
4.4
457
4G.
5GY
5VS
6TJ
7-5
71M
8P~
9JM
9JN
AABNK
AABVA
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALCJ
AALRI
AAOAW
AAQFI
AAQXK
AATLK
AAXUO
ABEFU
ABFNM
ABGRD
ABJNI
ABMAC
ABQEM
ABQYD
ABTAH
ABXDB
ABYKQ
ACDAQ
ACGFS
ACIUM
ACLVX
ACNCT
ACRLP
ACSBN
ADBBV
ADEZE
ADMUD
ADQTV
AEBSH
AEKER
AENEX
AEQOU
AFFNX
AFKWA
AFTJW
AFXIZ
AGHFR
AGUBO
AGYEJ
AHHHB
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ASPBG
ATOGT
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
CBWCG
CS3
D-I
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FA8
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HLV
HMA
HVGLF
HZ~
H~9
IHE
IMUCA
J1W
K-O
KOM
LW9
LY3
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SAB
SCC
SDF
SDG
SDP
SEP
SES
SEW
SPC
SPCBC
SPD
SSA
SSE
SSZ
T5K
TN5
UQL
VOH
WUQ
Y6R
ZCA
ZMT
ZY4
~02
~G-
~KM
9DU
AAHBH
AATTM
AAXKI
AAYWO
AAYXX
ABUFD
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
ADVLN
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
7S9
L.6
ID FETCH-LOGICAL-c342t-c5c77d2b84b0071d8a4ffcb576b6f3e4e2d5d912ae5b319c0e1f9e035a19e45f3
ISICitedReferencesCount 43
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000965718600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0022-1694
IngestDate Thu Oct 02 21:42:10 EDT 2025
Sat Nov 29 06:57:08 EST 2025
Tue Nov 18 21:09:13 EST 2025
Fri Feb 23 02:34:34 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
LSTM
Encoder-decoder
Runoff forecasting
Hydrological forecasting
Wavelet decomposition
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c342t-c5c77d2b84b0071d8a4ffcb576b6f3e4e2d5d912ae5b319c0e1f9e035a19e45f3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-3509-0312
0000-0002-0207-8077
PQID 2834212642
PQPubID 24069
ParticipantIDs proquest_miscellaneous_2834212642
crossref_citationtrail_10_1016_j_jhydrol_2023_129269
crossref_primary_10_1016_j_jhydrol_2023_129269
elsevier_sciencedirect_doi_10_1016_j_jhydrol_2023_129269
PublicationCentury 2000
PublicationDate 2023-04-01
PublicationDateYYYYMMDD 2023-04-01
PublicationDate_xml – month: 04
  year: 2023
  text: 2023-04-01
  day: 01
PublicationDecade 2020
PublicationTitle Journal of hydrology (Amsterdam)
PublicationYear 2023
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Borovykh, A., Bohte, S. and Oosterlee, C.W., 2017. Conditional time series forecasting with convolutional neural networks.
Yin, Zhang, Wang, Zhang, Xia, Jin (b0520) 2021; 598
Hu, Wu, Li, Jian, Li, Lou (b0215) 2018; 10
Kratzert, Klotz, Brenner, Schulz, Herrnegger (b0250) 2018; 22
Moriasi, Arnold, Van Liew, Bingner, Harmel, Veith (b0350) 2007; 50
Ding, Zhu, Feng, Zhang, Cheng (b0135) 2020; 403
Coulibaly, Baldwin (b0120) 2005; 307
Li, Lü, Horton, An, Yu (b0280) 2014; 16
Liu, Zhang, Kang, Li, Lei (b0300) 2021; 13
Partington, Brunner, Simmons, Werner, Therrien, Maier, Dandy (b0390) 2012; 458
Elman (b0140) 1990; 14
Chidepudi, Massei, Jardani, Henriot, Allier, Baulon (b0105) 2023; 865
Lv, Liang, Chen, Zhou, Li, Wei, Wang (b0320) 2020; 141
Barzegar, Aalami, Adamowski (b0050) 2021; 598
Bian, He, Yang, Huang (b0055) 2020; 449
Jamei, Ahmadianfar, Karbasi, Malik, Kisi, Yaseen (b0225) 2023; 117
Xie, Liu, Zhang, Han, Wang, Shen (b0510) 2021; 603
Head, T., Kumar, M., Nahrstaedt, H., Louppe, G. and Shcherbatyi, I., 2020. scikit-optimize/scikit-optimize: v0. 8.1.
12th {USENIX} symposium on operating systems design and implementation ({OSDI} 16)
Han, Choi, Jung, Kim (b0195) 2021; 13
Han, Morrison (b0190) 2022; 608
Jin, Zheng, Kong, Wang, Bai, Su, Lin (b0230) 2021; 14
Alibabaei, Gaspar, Lima (b0025) 2021; 11
Acharya, Babel, Madsen, Sisomphon, Shrestha (b0010) 2020; 13
Li, Jamieson, DeSalvo, Rostamizadeh, Talwalkar (b0275) 2017; 18
Adombi, Chesnaux, Boucher (b0020) 2021; 29
.
Hao, Cominola, Castelletti (b0200) 2022; 55
Zhou, Chen, Singh, Zhou, Chen, Xiong (b0545) 2019; 573
Le, Ho, Lee, Jung (b0270) 2019; 11
arXiv preprint arXiv:1012.2599.
Wang, Gan, Sun, Zhang, Lu, Kang (b0490) 2019; 235
arXiv preprint arXiv:1412.6980.
Apaydin, Sibtain (b0035) 2021; 603
Nevo, Morin, Gerzi Rosenthal, Metzger, Barshai, Weitzner, Voloshin, Kratzert, Elidan, Dror, Begelman (b0355) 2022; 26
Jahangir, Biazar, Hah, Quilty, Isazadeh (b0220) 2021
Zhou, Liu, Duan (b0550) 2020; 588
Feng, Fang, Shen (b0145) 2020; 56
Cui, Zhou, Guo, Wang, Xu (b0130) 2022; 609
Hah, Quilty, Sikorska-Senoner (b0180) 2022
Li, Marshall, Liang, Sharma, Zhou (b0290) 2021; 603
Quilty, Adamowski (b0410) 2020; 130
Li, Marshall, Liang, Sharma, Zhou (b0285) 2021; 57
Newman, Clark, Sampson, Wood, Hay, Bock, Viger, Blodgett, Brekke, Arnold, Hopson (b0360) 2015; 19
Mehr, Kahya, Olyaie (b0340) 2013; 505
Walden, A.T., 2001. Wavelet analysis of discrete time series. In
Smith, Marshall, Sharma (b0450) 2015; 528
Nielsen (b0370) 2001; 108
Boucher, Quilty, Adamowski (b0075) 2020; 56
Goodfellow, Bengio, Courville (b0170) 2016
Lian, Luo, Wang, Zuo, Wei (b0295) 2022; 36
Gupta, Kling, Yilmaz, Martinez (b0175) 2009; 377
Seeger (b0435) 2004; 14
Quilty, Adamowski (b0405) 2018; 563
Kratzert, Klotz, Hochreiter, Nearing (b0260) 2021; 25
Tasdighi, Arabi, Harmel (b0460) 2018; 564
Addor, Newman, Mizukami, Clark (b0015) 2017; 21
Mehdizadeh, Fathian, Adamowski (b0335) 2019; 80
Yucel, Onen, Yilmaz, Gochis (b0525) 2015; 523
Tyralis, Papacharalampous, Burnetas, Langousis (b0475) 2019; 577
Malik, Tikhamarine, Souag-Gamane, Kisi, Pham (b0325) 2020; 34
Chollet, F. (2015). Keras.
Sikorska-Senoner, Quilty (b0445) 2021; 143
Zuo, Luo, Wang, Lian, He (b0555) 2020; 24
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., ... & Zheng, X. (2016). Tensorflow: A system for large-scale machine learning. In
Sezen, Bezak, Bai, Šraj (b0440) 2019; 576
Luong, M.T., Pham, H. and Manning, C.D., 2015. Effective approaches to attention-based neural machine translation.
McCuen, Knight, Cutter (b0330) 2006; 11
Zhang, Chen, Khan, Zhang, Kuang, Liang, Taccari, Nuttall (b0530) 2021; 596
Quilty, Sikorska-Senoner, Hah (b0420) 2022; 149
Chadalawada, Herath, Babovic (b0095) 2020; 56
Ponnoprat (b0400) 2021; 102
Thornton, P.E., Thornton, M.M., Mayer, B.W., Wilhelmi, N., Wei, Y., Devarakonda, R. and Cook, R.B., 2014.
Zhang, Telesford, Giusti, Lim, Bassett (b0540) 2016; 11
Solomatine, Ostfeld (b0455) 2008; 10
Alizadeh, Ghaderi Bafti, Kamangir, Zhang, Wright, Franz (b0030) 2021; 601
Valipour (b0480) 2015; 22
Cheng, Fang, Kinouchi, Navon, Pain (b0100) 2020; 590
Ni, Wang, Singh, Wu, Wang, Tao, Zhang (b0365) 2020; 583
Bittelli, Tomei, Pistocchi, Flury, Boll, Brooks, Antolini (b0060) 2010; 33
Lu, Konapala, Painter, Kao, Gangrade (b0310) 2021; 22
Papacharalampous, Langousis (b0380) 2022; 58
Hochreiter, Schmidhuber (b0210) 1997; 9
Kao, Zhou, Chang, Chang (b0235) 2020; 583
Zhang, Peng, Zhang, Wang (b0535) 2015; 530
Hammad, Shoaib, Salahudin, Baig, Khan, Ullah (b0185) 2021; 35
Papacharalampous, Tyralis, Langousis, Jayawardena, Sivakumar, Mamassis, Montanari, Koutsoyiannis (b0385) 2019; 11
(pp. 265-283).
