Unsupervised anomaly detection in hourly water demand data using an asymmetric encoder–decoder model

Water demand forecasting (WDF) is essential for the design and optimal management of water distribution systems (WDS). Historical water demand data contribute significantly to WDF. Yet the obtained water demand data contain anomalies on occasions due to failures in WDS or monitoring systems. The con...

Full description

Saved in:
Bibliographic Details
Published in:Journal of hydrology (Amsterdam) Vol. 613; p. 128389
Main Authors: Yan, Jieru, Tao, Tao
Format: Journal Article
Language:English
Published: Elsevier B.V 01.10.2022
Subjects:
ISSN:0022-1694, 1879-2707
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Water demand forecasting (WDF) is essential for the design and optimal management of water distribution systems (WDS). Historical water demand data contribute significantly to WDF. Yet the obtained water demand data contain anomalies on occasions due to failures in WDS or monitoring systems. The contaminated water demand data are invalid to describe the actual water demand, thus degrading the performance of WDF models. However, the importance of anomaly detection in water demand data is underestimated, or at least not explicitly described in many published papers. To fill the gap, we propose an unsupervised anomaly detection method based on an asymmetric encoder–decoder (asyED) model. Different from the symmetric structure of a traditional autoencoder where a signal is reproduced from itself, asyED is asymmetric where a signal is reproduced from the upstream and downstream information of the signal, while the signal itself does not participate in the reconstruction. In light of this feature, asyED is powerful in identifying anomalies. The proposed method is employed to detect anomalies in hourly water demand data which exhibit trend and seasonality. The results show the superiority of the proposed method over the other four commonly used anomaly detection methods: Z-score, isolation forest, local outlier factor, and seasonal hybrid ESD (Extreme Studentized Deviate test). •An anomaly detection method based on an asymmetric encoder-decoder model is proposed.•The method applies to hourly water demand data which exhibit trend and seasonality.•A cluster-based metric is proposed for model evaluation.•The metric considers the continuity mechanism of anomalies found in the data.•Measures to quantify the strengths of different components in the data are proposed.
AbstractList Water demand forecasting (WDF) is essential for the design and optimal management of water distribution systems (WDS). Historical water demand data contribute significantly to WDF. Yet the obtained water demand data contain anomalies on occasions due to failures in WDS or monitoring systems. The contaminated water demand data are invalid to describe the actual water demand, thus degrading the performance of WDF models. However, the importance of anomaly detection in water demand data is underestimated, or at least not explicitly described in many published papers. To fill the gap, we propose an unsupervised anomaly detection method based on an asymmetric encoder–decoder (asyED) model. Different from the symmetric structure of a traditional autoencoder where a signal is reproduced from itself, asyED is asymmetric where a signal is reproduced from the upstream and downstream information of the signal, while the signal itself does not participate in the reconstruction. In light of this feature, asyED is powerful in identifying anomalies. The proposed method is employed to detect anomalies in hourly water demand data which exhibit trend and seasonality. The results show the superiority of the proposed method over the other four commonly used anomaly detection methods: Z-score, isolation forest, local outlier factor, and seasonal hybrid ESD (Extreme Studentized Deviate test). •An anomaly detection method based on an asymmetric encoder-decoder model is proposed.•The method applies to hourly water demand data which exhibit trend and seasonality.•A cluster-based metric is proposed for model evaluation.•The metric considers the continuity mechanism of anomalies found in the data.•Measures to quantify the strengths of different components in the data are proposed.
Water demand forecasting (WDF) is essential for the design and optimal management of water distribution systems (WDS). Historical water demand data contribute significantly to WDF. Yet the obtained water demand data contain anomalies on occasions due to failures in WDS or monitoring systems. The contaminated water demand data are invalid to describe the actual water demand, thus degrading the performance of WDF models. However, the importance of anomaly detection in water demand data is underestimated, or at least not explicitly described in many published papers. To fill the gap, we propose an unsupervised anomaly detection method based on an asymmetric encoder–decoder (asyED) model. Different from the symmetric structure of a traditional autoencoder where a signal is reproduced from itself, asyED is asymmetric where a signal is reproduced from the upstream and downstream information of the signal, while the signal itself does not participate in the reconstruction. In light of this feature, asyED is powerful in identifying anomalies. The proposed method is employed to detect anomalies in hourly water demand data which exhibit trend and seasonality. The results show the superiority of the proposed method over the other four commonly used anomaly detection methods: Z-score, isolation forest, local outlier factor, and seasonal hybrid ESD (Extreme Studentized Deviate test).
ArticleNumber 128389
Author Tao, Tao
Yan, Jieru
Author_xml – sequence: 1
  givenname: Jieru
  orcidid: 0000-0003-1073-5396
  surname: Yan
  fullname: Yan, Jieru
  email: yan_jieru@tongji.edu.cn
– sequence: 2
  givenname: Tao
  orcidid: 0000-0003-4214-7097
  surname: Tao
  fullname: Tao, Tao
  email: taotao@tongji.edu.cn
BookMark eNqFkEtuHCEQhlFkSxk_jhCJZTY94THd0Moiiqw4sWQpm3iNylDYjLphArSj2fkOuWFOEibjVTZmASWqvl-q74ycxBSRkHecrTnjw4ftevu4dzlNa8GEWHOhpR7fkBXXauyEYuqErFjrdHwYN2_JWSlb1o6UmxXxd7EsO8xPoaCjENMM0546rGhrSJGGSB_TktvfL6iYW2eG6KiDCnQpIT40hkLZzzPWHCzFaJPD_Of5t8N_FZ3bPV2QUw9TwcuX95zcXX_5cfWtu_3-9ebq821nhRK1U5Ip5pUbhbC97jX2sh88unGEQWjmUQIX9wy47YW196MWA3pQVkvrwW96eU7eH3N3Of1csFQzh2JxmiBiWooRimuphmHD2-jH46jNqZSM3thQ4bB0zRAmw5k52DVb82LXHOyao91G9__RuxxmyPtXuU9HDpuFp4DZFBuaNHQhN-XGpfBKwl9jQZz4
CitedBy_id crossref_primary_10_1016_j_jwpe_2025_108207
crossref_primary_10_1016_j_autcon_2024_105794
crossref_primary_10_1016_j_jenvman_2024_120496
crossref_primary_10_1177_14759217251372614
crossref_primary_10_1016_j_jhydrol_2024_132599
crossref_primary_10_1016_j_nucengdes_2024_113493
crossref_primary_10_1061_JPSEA2_PSENG_1589
Cites_doi 10.1002/2017WR022007
10.1061/(ASCE)HE.1943-5584.0000182
10.1145/2133360.2133363
10.1061/(ASCE)WR.1943-5452.0001276
10.3390/w13050582
10.1061/(ASCE)WR.1943-5452.0001535
10.1147/JRD.2009.5429018
10.1061/(ASCE)WR.1943-5452.0000992
10.1061/(ASCE)WR.1943-5452.0000983
10.1080/00401706.1983.10487848
10.1145/3444690
10.1155/2019/9765468
10.1007/s11269-021-02808-4
10.1145/335191.335388
10.1029/2009WR008147
10.1007/s10115-006-0026-6
10.3758/BRM.38.2.344
10.1016/j.envsoft.2014.06.016
10.1016/j.cam.2016.02.009
10.1016/j.patcog.2018.11.019
10.1038/nmeth.3945
10.1016/j.jhydrol.2010.04.005
10.1016/j.jhydrol.2021.126353
10.1016/j.jhydrol.2022.127440
ContentType Journal Article
Copyright 2022 Elsevier B.V.
Copyright_xml – notice: 2022 Elsevier B.V.