Liu, Zhou, Chen, Guan (b0305) 2015; 120
Kingma, D.P. and Ba, J., 2014. Adam: A method for stochastic optimization.
Kratzert, Klotz, Shalev, Klambauer, Hochreiter, Nearing (b0255) 2019; 23
Quilty, Adamowski (b0415) 2021; 144
Percival, Walden (b0395) 2000; Vol. 4
Asadi, Shahrabi, Abbaszadeh, Tabanmehr (b0040) 2013; 121
Girihagama, Naveed Khaliq, Lamontagne, Perdikaris, Roy, Sushama, Elshorbagy (b0160) 2022; 34
Wang, Karimi (b0495) 2022; 26
arXiv preprint arXiv:1508.04025.
Rathinasamy, Adamowski, Khosa (b0425) 2013; 507
Crowley (b0125) 2007; 21
Boucher, Tremblay, Delorme, Perreault, Anctil (b0070) 2012; 416
Yang, Zhang (b0515) 2021; 22
Olhede, Walden (b0375) 2004; 460
Samadi, Sadrolashrafi, Kholghi (b0430) 2019; 109
Cannon (b0090) 2011; 37
Gauch, Mai, Lin (b0150) 2021; 135
Team, R.C., 2013. R: A language and environment for statistical computing.
Bürger, Sobie, Cannon, Werner, Murdock (b0085) 2013; 26
Ghaemi, Rezaie-Balf, Adamowski, Kisi, Quilty (b0155) 2019; 278
Chlumsky, Mai, Craig, Tolson (b0110) 2021; 57
Knoben, Freer, Fowler, Peel, Woods (b0245) 2019; 12
Gneiting, Raftery (b0165) 2007; 102
Lang, Binder, Richter, Schratz, Pfisterer, Coors, Au, Casalicchio, Kotthoff, Bischl (b0265) 2019; 4
Daymet: Daily Surface Weather Data on a 1-km Grid for North America, Version 2. Oak Ridge National Lab.(ORNL), Oak Ridge, TN (United States).
Wu, Chen, Zhang, Xiong, Lei, Deng (b0500) 2019; 17
(pp. 627-641). Birkhäuser, Basel.
Bai, Li, Liu, Li, Zhang, Qin (b0045) 2021; 52
Moges, Demissie, Larsen, Yassin (b0345) 2020; 13
European Congress of Mathematics
Xiang, Yan, Demir (b0505) 2020; 56
arXiv preprint arXiv:1703.04691.
Brochu, E., Cora, V.M. and De Freitas, N., 2010. A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning.
Le (10.1016/j.jhydrol.2023.129269_b0270) 2019; 11
Yin (10.1016/j.jhydrol.2023.129269_b0520) 2021; 598
Zhang (10.1016/j.jhydrol.2023.129269_b0530) 2021; 596
Li (10.1016/j.jhydrol.2023.129269_b0290) 2021; 603
Nevo (10.1016/j.jhydrol.2023.129269_b0355) 2022; 26
Yucel (10.1016/j.jhydrol.2023.129269_b0525) 2015; 523
Quilty (10.1016/j.jhydrol.2023.129269_b0415) 2021; 144
Cannon (10.1016/j.jhydrol.2023.129269_b0090) 2011; 37
Moges (10.1016/j.jhydrol.2023.129269_b0345) 2020; 13
Gupta (10.1016/j.jhydrol.2023.129269_b0175) 2009; 377
Crowley (10.1016/j.jhydrol.2023.129269_b0125) 2007; 21
Elman (10.1016/j.jhydrol.2023.129269_b0140) 1990; 14
Cui (10.1016/j.jhydrol.2023.129269_b0130) 2022; 609
Yang (10.1016/j.jhydrol.2023.129269_b0515) 2021; 22
Li (10.1016/j.jhydrol.2023.129269_b0285) 2021; 57
10.1016/j.jhydrol.2023.129269_b0315
Sikorska-Senoner (10.1016/j.jhydrol.2023.129269_b0445) 2021; 143
Hammad (10.1016/j.jhydrol.2023.129269_b0185) 2021; 35
Kao (10.1016/j.jhydrol.2023.129269_b0235) 2020; 583
Liu (10.1016/j.jhydrol.2023.129269_b0305) 2015; 120
Ponnoprat (10.1016/j.jhydrol.2023.129269_b0400) 2021; 102
Jin (10.1016/j.jhydrol.2023.129269_b0230) 2021; 14
Asadi (10.1016/j.jhydrol.2023.129269_b0040) 2013; 121
Coulibaly (10.1016/j.jhydrol.2023.129269_b0120) 2005; 307
Hu (10.1016/j.jhydrol.2023.129269_b0215) 2018; 10
Nielsen (10.1016/j.jhydrol.2023.129269_b0370) 2001; 108
Lang (10.1016/j.jhydrol.2023.129269_b0265) 2019; 4
Feng (10.1016/j.jhydrol.2023.129269_b0145) 2020; 56
10.1016/j.jhydrol.2023.129269_b0205
Zhang (10.1016/j.jhydrol.2023.129269_b0540) 2016; 11
Goodfellow (10.1016/j.jhydrol.2023.129269_b0170) 2016
Liu (10.1016/j.jhydrol.2023.129269_b0300) 2021; 13
Partington (10.1016/j.jhydrol.2023.129269_b0390) 2012; 458
Papacharalampous (10.1016/j.jhydrol.2023.129269_b0385) 2019; 11
Jahangir (10.1016/j.jhydrol.2023.129269_b0220) 2021
Addor (10.1016/j.jhydrol.2023.129269_b0015) 2017; 21
Jamei (10.1016/j.jhydrol.2023.129269_b0225) 2023; 117
Apaydin (10.1016/j.jhydrol.2023.129269_b0035) 2021; 603
Wang (10.1016/j.jhydrol.2023.129269_b0495) 2022; 26
Chidepudi (10.1016/j.jhydrol.2023.129269_b0105) 2023; 865
Samadi (10.1016/j.jhydrol.2023.129269_b0430) 2019; 109
Hochreiter (10.1016/j.jhydrol.2023.129269_b0210) 1997; 9
Ding (10.1016/j.jhydrol.2023.129269_b0135) 2020; 403
Gauch (10.1016/j.jhydrol.2023.129269_b0150) 2021; 135
Kratzert (10.1016/j.jhydrol.2023.129269_b0250) 2018; 22
Han (10.1016/j.jhydrol.2023.129269_b0190) 2022; 608
Zhang (10.1016/j.jhydrol.2023.129269_b0535) 2015; 530
Zhou (10.1016/j.jhydrol.2023.129269_b0545) 2019; 573
10.1016/j.jhydrol.2023.129269_b0065
Newman (10.1016/j.jhydrol.2023.129269_b0360) 2015; 19
Wang (10.1016/j.jhydrol.2023.129269_b0490) 2019; 235
Chadalawada (10.1016/j.jhydrol.2023.129269_b0095) 2020; 56
10.1016/j.jhydrol.2023.129269_b0465
Seeger (10.1016/j.jhydrol.2023.129269_b0435) 2004; 14
Malik (10.1016/j.jhydrol.2023.129269_b0325) 2020; 34
Barzegar (10.1016/j.jhydrol.2023.129269_b0050) 2021; 598
Gneiting (10.1016/j.jhydrol.2023.129269_b0165) 2007; 102
Percival (10.1016/j.jhydrol.2023.129269_b0395) 2000; Vol. 4
Bai (10.1016/j.jhydrol.2023.129269_b0045) 2021; 52
Acharya (10.1016/j.jhydrol.2023.129269_b0010) 2020; 13
10.1016/j.jhydrol.2023.129269_b0470
Zhou (10.1016/j.jhydrol.2023.129269_b0550) 2020; 588
Lian (10.1016/j.jhydrol.2023.129269_b0295) 2022; 36
Ni (10.1016/j.jhydrol.2023.129269_b0365) 2020; 583
Alizadeh (10.1016/j.jhydrol.2023.129269_b0030) 2021; 601
10.1016/j.jhydrol.2023.129269_b0115
Rathinasamy (10.1016/j.jhydrol.2023.129269_b0425) 2013; 507
Wu (10.1016/j.jhydrol.2023.129269_b0500) 2019; 17
Kratzert (10.1016/j.jhydrol.2023.129269_b0255) 2019; 23
Smith (10.1016/j.jhydrol.2023.129269_b0450) 2015; 528
Quilty (10.1016/j.jhydrol.2023.129269_b0420) 2022; 149
10.1016/j.jhydrol.2023.129269_b0080
Lu (10.1016/j.jhydrol.2023.129269_b0310) 2021; 22
Olhede (10.1016/j.jhydrol.2023.129269_b0375) 2004; 460
Cheng (10.1016/j.jhydrol.2023.129269_b0100) 2020; 590
Knoben (10.1016/j.jhydrol.2023.129269_b0245) 2019; 12
Xiang (10.1016/j.jhydrol.2023.129269_b0505) 2020; 56
Bian (10.1016/j.jhydrol.2023.129269_b0055) 2020; 449
Xie (10.1016/j.jhydrol.2023.129269_b0510) 2021; 603
10.1016/j.jhydrol.2023.129269_b0240
McCuen (10.1016/j.jhydrol.2023.129269_b0330) 2006; 11
Tasdighi (10.1016/j.jhydrol.2023.129269_b0460) 2018; 564
Bittelli (10.1016/j.jhydrol.2023.129269_b0060) 2010; 33
Li (10.1016/j.jhydrol.2023.129269_b0280) 2014; 16
Alibabaei (10.1016/j.jhydrol.2023.129269_b0025) 2021; 11
10.1016/j.jhydrol.2023.129269_b0005
Papacharalampous (10.1016/j.jhydrol.2023.129269_b0380) 2022; 58
Mehr (10.1016/j.jhydrol.2023.129269_b0340) 2013; 505
Li (10.1016/j.jhydrol.2023.129269_b0275) 2017; 18
Moriasi (10.1016/j.jhydrol.2023.129269_b0350) 2007; 50
Valipour (10.1016/j.jhydrol.2023.129269_b0480) 2015; 22
10.1016/j.jhydrol.2023.129269_b0485
Girihagama (10.1016/j.jhydrol.2023.129269_b0160) 2022; 34
Mehdizadeh (10.1016/j.jhydrol.2023.129269_b0335) 2019; 80
Ghaemi (10.1016/j.jhydrol.2023.129269_b0155) 2019; 278
Lv (10.1016/j.jhydrol.2023.129269_b0320) 2020; 141
Solomatine (10.1016/j.jhydrol.2023.129269_b0455) 2008; 10
Adombi (10.1016/j.jhydrol.2023.129269_b0020) 2021; 29
Kratzert (10.1016/j.jhydrol.2023.129269_b0260) 2021; 25
Quilty (10.1016/j.jhydrol.2023.129269_b0410) 2020; 130
Boucher (10.1016/j.jhydrol.2023.129269_b0070) 2012; 416
Hah (10.1016/j.jhydrol.2023.129269_b0180) 2022
Zuo (10.1016/j.jhydrol.2023.129269_b0555) 2020; 24
Hao (10.1016/j.jhydrol.2023.129269_b0200) 2022; 55
Sezen (10.1016/j.jhydrol.2023.129269_b0440) 2019; 576
Quilty (10.1016/j.jhydrol.2023.129269_b0405) 2018; 563
Tyralis (10.1016/j.jhydrol.2023.129269_b0475) 2019; 577
Bürger (10.1016/j.jhydrol.2023.129269_b0085) 2013; 26
Boucher (10.1016/j.jhydrol.2023.129269_b0075) 2020; 56
Han (10.1016/j.jhydrol.2023.129269_b0195) 2021; 13
Chlumsky (10.1016/j.jhydrol.2023.129269_b0110) 2021; 57
References_xml – volume: 590
  start-page: 125376
  year: 2020
  ident: b0100
  article-title: Long lead-time daily and monthly streamflow forecasting using machine learning methods
  publication-title: J. Hydrol.
– volume: 18
  start-page: 6765
  year: 2017
  end-page: 6816
  ident: b0275
  article-title: Hyperband: A novel bandit-based approach to hyperparameter optimization
  publication-title: J. Machine Learn. Res.
– volume: 58
  year: 2022
  ident: b0380
  article-title: Probabilistic water demand forecasting using quantile regression algorithms
  publication-title: Water Resour. Res.
– volume: 583
  year: 2020
  ident: b0235
  article-title: Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting
  publication-title: J. Hydrol.
– volume: 13
  start-page: 28
  year: 2020
  ident: b0345
  article-title: Sources of hydrological model uncertainties and advances in their analysis
  publication-title: Water
– volume: 21
  start-page: 5293
  year: 2017
  end-page: 5313
  ident: b0015
  article-title: The CAMELS data set: catchment attributes and meteorology for large-sample studies
  publication-title: Hydrol. Earth Syst. Sci.
– volume: 26
  start-page: 4013
  year: 2022
  end-page: 4032
  ident: b0355
  article-title: Flood forecasting with machine learning models in an operational framework
  publication-title: Hydrol. Earth Syst. Sci.
– volume: 11
  start-page: 597
  year: 2006
  end-page: 602
  ident: b0330
  article-title: Evaluation of the Nash-Sutcliffe efficiency index
  publication-title: J. Hydrol. Eng.
– volume: 22
  start-page: 1421
  year: 2021
  end-page: 1438
  ident: b0310
  article-title: Streamflow simulation in data-scarce basins using bayesian and physics-informed machine learning models
  publication-title: J. Hydrometeorol.
– volume: 14
  start-page: 179
  year: 1990
  end-page: 211
  ident: b0140
  article-title: Finding structure in time
  publication-title: Cognit. Sci.
– volume: 598
  year: 2021
  ident: b0520
  article-title: Rainfall-runoff modeling using LSTM-based multi-state-vector sequence-to-sequence model
  publication-title: J. Hydrol.
– volume: 24
  start-page: 5491
  year: 2020
  end-page: 5518
  ident: b0555
  article-title: Two-stage variational mode decomposition and support vector regression for streamflow forecasting
  publication-title: Hydrol. Earth Syst. Sci.
– volume: 135
  start-page: 104926
  year: 2021
  ident: b0150
  article-title: The proper care and feeding of CAMELS: How limited training data affects streamflow prediction
  publication-title: Environ. Model. Softw.
– reference: Thornton, P.E., Thornton, M.M., Mayer, B.W., Wilhelmi, N., Wei, Y., Devarakonda, R. and Cook, R.B., 2014.
– volume: 865
  start-page: 161035
  year: 2023
  ident: b0105
  article-title: A wavelet-assisted deep learning approach for simulating groundwater levels affected by low-frequency variability
  publication-title: Sci. Total Environ.
– volume: 528
  start-page: 29
  year: 2015
  end-page: 37
  ident: b0450
  article-title: Modeling residual hydrologic errors with Bayesian inference
  publication-title: J. Hydrol.
– reference: arXiv preprint arXiv:1412.6980.
– volume: 16
  start-page: 973
  year: 2014
  end-page: 988
  ident: b0280
  article-title: Real-time flood forecast using the coupling support vector machine and data assimilation method
  publication-title: J. Hydroinf.
– volume: 10
  start-page: 3
  year: 2008
  end-page: 22
  ident: b0455
  article-title: Data-driven modelling: some past experiences and new approaches
  publication-title: J. Hydroinf.
– volume: 19
  start-page: 209
  year: 2015
  end-page: 223
  ident: b0360
  article-title: Development of a large-sample watershed-scale hydrometeorological data set for the contiguous USA: data set characteristics and assessment of regional variability in hydrologic model performance
  publication-title: Hydrol. Earth Syst. Sci.
– volume: 50
  start-page: 885
  year: 2007
  end-page: 900
  ident: b0350
  article-title: Model evaluation guidelines for systematic quantification of accuracy in watershed simulations
  publication-title: Trans. ASABE
– volume: 603
  start-page: 126831
  year: 2021
  ident: b0035
  article-title: A multivariate streamflow forecasting model by integrating improved complete ensemble empirical mode decomposition with additive noise, sample entropy, Gini index and sequence-to-sequence approaches
  publication-title: J. Hydrol.
– volume: 143
  year: 2021
  ident: b0445
  article-title: A novel ensemble-based conceptual-data-driven approach for improved streamflow simulations
  publication-title: Environ. Model. Softw.
– volume: 22
  start-page: 592
  year: 2015
  end-page: 598
  ident: b0480
  article-title: Long-term runoff study using SARIMA and ARIMA models in the United States
  publication-title: Meteorol. Appl.
– volume: 588
  year: 2020
  ident: b0550
  article-title: Coupling wavelet transform and artificial neural network for forecasting estuarine salinity
  publication-title: J. Hydrol.
– reference: arXiv preprint arXiv:1012.2599.
– volume: 56
  year: 2020
  ident: b0075
  article-title: Data assimilation for streamflow forecasting using extreme learning machines and multilayer perceptrons
  publication-title: Water Resour. Res.
– volume: 34
  start-page: 1755
  year: 2020
  end-page: 1773
  ident: b0325
  article-title: Support vector regression optimized by meta-heuristic algorithms for daily streamflow prediction
  publication-title: Stochastic Environ. Res. Risk Assess.
– volume: 23
  start-page: 5089
  year: 2019
  end-page: 5110
  ident: b0255
  article-title: Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets
  publication-title: Hydrol. Earth Syst. Sci.
– volume: 523
  start-page: 49
  year: 2015
  end-page: 66
  ident: b0525
  article-title: Calibration and evaluation of a flood forecasting system: Utility of numerical weather prediction model, data assimilation and satellite-based rainfall
  publication-title: J. Hydrol.