DBID AAYXX
CITATION
7S9
L.6
DOI 10.1016/j.jhydrol.2022.128389
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_2022_128389
S002216942200957X
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-c272t-73070f7d922c5858e5356fed99a6280fe3a12b0a1c52ccb9826efa7c83cfaf453
ISICitedReferencesCount 9
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000862204200001&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 Sun Sep 28 02:16:03 EDT 2025
Sat Nov 29 07:27:50 EST 2025
Tue Nov 18 21:59:35 EST 2025
Fri Feb 23 02:38:42 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Hourly water demand
Asymmetric encoder–decoder
Autoencoder
Anomaly detection
Time series
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c272t-73070f7d922c5858e5356fed99a6280fe3a12b0a1c52ccb9826efa7c83cfaf453
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0003-4214-7097
0000-0003-1073-5396
PQID 2718376641
PQPubID 24069
ParticipantIDs proquest_miscellaneous_2718376641
crossref_citationtrail_10_1016_j_jhydrol_2022_128389
crossref_primary_10_1016_j_jhydrol_2022_128389
elsevier_sciencedirect_doi_10_1016_j_jhydrol_2022_128389
PublicationCentury 2000
PublicationDate October 2022
2022-10-00
20221001
PublicationDateYYYYMMDD 2022-10-01
PublicationDate_xml – month: 10
  year: 2022
  text: October 2022
PublicationDecade 2020
PublicationTitle Journal of hydrology (Amsterdam)
PublicationYear 2022
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Guo, Liu, Wu, Li, Zhou, Zhu (b16) 2018; 144
Lempitsky (b22) 2021
An, Cho (b2) 2015
Breunig, Kriegel, Ng, Sander (b7) 2000; 29
Mehrang, Helander, Pavel, Chieh, Korhonen (b26) 2015
Carrera, Rossi, Fragneto, Boracchi (b10) 2019; 88
Liu, Ting, Zhou (b25) 2012; 6
Chen, Boccelli (b12) 2018; 54
Chen, Yan, Yan, Wang, Tao, Xin, Li, Pu, Qiu (b13) 2022; 606
Hochenbaum, Vallis, Kejariwal (b18) 2017
Lever, Krzywinski, Altman (b23) 2016; 13
Thompson (b33) 2006; 38
Lecun (b21) 1987
Herrera, Torgo, Izquierdo, Pérez-García (b17) 2010; 387
Blázquez-García, Conde, Mori, Lozano (b5) 2021; 54
Brentan, Luvizotto Jr., Herrera, Izquierdo, Pérez-García (b6) 2017; 309
Huang, Zhang, Song (b20) 2021; 35
Salloom, Kaynak, He (b31) 2021; 599
Carter, Streilein (b11) 2012
Hu, Gao, Zhong, Deng, Ou, Xin (b19) 2021; 13
Wong, Zhang, Chen (b34) 2010; 46
Basu, Meckesheimer (b4) 2007; 11
Yan (b35) 2022
Bunn, Reynolds (b8) 2009; 53
Liu, Ting, Zhou (b24) 2008
Mu, Zheng, Tao, Zhang, Kapelan (b27) 2020; 146
Romano, Kapelan (b29) 2014; 60
Daniel, Pesantez, Letzgus, Fasaee, Alghamdi, Berglund, Mahinthakumar, Cominola (b15) 2022; 148
Cleveland, Cleveland, McRae, Terpenning (b14) 1990
Rosner (b30) 1983; 25
Ambrosio, Brentan, Herrera, Luvizotto, Ribeiro, Izquierdo (b1) 2019
Caiado (b9) 2010; 15
Arandia, Ba, Eck, McKenna (b3) 2015; 142
Reddy, Ordway-West, Lee, Dugan, Whitney, Kahana, Ford, Muedsam, Henslee, Rao (b28) 2017
Taormina, Galelli (b32) 2018; 144
Caiado (10.1016/j.jhydrol.2022.128389_b9) 2010; 15
Herrera (10.1016/j.jhydrol.2022.128389_b17) 2010; 387
Reddy (10.1016/j.jhydrol.2022.128389_b28) 2017
Blázquez-García (10.1016/j.jhydrol.2022.128389_b5) 2021; 54