– volume: 141
  year: 2020
  ident: b0320
  article-title: A long Short-Term memory cyclic model with mutual information for hydrology forecasting: A Case study in the xixian basin
  publication-title: Adv. Water Resour.
– volume: 22
  start-page: 6005
  year: 2018
  end-page: 6022
  ident: b0250
  article-title: Rainfall–runoff modelling using long short-term memory (LSTM) networks
  publication-title: Hydrol. Earth Syst. Sci.
– volume: 9
  start-page: 1735
  year: 1997
  end-page: 1780
  ident: b0210
  article-title: Long short-term memory
  publication-title: Neural Comput.
– reference: (pp. 627-641). Birkhäuser, Basel.
– reference: Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., ... & Zheng, X. (2016). Tensorflow: A system for large-scale machine learning. In
– volume: 576
  start-page: 98
  year: 2019
  end-page: 110
  ident: b0440
  article-title: Hydrological modelling of karst catchment using lumped conceptual and data mining models
  publication-title: J. Hydrol.
– volume: 13
  start-page: e12585
  year: 2020
  ident: b0010
  article-title: Comparison of different quantile regression methods to estimate predictive hydrological uncertainty in the Upper Chao Phraya River Basin, Thailand
  publication-title: J. Flood Risk Manage.
– volume: 21
  start-page: 207
  year: 2007
  end-page: 267
  ident: b0125
  article-title: A guide to wavelets for economists
  publication-title: J. Econ. Surv.
– volume: 109
  start-page: 9
  year: 2019
  end-page: 25
  ident: b0430
  article-title: Development and testing of a rainfall-runoff model for flood simulation in dry mountain catchments: A case study for the Dez River Basin
  publication-title: Physics and Chemistry of the Earth, Parts A/B/C
– volume: 102
  start-page: 359
  year: 2007
  end-page: 378
  ident: b0165
  article-title: Strictly proper scoring rules, prediction, and estimation
  publication-title: J. Am. Stat. Assoc.
– reference: Team, R.C., 2013. R: A language and environment for statistical computing.
– volume: 563
  start-page: 336
  year: 2018
  end-page: 353
  ident: b0405
  article-title: Addressing the incorrect usage of wavelet-based hydrological and water resources forecasting models for real-world applications with best practices and a new forecasting framework
  publication-title: J. Hydrol.
– volume: 4
  start-page: 1903
  year: 2019
  ident: b0265
  article-title: mlr3: A modern object-oriented machine learning framework in R
  publication-title: J. Open Source Software
– reference: Luong, M.T., Pham, H. and Manning, C.D., 2015. Effective approaches to attention-based neural machine translation.
– volume: 29
  start-page: 2671
  year: 2021
  end-page: 2683
  ident: b0020
  article-title: Theory-guided machine learning applied to hydrogeology—state of the art, opportunities and future challenges
  publication-title: Hydrgeol. J.
– volume: 14
  start-page: 1596
  year: 2021
  ident: b0230
  article-title: Deep-learning forecasting method for electric power load via attention-based encoder-decoder with bayesian optimization
  publication-title: Energies
– volume: 601
  start-page: 126526
  year: 2021
  ident: b0030
  article-title: A novel attention-based LSTM cell post-processor coupled with bayesian optimization for streamflow prediction
  publication-title: J. Hydrol.
– volume: 144
  year: 2021
  ident: b0415
  article-title: A maximal overlap discrete wavelet packet transform integrated approach for rainfall forecasting–A case study in the Awash River Basin (Ethiopia)
  publication-title: Environ. Model. Softw.
– volume: 26
  start-page: 3429
  year: 2013
  end-page: 3449
  ident: b0085
  article-title: Downscaling extremes: An intercomparison of multiple methods for future climate
  publication-title: J. Clim.
– volume: 505
  start-page: 240
  year: 2013
  end-page: 249
  ident: b0340
  article-title: Streamflow prediction using linear genetic programming in comparison with a neuro-wavelet technique
  publication-title: J. Hydrol.
– volume: 17
  start-page: 26
  year: 2019
  end-page: 40
  ident: b0500
  article-title: Hyperparameter optimization for machine learning models based on Bayesian optimization
  publication-title: J. Electron. Sci. Technol.
– volume: 57
  year: 2021
  ident: b0110
  article-title: Simultaneous calibration of hydrologic model structure and parameters using a blended model
  publication-title: Water Resour. Res.
– volume: 14
  start-page: 69
  year: 2004
  end-page: 106
  ident: b0435
  article-title: Gaussian processes for machine learning
  publication-title: Int. J. Neural Syst.
– volume: 121
  start-page: 470
  year: 2013
  end-page: 480
  ident: b0040
  article-title: A new hybrid artificial neural networks for rainfall–runoff process modeling
  publication-title: Neurocomputing
– volume: 10
  start-page: 1543
  year: 2018
  ident: b0215
  article-title: Deep learning with a long short-term memory networks approach for rainfall-runoff simulation
  publication-title: Water
– volume: 564
  start-page: 476
  year: 2018
  end-page: 489
  ident: b0460
  article-title: A probabilistic appraisal of rainfall-runoff modeling approaches within SWAT in mixed land use watersheds
  publication-title: J. Hydrol.
– reference: arXiv preprint arXiv:1703.04691.
– volume: 117
  year: 2023
  ident: b0225
  article-title: Development of wavelet-based Kalman online sequential extreme learning machine optimized with Boruta-Random Forest for drought index forecasting
  publication-title: Eng. Appl. Artif. Intel.
– volume: 598
  start-page: 126196
  year: 2021
  ident: b0050
  article-title: Coupling a hybrid CNN-LSTM deep learning model with a Boundary Corrected Maximal Overlap Discrete Wavelet Transform for multiscale Lake water level forecasting
  publication-title: J. Hydrol.
– volume: 307
  start-page: 164
  year: 2005
  end-page: 174
  ident: b0120
  article-title: Nonstationary hydrological time series forecasting using nonlinear dynamic methods
  publication-title: J. Hydrol.
– volume: 460
  start-page: 955
  year: 2004
  end-page: 975
  ident: b0375
  article-title: The Hilbert spectrum via wavelet projections
  publication-title: Proc. Royal Soc. London. Series A: Math. Phys. Eng. Sci.
– volume: 603
  year: 2021
  ident: b0290
  article-title: Characterizing distributed hydrological model residual errors using a probabilistic long short-term memory network
  publication-title: J. Hydrol.
– volume: 596
  year: 2021
  ident: b0530
  article-title: Daily runoff forecasting by deep recursive neural network
  publication-title: J. Hydrol.
– volume: 26
  start-page: 2387
  year: 2022
  end-page: 2403
  ident: b0495
  article-title: Impact of spatial distribution information of rainfall in runoff simulation using deep learning method
  publication-title: Hydrol. Earth Syst. Sci.
– volume: 449
  start-page: 227558
  year: 2020
  ident: b0055
  article-title: State-of-charge sequence estimation of lithium-ion battery based on bidirectional long short-term memory encoder-decoder architecture
  publication-title: J. Power Sources
– volume: 403
  start-page: 348
  year: 2020
  end-page: 359
  ident: b0135
  article-title: Interpretable spatio-temporal attention LSTM model for flood forecasting
  publication-title: Neurocomputing
– volume: 573
  start-page: 524
  year: 2019
  end-page: 533
  ident: b0545
  article-title: Rainfall-runoff simulation in karst dominated areas based on a coupled conceptual hydrological model
  publication-title: J. Hydrol.
– start-page: 1
  year: 2021
  end-page: 25
  ident: b0220
  article-title: Investigating the impact of input variable selection on daily solar radiation prediction accuracy using data-driven models: a case study in northern Iran
  publication-title: Stoch. Env. Res. Risk A.
– volume: 235
  start-page: 10
  year: 2019
  end-page: 20
  ident: b0490
  article-title: Probabilistic individual load forecasting using pinball loss guided LSTM
  publication-title: Appl. Energy
– volume: 34
  start-page: 19995
  year: 2022
  end-page: 20015
  ident: b0160
  article-title: Streamflow modelling and forecasting for Canadian watersheds using LSTM networks with attention mechanism
  publication-title: Neural Comput. Appl.
– volume: 130
  year: 2020
  ident: b0410
  article-title: A stochastic wavelet-based data-driven framework for forecasting uncertain multiscale hydrological and water resources processes
  publication-title: Environ. Model. Softw.
– reference: Walden, A.T., 2001. Wavelet analysis of discrete time series. In
– volume: 80
  start-page: 873
  year: 2019
  end-page: 887
  ident: b0335
  article-title: Hybrid artificial intelligence-time series models for monthly streamflow modeling
  publication-title: Appl. Soft Comput.
– reference: 12th {USENIX} symposium on operating systems design and implementation ({OSDI} 16)
– volume: 11
  start-page: 5029
  year: 2021
  ident: b0025
  article-title: Modeling soil water content and reference evapotranspiration from climate data using deep learning method
  publication-title: Appl. Sci.
– volume: 583
  year: 2020
  ident: b0365
  article-title: Streamflow and rainfall forecasting by two long short-term memory-based models
  publication-title: J. Hydrol.
– reference: Brochu, E., Cora, V.M. and De Freitas, N., 2010. A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning.