Hu (10.1016/j.jhydrol.2022.128389_b19) 2021; 13
Mu (10.1016/j.jhydrol.2022.128389_b27) 2020; 146
Mehrang (10.1016/j.jhydrol.2022.128389_b26) 2015
Wong (10.1016/j.jhydrol.2022.128389_b34) 2010; 46
Huang (10.1016/j.jhydrol.2022.128389_b20) 2021; 35
Liu (10.1016/j.jhydrol.2022.128389_b24) 2008
Guo (10.1016/j.jhydrol.2022.128389_b16) 2018; 144
Brentan (10.1016/j.jhydrol.2022.128389_b6) 2017; 309
Cleveland (10.1016/j.jhydrol.2022.128389_b14) 1990
Romano (10.1016/j.jhydrol.2022.128389_b29) 2014; 60
Yan (10.1016/j.jhydrol.2022.128389_b35) 2022
Ambrosio (10.1016/j.jhydrol.2022.128389_b1) 2019
Hochenbaum (10.1016/j.jhydrol.2022.128389_b18) 2017
Breunig (10.1016/j.jhydrol.2022.128389_b7) 2000; 29
Chen (10.1016/j.jhydrol.2022.128389_b12) 2018; 54
Chen (10.1016/j.jhydrol.2022.128389_b13) 2022; 606
Rosner (10.1016/j.jhydrol.2022.128389_b30) 1983; 25
Bunn (10.1016/j.jhydrol.2022.128389_b8) 2009; 53
Carrera (10.1016/j.jhydrol.2022.128389_b10) 2019; 88
Lecun (10.1016/j.jhydrol.2022.128389_b21) 1987
An (10.1016/j.jhydrol.2022.128389_b2) 2015
Thompson (10.1016/j.jhydrol.2022.128389_b33) 2006; 38
Taormina (10.1016/j.jhydrol.2022.128389_b32) 2018; 144
Daniel (10.1016/j.jhydrol.2022.128389_b15) 2022; 148
Lempitsky (10.1016/j.jhydrol.2022.128389_b22) 2021
Salloom (10.1016/j.jhydrol.2022.128389_b31) 2021; 599
Liu (10.1016/j.jhydrol.2022.128389_b25) 2012; 6
Lever (10.1016/j.jhydrol.2022.128389_b23) 2016; 13
Arandia (10.1016/j.jhydrol.2022.128389_b3) 2015; 142
Basu (10.1016/j.jhydrol.2022.128389_b4) 2007; 11
Carter (10.1016/j.jhydrol.2022.128389_b11) 2012
References_xml – volume: 60
  start-page: 265
  year: 2014
  end-page: 276
  ident: b29
  article-title: Adaptive water demand forecasting for near real-time management of smart water distribution systems
  publication-title: Environ. Model. Softw.
– volume: 29
  start-page: 93
  year: 2000
  end-page: 104
  ident: b7
  article-title: LOF: identifying density-based local outliers
  publication-title: ACM SIGMOD Rec.
– year: 2015
  ident: b2
  article-title: Variational autoencoder based anomaly detection using reconstruction probability
– start-page: 1489
  year: 2015
  end-page: 1496
  ident: b26
  article-title: Outlier detection in weight time series of connected scales
  publication-title: 2015 IEEE International Conference on Bioinformatics and Biomedicine
– volume: 54
  start-page: 1
  year: 2021
  end-page: 33
  ident: b5
  article-title: A review on outlier/anomaly detection in time series data
  publication-title: ACM Comput. Surv.
– volume: 53
  start-page: 5:1
  year: 2009
  end-page: 5:13
  ident: b8
  article-title: The energy-efficiency benefits of pump-scheduling optimization for potable water supplies
  publication-title: IBM J. Res. Dev.
– volume: 25
  start-page: 165
  year: 1983
  end-page: 172
  ident: b30
  article-title: Percentage points for a generalized ESD many-outlier procedure
  publication-title: Technometrics
– year: 2019
  ident: b1
  article-title: Committee machines for hourly water demand forecasting in water supply systems
  publication-title: Math. Probl. Eng.