– volume: 278
  start-page: 107647
  year: 2019
  ident: b0155
  article-title: On the applicability of maximum overlap discrete wavelet transform integrated with MARS and M5 model tree for monthly pan evaporation prediction
  publication-title: Agric. For. Meteorol.
– volume: 56
  year: 2020
  ident: b0145
  article-title: Enhancing streamflow forecast and extracting insights using long-short term memory networks with data integration at continental scales
  publication-title: Water Resour. Res.
– volume: 13
  start-page: 437
  year: 2021
  ident: b0195
  article-title: Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation
  publication-title: Water
– volume: 37
  start-page: 1277
  year: 2011
  end-page: 1284
  ident: b0090
  article-title: Quantile regression neural networks: Implementation in R and application to precipitation downscaling
  publication-title: Comput. Geosci.
– volume: 149
  year: 2022
  ident: b0420
  article-title: A stochastic conceptual-data-driven approach for improved hydrological simulations
  publication-title: Environ. Model. Softw.
– volume: 11
  start-page: e0157243
  year: 2016
  ident: b0540
  article-title: Choosing wavelet methods, filters, and lengths for functional brain network construction
  publication-title: PLoS One
– volume: 33
  start-page: 106
  year: 2010
  end-page: 122
  ident: b0060
  article-title: Development and testing of a physically based, three-dimensional model of surface and subsurface hydrology
  publication-title: Adv. Water Resour.
– volume: 416
  start-page: 133
  year: 2012
  end-page: 144
  ident: b0070
  article-title: Hydro-economic assessment of hydrological forecasting systems
  publication-title: J. Hydrol.
– reference: Daymet: Daily Surface Weather Data on a 1-km Grid for North America, Version 2. Oak Ridge National Lab.(ORNL), Oak Ridge, TN (United States).
– volume: 36
  start-page: 21
  year: 2022
  end-page: 37
  ident: b0295
  article-title: Climate-driven model based on long short-term memory and bayesian optimization for multi-day-ahead daily streamflow forecasting
  publication-title: Water Resour. Manag.
– volume: Vol. 4
  year: 2000
  ident: b0395
  publication-title: Wavelet methods for time series analysis
– volume: 577
  year: 2019
  ident: b0475
  article-title: Hydrological post-processing using stacked generalization of quantile regression algorithms: Large-scale application over CONUS
  publication-title: J. Hydrol.
– reference: Chollet, F. (2015). Keras.
– volume: 377
  start-page: 80
  year: 2009
  end-page: 91
  ident: b0175
  article-title: Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling
  publication-title: J. Hydrol.
– volume: 507
  start-page: 186
  year: 2013
  end-page: 200
  ident: b0425
  article-title: Multiscale streamflow forecasting using a new Bayesian Model Average based ensemble multi-wavelet Volterra nonlinear method
  publication-title: J. Hydrol.
– volume: 102
  year: 2021
  ident: b0400
  article-title: Short-term daily precipitation forecasting with seasonally-integrated autoencoder
  publication-title: Appl. Soft Comput.
– reference: (pp. 265-283).
– volume: 25
  start-page: 2685
  year: 2021
  end-page: 2703
  ident: b0260
  article-title: A note on leveraging synergy in multiple meteorological data sets with deep learning for rainfall–runoff modeling
  publication-title: Hydrol. Earth Syst. Sci.
– volume: 22
  start-page: 149
  year: 2021
  end-page: 1141
  ident: b0515
  article-title: Hyperparameter Optimization via Sequential Uniform Designs
  publication-title: Journal of Machin Learning Research.
– year: 2016
  ident: b0170
  article-title: Deep Learning
– volume: 56
  year: 2020
  ident: b0505
  article-title: A rainfall‐runoff model with LSTM‐based sequence‐to‐sequence learning
  publication-title: Water Resour. Res.
– reference: Kingma, D.P. and Ba, J., 2014. Adam: A method for stochastic optimization.
– volume: 52
  start-page: 927
  year: 2021
  end-page: 943
  ident: b0045
  article-title: Hydrological probabilistic forecasting based on deep learning and Bayesian optimization algorithm
  publication-title: Hydrol. Res.
– reference: Borovykh, A., Bohte, S. and Oosterlee, C.W., 2017. Conditional time series forecasting with convolutional neural networks.
– volume: 108
  start-page: 36
  year: 2001
  end-page: 52
  ident: b0370
  article-title: On the construction and frequency localization of finite orthogonal quadrature filters
  publication-title: J. Approx. Theory
– volume: 608
  year: 2022
  ident: b0190
  article-title: Improved runoff forecasting performance through error predictions using a deep-learning approach
  publication-title: J. Hydrol.
– reference: arXiv preprint arXiv:1508.04025.
– volume: 11
  start-page: 2126
  year: 2019
  ident: b0385
  article-title: Probabilistic hydrological post-processing at scale: Why and how to apply machine-learning quantile regression algorithms
  publication-title: Water
– volume: 120
  start-page: 10
  year: 2015
  end-page: 116
  ident: b0305
  article-title: A multivariate conditional model for streamflow prediction and spatial precipitation refinement
  publication-title: J. Geophys. Res. Atmos.
– volume: 11
  start-page: 1387
  year: 2019
  ident: b0270
  article-title: Application of long short-term memory (lstm) neural network for flood forecasting
  publication-title: Water
– volume: 35
  start-page: 2213
  year: 2021
  end-page: 2235
  ident: b0185
  article-title: Rainfall forecasting in upper Indus basin using various artificial intelligence techniques
  publication-title: Stoch. Env. Res. Risk A.
– volume: 56
  year: 2020
  ident: b0095
  article-title: Hydrologically informed machine learning for rainfall-runoff modeling: A genetic programming-based toolkit for automatic model induction
  publication-title: Water Resour. Res.
– volume: 530
  start-page: 137
  year: 2015
  end-page: 152
  ident: b0535
  article-title: Are hybrid models integrated with data preprocessing techniques suitable for monthly streamflow forecasting? Some experiment evidences
  publication-title: J. Hydrol.
– volume: 12
  start-page: 2463
  year: 2019
  end-page: 2480
  ident: b0245
  article-title: Modular Assessment of Rainfall-Runoff Models Toolbox (MARRMoT) v1. 2: an open-source, extendable framework providing implementations of 46 conceptual hydrologic models as continuous state-space formulations
  publication-title: Geosci. Model Dev.
– reference: European Congress of Mathematics
– volume: 55
  start-page: 92
  year: 2022
  end-page: 98
  ident: b0200
  article-title: Comparing Predictive Machine Learning Models for Short-and Long-Term Urban Water Demand Forecasting in Milan
  publication-title: Italy. IFAC-PapersOnLine
– reference: Head, T., Kumar, M., Nahrstaedt, H., Louppe, G. and Shcherbatyi, I., 2020. scikit-optimize/scikit-optimize: v0. 8.1.
– volume: 13
  start-page: 1336
  year: 2021
  ident: b0300
  article-title: Research on runoff simulations using deep-learning methods
  publication-title: Sustainability
– reference: .
– volume: 57
  year: 2021
  ident: b0285
  article-title: Bayesian LSTM with stochastic variational inference for estimating model uncertainty in process-based hydrological models
  publication-title: Water Resour. Res.
– volume: 603
  year: 2021
  ident: b0510
  article-title: Physics-guided deep learning for rainfall-runoff modeling by considering extreme events and monotonic relationships
  publication-title: J. Hydrol.
– volume: 458
  start-page: 28
  year: 2012
  end-page: 39
  ident: b0390
  article-title: Evaluation of outputs from automated baseflow separation methods against simulated baseflow from a physically based, surface water-groundwater flow model
  publication-title: J. Hydrol.
– volume: 609
  start-page: 127764
  year: 2022
  ident: b0130
  article-title: Effective improvement of multi-step-ahead flood forecasting accuracy through encoder-decoder with an exogenous input structure
  publication-title: J. Hydrol.
– year: 2022
  ident: b0180
  article-title: Ensemble and stochastic conceptual data-driven approaches for improving streamflow simulations: Exploring different hydrological and data-driven models and a diagnostic tool
  publication-title: Environ. Model. Softw.