– volume: 15
  start-page: 215
  year: 2010
  end-page: 222
  ident: b9
  article-title: Performance of combined double seasonal univariate time series models for forecasting water demand
  publication-title: J. Hydrol. Eng.
– start-page: 68
  year: 2021
  end-page: 73
  ident: b22
  article-title: Autoencoder
  publication-title: Computer Vision: A Reference Guide
– volume: 11
  start-page: 137
  year: 2007
  end-page: 154
  ident: b4
  article-title: Automatic outlier detection for time series: an application to sensor data
  publication-title: Knowl. Inf. Syst.
– year: 2022
  ident: b35
  article-title: Test datasets for the paper ”unsupervised anomaly detection in hourly water demand data using an asymmetric encoder-decoder model”
– start-page: 413
  year: 2008
  end-page: 422
  ident: b24
  article-title: Isolation forest
  publication-title: 2008 Eighth IEEE International Conference on Data Mining
– volume: 54
  start-page: 879
  year: 2018
  end-page: 894
  ident: b12
  article-title: Forecasting hourly water demands with seasonal autoregressive models for real-time application
  publication-title: Water Resour. Res.
– volume: 148
  year: 2022
  ident: b15
  article-title: A sequential pressure-based algorithm for data-driven leakage identification and model-based localization in water distribution networks
  publication-title: J. Water Resour. Plan. Manage.
– volume: 387
  start-page: 141
  year: 2010
  end-page: 150
  ident: b17
  article-title: Predictive models for forecasting hourly urban water demand
  publication-title: J. Hydrol.
– volume: 88
  start-page: 482
  year: 2019
  end-page: 492
  ident: b10
  article-title: Online anomaly detection for long-term ECG monitoring using wearable devices
  publication-title: Pattern Recognit.
– volume: 142
  year: 2015
  ident: b3
  article-title: Tailoring seasonal time series models to forecast short-term water demand
  publication-title: J. Water Resour. Plan. Manage.
– year: 2017
  ident: b18
  article-title: Automatic anomaly detection in the cloud via statistical learning
– volume: 13
  start-page: 603
  year: 2016
  end-page: 604
  ident: b23
  article-title: Classification evaluation
  publication-title: Nature Methods
– volume: 144
  year: 2018
  ident: b32
  article-title: Deep-learning approach to the detection and localization of cyber-physical attacks on water distribution systems
  publication-title: J. Water Resour. Plan. Manage.
– year: 1990
  ident: b14
  article-title: STL: A seasonal-trend decomposition procedure based on loess (with discussion)
– volume: 599
  year: 2021
  ident: b31
  article-title: A novel deep neural network architecture for real-time water demand forecasting
  publication-title: J. Hydrol.
– volume: 13
  year: 2021
  ident: b19
  article-title: An innovative hourly water demand forecasting preprocessing framework with local outlier correction and adaptive decomposition techniques
  publication-title: Water
– volume: 309
  start-page: 532
  year: 2017
  end-page: 541
  ident: b6
  article-title: Hybrid regression model for near real-time urban water demand forecasting
  publication-title: J. Comput. Appl. Math.
– volume: 6
  start-page: 1
  year: 2012
  end-page: 39
  ident: b25
  article-title: Isolation-based anomaly detection
  publication-title: ACM Trans. Knowl. Discov. Data
– volume: 144
  year: 2018
  ident: b16
  article-title: Short-term water demand forecast based on deep learning method
  publication-title: J. Water Resour. Plan. Manage.
– year: 2017
  ident: b28
  article-title: Using Gaussian mixture models to detect outliers in seasonal univariate network traffic
– year: 1987
  ident: b21
  article-title: Modeles Connexionnistes de L’Apprentissage (Connectionist Learning Models)
– volume: 35
  year: 2021
  ident: b20
  article-title: An ensemble-learning-based method for short-term water demand forecasting
  publication-title: Water Resour. Manage.
– start-page: 377
  year: 2012
  end-page: 380
  ident: b11
  article-title: Probabilistic Reasoning for Streaming Anomaly Detection
– volume: 146
  year: 2020
  ident: b27
  article-title: Hourly and daily urban water demand predictions using a long short-term memory based model
  publication-title: J. Water Resour. Plan. Manage.