– volume: 573
  start-page: 524
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0545
  article-title: Rainfall-runoff simulation in karst dominated areas based on a coupled conceptual hydrological model
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2019.03.099
– volume: 449
  start-page: 227558
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0055
  article-title: State-of-charge sequence estimation of lithium-ion battery based on bidirectional long short-term memory encoder-decoder architecture
  publication-title: J. Power Sources
  doi: 10.1016/j.jpowsour.2019.227558
– volume: 13
  start-page: 437
  issue: 4
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0195
  article-title: Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation
  publication-title: Water
  doi: 10.3390/w13040437
– ident: 10.1016/j.jhydrol.2023.129269_b0205
– volume: 117
  year: 2023
  ident: 10.1016/j.jhydrol.2023.129269_b0225
  article-title: Development of wavelet-based Kalman online sequential extreme learning machine optimized with Boruta-Random Forest for drought index forecasting
  publication-title: Eng. Appl. Artif. Intel.
  doi: 10.1016/j.engappai.2022.105545
– volume: 458
  start-page: 28
  year: 2012
  ident: 10.1016/j.jhydrol.2023.129269_b0390
  article-title: Evaluation of outputs from automated baseflow separation methods against simulated baseflow from a physically based, surface water-groundwater flow model
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2012.06.029
– volume: 10
  start-page: 3
  issue: 1
  year: 2008
  ident: 10.1016/j.jhydrol.2023.129269_b0455
  article-title: Data-driven modelling: some past experiences and new approaches
  publication-title: J. Hydroinf.
  doi: 10.2166/hydro.2008.015
– volume: 460
  start-page: 955
  issue: 2044
  year: 2004
  ident: 10.1016/j.jhydrol.2023.129269_b0375
  article-title: The Hilbert spectrum via wavelet projections
  publication-title: Proc. Royal Soc. London. Series A: Math. Phys. Eng. Sci.
  doi: 10.1098/rspa.2003.1199
– volume: 143
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0445
  article-title: A novel ensemble-based conceptual-data-driven approach for improved streamflow simulations
  publication-title: Environ. Model. Softw.
  doi: 10.1016/j.envsoft.2021.105094
– volume: 34
  start-page: 1755
  issue: 11
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0325
  article-title: Support vector regression optimized by meta-heuristic algorithms for daily streamflow prediction
  publication-title: Stochastic Environ. Res. Risk Assess.
  doi: 10.1007/s00477-020-01874-1
– volume: 235
  start-page: 10
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0490
  article-title: Probabilistic individual load forecasting using pinball loss guided LSTM
  publication-title: Appl. Energy
  doi: 10.1016/j.apenergy.2018.10.078
– volume: 603
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0510
  article-title: Physics-guided deep learning for rainfall-runoff modeling by considering extreme events and monotonic relationships
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2021.127043
– volume: 130
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0410
  article-title: A stochastic wavelet-based data-driven framework for forecasting uncertain multiscale hydrological and water resources processes
  publication-title: Environ. Model. Softw.
  doi: 10.1016/j.envsoft.2020.104718
– volume: 588
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0550
  article-title: Coupling wavelet transform and artificial neural network for forecasting estuarine salinity
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2020.125127
– volume: 102
  start-page: 359
  issue: 477
  year: 2007
  ident: 10.1016/j.jhydrol.2023.129269_b0165
  article-title: Strictly proper scoring rules, prediction, and estimation
  publication-title: J. Am. Stat. Assoc.
  doi: 10.1198/016214506000001437
– volume: 12
  start-page: 2463
  issue: 6
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0245
  article-title: Modular Assessment of Rainfall-Runoff Models Toolbox (MARRMoT) v1. 2: an open-source, extendable framework providing implementations of 46 conceptual hydrologic models as continuous state-space formulations
  publication-title: Geosci. Model Dev.
  doi: 10.5194/gmd-12-2463-2019
– volume: 21
  start-page: 5293
  issue: 10
  year: 2017
  ident: 10.1016/j.jhydrol.2023.129269_b0015
  article-title: The CAMELS data set: catchment attributes and meteorology for large-sample studies
  publication-title: Hydrol. Earth Syst. Sci.
  doi: 10.5194/hess-21-5293-2017
– volume: 596
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0530
  article-title: Daily runoff forecasting by deep recursive neural network
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2021.126067
– volume: 57
  issue: 5
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0110
  article-title: Simultaneous calibration of hydrologic model structure and parameters using a blended model
  publication-title: Water Resour. Res.
  doi: 10.1029/2020WR029229
– ident: 10.1016/j.jhydrol.2023.129269_b0080
– year: 2016
  ident: 10.1016/j.jhydrol.2023.129269_b0170
– volume: 22
  start-page: 6005
  issue: 11
  year: 2018
  ident: 10.1016/j.jhydrol.2023.129269_b0250
  article-title: Rainfall–runoff modelling using long short-term memory (LSTM) networks
  publication-title: Hydrol. Earth Syst. Sci.
  doi: 10.5194/hess-22-6005-2018
– volume: 56
  issue: 1
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0505
  article-title: A rainfall‐runoff model with LSTM‐based sequence‐to‐sequence learning
  publication-title: Water Resour. Res.
  doi: 10.1029/2019WR025326
– volume: 563
  start-page: 336
  year: 2018
  ident: 10.1016/j.jhydrol.2023.129269_b0405
  article-title: Addressing the incorrect usage of wavelet-based hydrological and water resources forecasting models for real-world applications with best practices and a new forecasting framework
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2018.05.003
– ident: 10.1016/j.jhydrol.2023.129269_b0005
– volume: 14
  start-page: 179
  issue: 2
  year: 1990
  ident: 10.1016/j.jhydrol.2023.129269_b0140
  article-title: Finding structure in time
  publication-title: Cognit. Sci.
  doi: 10.1207/s15516709cog1402_1
– volume: 55
  start-page: 92
  issue: 33
  year: 2022
  ident: 10.1016/j.jhydrol.2023.129269_b0200
  article-title: Comparing Predictive Machine Learning Models for Short-and Long-Term Urban Water Demand Forecasting in Milan
  publication-title: Italy. IFAC-PapersOnLine
  doi: 10.1016/j.ifacol.2022.11.015
– ident: 10.1016/j.jhydrol.2023.129269_b0240
– volume: 50
  start-page: 885
  issue: 3
  year: 2007
  ident: 10.1016/j.jhydrol.2023.129269_b0350
  article-title: Model evaluation guidelines for systematic quantification of accuracy in watershed simulations
  publication-title: Trans. ASABE
  doi: 10.13031/2013.23153
– volume: 278
  start-page: 107647
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0155
  article-title: On the applicability of maximum overlap discrete wavelet transform integrated with MARS and M5 model tree for monthly pan evaporation prediction
  publication-title: Agric. For. Meteorol.
  doi: 10.1016/j.agrformet.2019.107647
– volume: 102
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0400
  article-title: Short-term daily precipitation forecasting with seasonally-integrated autoencoder
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2021.107083
– volume: 35
  start-page: 2213
  issue: 11
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0185
  article-title: Rainfall forecasting in upper Indus basin using various artificial intelligence techniques
  publication-title: Stoch. Env. Res. Risk A.
  doi: 10.1007/s00477-021-02013-0
– volume: 18
  start-page: 6765
  issue: 1
  year: 2017
  ident: 10.1016/j.jhydrol.2023.129269_b0275
  article-title: Hyperband: A novel bandit-based approach to hyperparameter optimization
  publication-title: J. Machine Learn. Res.
– volume: 16
  start-page: 973
  issue: 5
  year: 2014
  ident: 10.1016/j.jhydrol.2023.129269_b0280
  article-title: Real-time flood forecast using the coupling support vector machine and data assimilation method
  publication-title: J. Hydroinf.
  doi: 10.2166/hydro.2013.075
– volume: 19
  start-page: 209
  issue: 1
  year: 2015
  ident: 10.1016/j.jhydrol.2023.129269_b0360
  article-title: Development of a large-sample watershed-scale hydrometeorological data set for the contiguous USA: data set characteristics and assessment of regional variability in hydrologic model performance
  publication-title: Hydrol. Earth Syst. Sci.
  doi: 10.5194/hess-19-209-2015
– volume: 608
  year: 2022
  ident: 10.1016/j.jhydrol.2023.129269_b0190
  article-title: Improved runoff forecasting performance through error predictions using a deep-learning approach
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2022.127653
– volume: 36
  start-page: 21
  issue: 1
  year: 2022
  ident: 10.1016/j.jhydrol.2023.129269_b0295
  article-title: Climate-driven model based on long short-term memory and bayesian optimization for multi-day-ahead daily streamflow forecasting
  publication-title: Water Resour. Manag.
  doi: 10.1007/s11269-021-03002-2
– volume: 523
  start-page: 49
  year: 2015
  ident: 10.1016/j.jhydrol.2023.129269_b0525
  article-title: Calibration and evaluation of a flood forecasting system: Utility of numerical weather prediction model, data assimilation and satellite-based rainfall
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2015.01.042
– volume: 4
  start-page: 1903
  issue: 44
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0265
  article-title: mlr3: A modern object-oriented machine learning framework in R
  publication-title: J. Open Source Software
  doi: 10.21105/joss.01903
– volume: 583
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0365
  article-title: Streamflow and rainfall forecasting by two long short-term memory-based models
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2019.124296
– volume: 26
  start-page: 3429
  issue: 10
  year: 2013
  ident: 10.1016/j.jhydrol.2023.129269_b0085
  article-title: Downscaling extremes: An intercomparison of multiple methods for future climate
  publication-title: J. Clim.
  doi: 10.1175/JCLI-D-12-00249.1
– volume: 11
  start-page: 597
  issue: 6
  year: 2006
  ident: 10.1016/j.jhydrol.2023.129269_b0330
  article-title: Evaluation of the Nash-Sutcliffe efficiency index
  publication-title: J. Hydrol. Eng.
  doi: 10.1061/(ASCE)1084-0699(2006)11:6(597)
– volume: 109
  start-page: 9
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0430
  article-title: Development and testing of a rainfall-runoff model for flood simulation in dry mountain catchments: A case study for the Dez River Basin
  publication-title: Physics and Chemistry of the Earth, Parts A/B/C
  doi: 10.1016/j.pce.2018.07.003
– volume: 108
  start-page: 36
  issue: 1
  year: 2001
  ident: 10.1016/j.jhydrol.2023.129269_b0370
  article-title: On the construction and frequency localization of finite orthogonal quadrature filters
  publication-title: J. Approx. Theory
  doi: 10.1006/jath.2000.3514
– volume: 11
  start-page: 1387
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0270
  article-title: Application of long short-term memory (lstm) neural network for flood forecasting
  publication-title: Water
  doi: 10.3390/w11071387
– volume: 603
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0290
  article-title: Characterizing distributed hydrological model residual errors using a probabilistic long short-term memory network
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2021.126888
– volume: Vol. 4
  year: 2000
  ident: 10.1016/j.jhydrol.2023.129269_b0395
– volume: 149
  year: 2022
  ident: 10.1016/j.jhydrol.2023.129269_b0420
  article-title: A stochastic conceptual-data-driven approach for improved hydrological simulations
  publication-title: Environ. Model. Softw.
  doi: 10.1016/j.envsoft.2022.105326
– ident: 10.1016/j.jhydrol.2023.129269_b0470
– volume: 528
  start-page: 29
  year: 2015
  ident: 10.1016/j.jhydrol.2023.129269_b0450
  article-title: Modeling residual hydrologic errors with Bayesian inference
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2015.05.051
– volume: 505
  start-page: 240
  year: 2013
  ident: 10.1016/j.jhydrol.2023.129269_b0340
  article-title: Streamflow prediction using linear genetic programming in comparison with a neuro-wavelet technique
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2013.10.003
– ident: 10.1016/j.jhydrol.2023.129269_b0065
– volume: 24
  start-page: 5491
  issue: 11
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0555
  article-title: Two-stage variational mode decomposition and support vector regression for streamflow forecasting
  publication-title: Hydrol. Earth Syst. Sci.
  doi: 10.5194/hess-24-5491-2020
– volume: 865
  start-page: 161035
  year: 2023
  ident: 10.1016/j.jhydrol.2023.129269_b0105
  article-title: A wavelet-assisted deep learning approach for simulating groundwater levels affected by low-frequency variability
  publication-title: Sci. Total Environ.
  doi: 10.1016/j.scitotenv.2022.161035
– volume: 13
  start-page: e12585
  issue: 1
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0010
  article-title: Comparison of different quantile regression methods to estimate predictive hydrological uncertainty in the Upper Chao Phraya River Basin, Thailand
  publication-title: J. Flood Risk Manage.
  doi: 10.1111/jfr3.12585
– ident: 10.1016/j.jhydrol.2023.129269_b0465
– volume: 121
  start-page: 470
  year: 2013
  ident: 10.1016/j.jhydrol.2023.129269_b0040
  article-title: A new hybrid artificial neural networks for rainfall–runoff process modeling
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2013.05.023
– volume: 590
  start-page: 125376
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0100
  article-title: Long lead-time daily and monthly streamflow forecasting using machine learning methods
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2020.125376
– volume: 14
  start-page: 1596
  issue: 6
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0230
  article-title: Deep-learning forecasting method for electric power load via attention-based encoder-decoder with bayesian optimization
  publication-title: Energies
  doi: 10.3390/en14061596
– volume: 56
  issue: 6
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0075
  article-title: Data assimilation for streamflow forecasting using extreme learning machines and multilayer perceptrons
  publication-title: Water Resour. Res.
  doi: 10.1029/2019WR026226
– volume: 11
  start-page: 2126
  issue: 10
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0385
  article-title: Probabilistic hydrological post-processing at scale: Why and how to apply machine-learning quantile regression algorithms
  publication-title: Water
  doi: 10.3390/w11102126
– volume: 564
  start-page: 476
  year: 2018
  ident: 10.1016/j.jhydrol.2023.129269_b0460
  article-title: A probabilistic appraisal of rainfall-runoff modeling approaches within SWAT in mixed land use watersheds
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2018.07.035
– volume: 598
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0520
  article-title: Rainfall-runoff modeling using LSTM-based multi-state-vector sequence-to-sequence model
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2021.126378
– volume: 307
  start-page: 164
  issue: 1–4
  year: 2005
  ident: 10.1016/j.jhydrol.2023.129269_b0120
  article-title: Nonstationary hydrological time series forecasting using nonlinear dynamic methods
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2004.10.008
– volume: 25
  start-page: 2685
  issue: 5
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0260
  article-title: A note on leveraging synergy in multiple meteorological data sets with deep learning for rainfall–runoff modeling
  publication-title: Hydrol. Earth Syst. Sci.
  doi: 10.5194/hess-25-2685-2021
– volume: 583
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0235
  article-title: Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2020.124631
– ident: 10.1016/j.jhydrol.2023.129269_b0115
– volume: 26
  start-page: 2387
  issue: 9
  year: 2022
  ident: 10.1016/j.jhydrol.2023.129269_b0495
  article-title: Impact of spatial distribution information of rainfall in runoff simulation using deep learning method
  publication-title: Hydrol. Earth Syst. Sci.
  doi: 10.5194/hess-26-2387-2022
– volume: 10
  start-page: 1543
  year: 2018
  ident: 10.1016/j.jhydrol.2023.129269_b0215
  article-title: Deep learning with a long short-term memory networks approach for rainfall-runoff simulation
  publication-title: Water
  doi: 10.3390/w10111543
– start-page: 1
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0220
  article-title: Investigating the impact of input variable selection on daily solar radiation prediction accuracy using data-driven models: a case study in northern Iran
  publication-title: Stoch. Env. Res. Risk A.
– volume: 11
  start-page: e0157243
  issue: 6
  year: 2016
  ident: 10.1016/j.jhydrol.2023.129269_b0540
  article-title: Choosing wavelet methods, filters, and lengths for functional brain network construction
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0157243
– volume: 22
  start-page: 149
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0515
  article-title: Hyperparameter Optimization via Sequential Uniform Designs
  publication-title: Journal of Machin Learning Research.
– volume: 577
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0475
  article-title: Hydrological post-processing using stacked generalization of quantile regression algorithms: Large-scale application over CONUS
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2019.123957
– volume: 135
  start-page: 104926
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0150
  article-title: The proper care and feeding of CAMELS: How limited training data affects streamflow prediction
  publication-title: Environ. Model. Softw.
  doi: 10.1016/j.envsoft.2020.104926
– volume: 603
  start-page: 126831
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0035
  article-title: A multivariate streamflow forecasting model by integrating improved complete ensemble empirical mode decomposition with additive noise, sample entropy, Gini index and sequence-to-sequence approaches
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2021.126831
– volume: 56
  issue: 4
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0095
  article-title: Hydrologically informed machine learning for rainfall-runoff modeling: A genetic programming-based toolkit for automatic model induction
  publication-title: Water Resour. Res.
  doi: 10.1029/2019WR026933
– volume: 21
  start-page: 207
  issue: 2
  year: 2007
  ident: 10.1016/j.jhydrol.2023.129269_b0125
  article-title: A guide to wavelets for economists
  publication-title: J. Econ. Surv.
  doi: 10.1111/j.1467-6419.2006.00502.x
– volume: 598
  start-page: 126196
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0050
  article-title: Coupling a hybrid CNN-LSTM deep learning model with a Boundary Corrected Maximal Overlap Discrete Wavelet Transform for multiscale Lake water level forecasting
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2021.126196
– volume: 609
  start-page: 127764
  year: 2022
  ident: 10.1016/j.jhydrol.2023.129269_b0130
  article-title: Effective improvement of multi-step-ahead flood forecasting accuracy through encoder-decoder with an exogenous input structure
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2022.127764
– volume: 120
  start-page: 10
  issue: 19
  year: 2015
  ident: 10.1016/j.jhydrol.2023.129269_b0305
  article-title: A multivariate conditional model for streamflow prediction and spatial precipitation refinement
  publication-title: J. Geophys. Res. Atmos.
  doi: 10.1002/2015JD023787
– volume: 26
  start-page: 4013
  issue: 15
  year: 2022
  ident: 10.1016/j.jhydrol.2023.129269_b0355
  article-title: Flood forecasting with machine learning models in an operational framework
  publication-title: Hydrol. Earth Syst. Sci.
  doi: 10.5194/hess-26-4013-2022
– volume: 29
  start-page: 2671
  issue: 8
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0020
  article-title: Theory-guided machine learning applied to hydrogeology—state of the art, opportunities and future challenges
  publication-title: Hydrgeol. J.
  doi: 10.1007/s10040-021-02403-2
– volume: 52
  start-page: 927
  issue: 4
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0045
  article-title: Hydrological probabilistic forecasting based on deep learning and Bayesian optimization algorithm
  publication-title: Hydrol. Res.
  doi: 10.2166/nh.2021.161
– volume: 144
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0415
  article-title: A maximal overlap discrete wavelet packet transform integrated approach for rainfall forecasting–A case study in the Awash River Basin (Ethiopia)
  publication-title: Environ. Model. Softw.
  doi: 10.1016/j.envsoft.2021.105119
– volume: 34
  start-page: 19995
  issue: 22
  year: 2022
  ident: 10.1016/j.jhydrol.2023.129269_b0160
  article-title: Streamflow modelling and forecasting for Canadian watersheds using LSTM networks with attention mechanism
  publication-title: Neural Comput. Appl.