– volume: 46
  year: 2010
  ident: b34
  article-title: Statistical modeling of daily urban water consumption in Hong Kong: Trend, changing patterns, and forecast
  publication-title: Water Resour. Res.
– volume: 38
  start-page: 344
  year: 2006
  end-page: 352
  ident: b33
  article-title: An SPSS implementation of the nonrecursive outlier deletion procedure with shifting z score criterion (Van Seist & Jolicøur, 1994)
  publication-title: Behav. Res. Methods
– volume: 606
  year: 2022
  ident: b13
  article-title: Short-term water demand forecast based on automatic feature extraction by one-dimensional convolution
  publication-title: J. Hydrol.
– start-page: 1489
  year: 2015
  ident: 10.1016/j.jhydrol.2022.128389_b26
  article-title: Outlier detection in weight time series of connected scales
– volume: 54
  start-page: 879
  issue: 2
  year: 2018
  ident: 10.1016/j.jhydrol.2022.128389_b12
  article-title: Forecasting hourly water demands with seasonal autoregressive models for real-time application
  publication-title: Water Resour. Res.
  doi: 10.1002/2017WR022007
– start-page: 413
  year: 2008
  ident: 10.1016/j.jhydrol.2022.128389_b24
  article-title: Isolation forest
– volume: 15
  start-page: 215
  issue: 3
  year: 2010
  ident: 10.1016/j.jhydrol.2022.128389_b9
  article-title: Performance of combined double seasonal univariate time series models for forecasting water demand
  publication-title: J. Hydrol. Eng.
  doi: 10.1061/(ASCE)HE.1943-5584.0000182
– volume: 6
  start-page: 1
  issue: 1
  year: 2012
  ident: 10.1016/j.jhydrol.2022.128389_b25
  article-title: Isolation-based anomaly detection
  publication-title: ACM Trans. Knowl. Discov. Data
  doi: 10.1145/2133360.2133363
– year: 2015
  ident: 10.1016/j.jhydrol.2022.128389_b2
– volume: 146
  issue: 9
  year: 2020
  ident: 10.1016/j.jhydrol.2022.128389_b27
  article-title: Hourly and daily urban water demand predictions using a long short-term memory based model
  publication-title: J. Water Resour. Plan. Manage.
  doi: 10.1061/(ASCE)WR.1943-5452.0001276
– year: 1987
  ident: 10.1016/j.jhydrol.2022.128389_b21
– volume: 13
  issue: 5
  year: 2021
  ident: 10.1016/j.jhydrol.2022.128389_b19
  article-title: An innovative hourly water demand forecasting preprocessing framework with local outlier correction and adaptive decomposition techniques
  publication-title: Water
  doi: 10.3390/w13050582
– volume: 148
  issue: 6
  year: 2022
  ident: 10.1016/j.jhydrol.2022.128389_b15
  article-title: A sequential pressure-based algorithm for data-driven leakage identification and model-based localization in water distribution networks
  publication-title: J. Water Resour. Plan. Manage.
  doi: 10.1061/(ASCE)WR.1943-5452.0001535
– start-page: 68
  year: 2021
  ident: 10.1016/j.jhydrol.2022.128389_b22
  article-title: Autoencoder
– volume: 53
  start-page: 5:1
  issue: 3
  year: 2009
  ident: 10.1016/j.jhydrol.2022.128389_b8
  article-title: The energy-efficiency benefits of pump-scheduling optimization for potable water supplies
  publication-title: IBM J. Res. Dev.
  doi: 10.1147/JRD.2009.5429018
– year: 2022
  ident: 10.1016/j.jhydrol.2022.128389_b35
– year: 2017
  ident: 10.1016/j.jhydrol.2022.128389_b18
– volume: 144
  issue: 12
  year: 2018
  ident: 10.1016/j.jhydrol.2022.128389_b16
  article-title: Short-term water demand forecast based on deep learning method
  publication-title: J. Water Resour. Plan. Manage.
  doi: 10.1061/(ASCE)WR.1943-5452.0000992
– volume: 144
  issue: 10
  year: 2018
  ident: 10.1016/j.jhydrol.2022.128389_b32
  article-title: Deep-learning approach to the detection and localization of cyber-physical attacks on water distribution systems
  publication-title: J. Water Resour. Plan. Manage.
  doi: 10.1061/(ASCE)WR.1943-5452.0000983
– volume: 25
  start-page: 165
  issue: 2
  year: 1983
  ident: 10.1016/j.jhydrol.2022.128389_b30
  article-title: Percentage points for a generalized ESD many-outlier procedure
  publication-title: Technometrics
  doi: 10.1080/00401706.1983.10487848
– year: 2017
  ident: 10.1016/j.jhydrol.2022.128389_b28
– volume: 54
  start-page: 1
  year: 2021
  ident: 10.1016/j.jhydrol.2022.128389_b5
  article-title: A review on outlier/anomaly detection in time series data
  publication-title: ACM Comput. Surv.
  doi: 10.1145/3444690
– year: 2019
  ident: 10.1016/j.jhydrol.2022.128389_b1
  article-title: Committee machines for hourly water demand forecasting in water supply systems
  publication-title: Math. Probl. Eng.
  doi: 10.1155/2019/9765468
– volume: 35
  year: 2021
  ident: 10.1016/j.jhydrol.2022.128389_b20
  article-title: An ensemble-learning-based method for short-term water demand forecasting
  publication-title: Water Resour. Manage.
  doi: 10.1007/s11269-021-02808-4
– volume: 29
  start-page: 93
  year: 2000
  ident: 10.1016/j.jhydrol.2022.128389_b7
  article-title: LOF: identifying density-based local outliers
  publication-title: ACM SIGMOD Rec.
  doi: 10.1145/335191.335388
– volume: 46
  issue: 3
  year: 2010
  ident: 10.1016/j.jhydrol.2022.128389_b34
  article-title: Statistical modeling of daily urban water consumption in Hong Kong: Trend, changing patterns, and forecast
  publication-title: Water Resour. Res.
  doi: 10.1029/2009WR008147
– volume: 11
  start-page: 137
  issue: 2
  year: 2007
  ident: 10.1016/j.jhydrol.2022.128389_b4
  article-title: Automatic outlier detection for time series: an application to sensor data
  publication-title: Knowl. Inf. Syst.
  doi: 10.1007/s10115-006-0026-6
– year: 1990
  ident: 10.1016/j.jhydrol.2022.128389_b14
– start-page: 377
  year: 2012
  ident: 10.1016/j.jhydrol.2022.128389_b11
– volume: 38
  start-page: 344
  year: 2006
  ident: 10.1016/j.jhydrol.2022.128389_b33
  article-title: An SPSS implementation of the nonrecursive outlier deletion procedure with shifting z score criterion (Van Seist & Jolicøur, 1994)
  publication-title: Behav. Res. Methods
  doi: 10.3758/BRM.38.2.344
– volume: 60
  start-page: 265
  year: 2014
  ident: 10.1016/j.jhydrol.2022.128389_b29
  article-title: Adaptive water demand forecasting for near real-time management of smart water distribution systems
  publication-title: Environ. Model. Softw.
  doi: 10.1016/j.envsoft.2014.06.016
– volume: 309
  start-page: 532
  year: 2017
  ident: 10.1016/j.jhydrol.2022.128389_b6
  article-title: Hybrid regression model for near real-time urban water demand forecasting
  publication-title: J. Comput. Appl. Math.
  doi: 10.1016/j.cam.2016.02.009
– volume: 88
  start-page: 482
  year: 2019
  ident: 10.1016/j.jhydrol.2022.128389_b10
  article-title: Online anomaly detection for long-term ECG monitoring using wearable devices
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2018.11.019
– volume: 142
  year: 2015
  ident: 10.1016/j.jhydrol.2022.128389_b3
  article-title: Tailoring seasonal time series models to forecast short-term water demand
  publication-title: J. Water Resour. Plan. Manage.