  doi: 10.1007/s00521-022-07523-8
– volume: 13
  start-page: 28
  issue: 1
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0345
  article-title: Sources of hydrological model uncertainties and advances in their analysis
  publication-title: Water
  doi: 10.3390/w13010028
– volume: 403
  start-page: 348
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0135
  article-title: Interpretable spatio-temporal attention LSTM model for flood forecasting
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2020.04.110
– volume: 14
  start-page: 69
  issue: 02
  year: 2004
  ident: 10.1016/j.jhydrol.2023.129269_b0435
  article-title: Gaussian processes for machine learning
  publication-title: Int. J. Neural Syst.
  doi: 10.1142/S0129065704001899
– volume: 576
  start-page: 98
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0440
  article-title: Hydrological modelling of karst catchment using lumped conceptual and data mining models
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2019.06.036
– ident: 10.1016/j.jhydrol.2023.129269_b0315
  doi: 10.18653/v1/D15-1166
– volume: 507
  start-page: 186
  year: 2013
  ident: 10.1016/j.jhydrol.2023.129269_b0425
  article-title: Multiscale streamflow forecasting using a new Bayesian Model Average based ensemble multi-wavelet Volterra nonlinear method
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2013.09.025
– volume: 141
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0320
  article-title: A long Short-Term memory cyclic model with mutual information for hydrology forecasting: A Case study in the xixian basin
  publication-title: Adv. Water Resour.
  doi: 10.1016/j.advwatres.2020.103622
– volume: 22
  start-page: 1421
  issue: 6
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0310
  article-title: Streamflow simulation in data-scarce basins using bayesian and physics-informed machine learning models
  publication-title: J. Hydrometeorol.
– volume: 17
  start-page: 26
  issue: 1
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0500
  article-title: Hyperparameter optimization for machine learning models based on Bayesian optimization
  publication-title: J. Electron. Sci. Technol.
– volume: 33
  start-page: 106
  issue: 1
  year: 2010
  ident: 10.1016/j.jhydrol.2023.129269_b0060
  article-title: Development and testing of a physically based, three-dimensional model of surface and subsurface hydrology
  publication-title: Adv. Water Resour.
  doi: 10.1016/j.advwatres.2009.10.013
– volume: 11
  start-page: 5029
  issue: 11
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0025
  article-title: Modeling soil water content and reference evapotranspiration from climate data using deep learning method
  publication-title: Appl. Sci.
  doi: 10.3390/app11115029
– volume: 601
  start-page: 126526
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0030
  article-title: A novel attention-based LSTM cell post-processor coupled with bayesian optimization for streamflow prediction
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2021.126526
– volume: 13
  start-page: 1336
  issue: 3
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0300
  article-title: Research on runoff simulations using deep-learning methods
  publication-title: Sustainability
  doi: 10.3390/su13031336
– volume: 23
  start-page: 5089
  issue: 12
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0255
  article-title: Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets
  publication-title: Hydrol. Earth Syst. Sci.
  doi: 10.5194/hess-23-5089-2019
– ident: 10.1016/j.jhydrol.2023.129269_b0485
  doi: 10.1007/978-3-0348-8266-8_56
– volume: 22
  start-page: 592
  issue: 3
  year: 2015
  ident: 10.1016/j.jhydrol.2023.129269_b0480
  article-title: Long-term runoff study using SARIMA and ARIMA models in the United States
  publication-title: Meteorol. Appl.
  doi: 10.1002/met.1491
– volume: 56
  issue: 9
  year: 2020
  ident: 10.1016/j.jhydrol.2023.129269_b0145
  article-title: Enhancing streamflow forecast and extracting insights using long-short term memory networks with data integration at continental scales
  publication-title: Water Resour. Res.
  doi: 10.1029/2019WR026793
– year: 2022
  ident: 10.1016/j.jhydrol.2023.129269_b0180
  article-title: Ensemble and stochastic conceptual data-driven approaches for improving streamflow simulations: Exploring different hydrological and data-driven models and a diagnostic tool
  publication-title: Environ. Model. Softw.
  doi: 10.1016/j.envsoft.2022.105474
– volume: 530
  start-page: 137
  year: 2015
  ident: 10.1016/j.jhydrol.2023.129269_b0535
  article-title: Are hybrid models integrated with data preprocessing techniques suitable for monthly streamflow forecasting? Some experiment evidences
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2015.09.047
– volume: 58
  issue: 6
  year: 2022
  ident: 10.1016/j.jhydrol.2023.129269_b0380
  article-title: Probabilistic water demand forecasting using quantile regression algorithms
  publication-title: Water Resour. Res.
  doi: 10.1029/2021WR030216
– volume: 377
  start-page: 80
  issue: 1–2
  year: 2009
  ident: 10.1016/j.jhydrol.2023.129269_b0175
  article-title: Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2009.08.003
– volume: 416
  start-page: 133
  year: 2012
  ident: 10.1016/j.jhydrol.2023.129269_b0070
  article-title: Hydro-economic assessment of hydrological forecasting systems
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2011.11.042
– volume: 37
  start-page: 1277
  issue: 9
  year: 2011
  ident: 10.1016/j.jhydrol.2023.129269_b0090
  article-title: Quantile regression neural networks: Implementation in R and application to precipitation downscaling
  publication-title: Comput. Geosci.
  doi: 10.1016/j.cageo.2010.07.005
– volume: 9
  start-page: 1735
  issue: 8
  year: 1997
  ident: 10.1016/j.jhydrol.2023.129269_b0210
  article-title: Long short-term memory
  publication-title: Neural Comput.
  doi: 10.1162/neco.1997.9.8.1735
– volume: 80
  start-page: 873
  year: 2019
  ident: 10.1016/j.jhydrol.2023.129269_b0335
  article-title: Hybrid artificial intelligence-time series models for monthly streamflow modeling
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2019.03.046
– volume: 57
  issue: 9
  year: 2021
  ident: 10.1016/j.jhydrol.2023.129269_b0285
  article-title: Bayesian LSTM with stochastic variational inference for estimating model uncertainty in process-based hydrological models
  publication-title: Water Resour. Res.
  doi: 10.1029/2021WR029772
SSID ssj0000334
Score 2.5715532
Snippet •Quantile-based encoder-decoder models proposed for probabilistic runoff forecasting.•Proposed models more accurate and reliable than benchmarks for 3 test...
Deep neural network (DNN) models have become increasingly popular in the hydrology community. However, most studies are related to (rainfall-) runoff...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 129269
SubjectTerms data collection
Deep learning
Encoder-decoder
Hydrological forecasting
LSTM
meteorology
neural networks
rain
runoff
Runoff forecasting
snowmelt
watersheds
wavelet
Wavelet decomposition
Title A quantile-based encoder-decoder framework for multi-step ahead runoff forecasting
URI https://dx.doi.org/10.1016/j.jhydrol.2023.129269
https://www.proquest.com/docview/2834212642
Volume 619
WOSCitedRecordID wos000965718600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1879-2707
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000334
  issn: 0022-1694
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELegQ4IXxKcYXwoS4iVyaRKncR4j1AmmUb46qW-WHdtqqzUtaYq2_55z7CRdB9p44CWp3DiN7ne9Ozt390PobQjLiIEQFCcQbGOSCIU5-G1MYSkQB0PNldI12UQyHtPpNP3qWPo2NZ1AUhT0_Dxd_1eoYQzANqWz_wB3e1MYgM8AOhwBdjjeCPjMFEoWFfzbsXFR0jetKqUqsVT12ddNPladYlhnFGLAeu1zMMzSL7fFSmvzncr5pmpc29UAdnYhS9vBCaLUbGk6LkijXu3Wwo95wf1jbrak57VifF7N-HLJ5Y6p2U8H_radn1megnbU7UmE0U4qS1cjEAwtffEVI233Cxb9hX3OvrlDH-KO0JK2XG6KPf7Cjk5PTthkNJ28W__Ehi_MvFd35Cm30UGYxCntoYPs02h63HnhKCJNp3jzJF311vs__vLf4pI9D12HHZMH6L4Tt5dZnB-iW6p4hO466vrZxWP0PfMu4-3t4e21eHuAqdfh7dV4exZvbwfvJ-j0aDT58BE7ogycRySscB7nSSJDQYkwIaOknGidC1hKiqGOFFGhjGUahFzFAkxuPlCBTtUginmQKhLr6CnqFatCPUMej0NN8pAoMYwJj3M64LDApcLUV6dC00NEGjGx3HWRN2QmZ6xJF1wwJ11mpMusdA9Rv522tm1UrptAGwyYiwVtjMdAi66b-qbBjIGtNC_AeKFW2w2DUNokQMCS-_kNrnmB7nW6_RL1qnKrXqE7-a9qvilfO337DRHhjpM
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+quantile-based+encoder-decoder+framework+for+multi-step+ahead+runoff+forecasting&rft.jtitle=Journal+of+hydrology+%28Amsterdam%29&rft.au=Sina+Jahangir%2C+Mohammad&rft.au=You%2C+John&rft.au=Quilty%2C+John&rft.date=2023-04-01&rft.issn=0022-1694&rft_id=info:doi/10.1016%2Fj.jhydrol.2023.129269&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0022-1694&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0022-1694&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0022-1694&client=summon