– volume: 13
  start-page: 603
  issue: 8
  year: 2016
  ident: 10.1016/j.jhydrol.2022.128389_b23
  article-title: Classification evaluation
  publication-title: Nature Methods
  doi: 10.1038/nmeth.3945
– volume: 387
  start-page: 141
  issue: 1
  year: 2010
  ident: 10.1016/j.jhydrol.2022.128389_b17
  article-title: Predictive models for forecasting hourly urban water demand
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2010.04.005
– volume: 599
  year: 2021
  ident: 10.1016/j.jhydrol.2022.128389_b31
  article-title: A novel deep neural network architecture for real-time water demand forecasting
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2021.126353
– volume: 606
  year: 2022
  ident: 10.1016/j.jhydrol.2022.128389_b13
  article-title: Short-term water demand forecast based on automatic feature extraction by one-dimensional convolution
  publication-title: J. Hydrol.
  doi: 10.1016/j.jhydrol.2022.127440
SSID ssj0000334
Score 2.4449258
Snippet Water demand forecasting (WDF) is essential for the design and optimal management of water distribution systems (WDS). Historical water demand data contribute...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 128389
SubjectTerms Anomaly detection
Asymmetric encoder–decoder
Autoencoder
forests
Hourly water demand
hybrids
hydrology
Time series
water distribution
water pollution
Title Unsupervised anomaly detection in hourly water demand data using an asymmetric encoder–decoder model
URI https://dx.doi.org/10.1016/j.jhydrol.2022.128389
https://www.proquest.com/docview/2718376641
Volume 613
WOSCitedRecordID wos000862204200001&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/eLvHCXMwtV1LbxMxELagRYIL4qm2PGQkbtGGrL27to8RKoIeKg6tFE4rxw-lUXcTZbO0ufEf-If8EsZr724olNIDl03WiSdW5svMeDKeD6G3nCuqU6siIZmJEilEJONMRkQRw60ynGvZkE2w42M-mYjPoWysaugEWFnyy0ux_K-qhjFQtjs6ewt1d0JhAJ6D0uEKaofrPyn-tKzqpbMAlXFtWBeFPN8MtFkb1dY1zkAMjF1ITw9euNy5qxQd1JU_sjiQ1aYoHNeWGrhGl67JSCiKoNo0955C55rQdrbRK9_bCeLXceF6MWgHvC7p8MWnXY_AJ9d97qDJ2sLDdiYCNrFtTdv2yYA486TFrXXNYrplH8EbUk8Z9Jvp9lmE-XDu1zh0nzDs3_9rq-wrLqwrLGxr1uZ5EJM7MbkXcxftEpYKsH2740-Hk6PeY1OatF3l3fr7k17v_rie62KYK968CVFOHqGHQQF47DHxGN0x5RN0P9DczzZPkd3GBg7YwB028FmJPTZwgw3ssYEdNnCDDZiDe2zggI0f374HVOAGFc_Q6YfDk_cfo0C0ESnCyDpizvBbpgUhCraP3KQ0zazRQsiM8JE1VMZkOpKxSolSUwFbUmMlU5wqK22S0udop1yUZg_hVIPHkPCyTUeJJWKqIWA1AAKpTZKM2D5K2q8uV6ELvSNDOc__qrp9NOymLX0blpsm8FYveYglfYyYA95umvqm1WMOttb9gSZLs6irnEAgBw45S-KD267nBXrQ_2Reop31qjav0D31dX1WrV4HQP4EBO2oNg
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=Unsupervised+anomaly+detection+in+hourly+water+demand+data+using+an+asymmetric+encoder%E2%80%93decoder+model&rft.jtitle=Journal+of+hydrology+%28Amsterdam%29&rft.au=Yan%2C+Jieru&rft.au=Tao%2C+Tao&rft.date=2022-10-01&rft.issn=0022-1694&rft.volume=613&rft.spage=128389&rft_id=info:doi/10.1016%2Fj.jhydrol.2022.128389&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_jhydrol_2022_128389
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