Deep learning-based uncertainty quantification of groundwater level predictions

Due to the underlying uncertainty in the groundwater level (GWL) modeling, point prediction of the GWLs does not provide sufficient information for decision making and management purposes. Thus, estimating prediction intervals (PIs) for groundwater modeling can be an important step in sustainable wa...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Stochastic environmental research and risk assessment 2022-10, Vol.36 (10), p.3081-3107
Hauptverfasser: Nourani, Vahid, Khodkar, Kasra, Paknezhad, Nardin Jabbarian, Laux, Patrick
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 3107
container_issue 10
container_start_page 3081
container_title Stochastic environmental research and risk assessment
container_volume 36
creator Nourani, Vahid
Khodkar, Kasra
Paknezhad, Nardin Jabbarian
Laux, Patrick
description Due to the underlying uncertainty in the groundwater level (GWL) modeling, point prediction of the GWLs does not provide sufficient information for decision making and management purposes. Thus, estimating prediction intervals (PIs) for groundwater modeling can be an important step in sustainable water resources management. In this paper, PIs were estimated for GWL of selected piezometers of the Ardebil plain located in northwest of Iran and the Qorveh–Dehgolan plain located in west of Iran, using bootstrap methods based on artificial neural networks (ANNs). For this purpose, the classic feedforward neural network (FFNN) and deep learning (DL)-based long short-term memory (LSTM) were used as ANN bases and the classic bootstrap and moving blocks bootstrap (MBB) as the bootstrap variations. Monthly GWL data of some piezometers as well as hydrologic data of the related stations from both plains were used for the training and validation of the models. The results showed that the LSTM outperforms the seasonal auto regressive integrated moving average model with exogeneous data (SARIMAX), which is a linear model, and classic FFNN in point prediction task. Moreover, in terms of PIs model performance, the LSTM-based MBB (MBLSTM) achieved an average of 30% lower coverage width criterion (CWC) than the FFNN-based MBB (MBFN) and average of 40% lower CWC than the FFNN-based classic bootstrap (BFN). In addition, PIs estimated for piezometers situated in areas with high transmissivity resulted in 55% lower CWC than PIs estimated for piezometers, which are located in areas with lower transmissivity.
doi_str_mv 10.1007/s00477-022-02181-7
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2721466346</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2721466346</sourcerecordid><originalsourceid>FETCH-LOGICAL-c319t-c96a0f6940aaeeb543185574c2ce1f75a4185544e6f6de18df25d9b05cd8947e3</originalsourceid><addsrcrecordid>eNp9kE1LAzEQhoMoWGr_gKcFz6v5zuYo9RMKveg5ZLOTEqnZNtlV-u9NXdGbh2FmmPd5B16ELgm-Jhirm4wxV6rGlJYiDanVCZoRzmTNqNCnvzPH52iRc2gLJJjWBM_Q-g5gV23Bphjipm5thq4ao4M02BCHQ7UfbRyCD84OoY9V76tN6sfYfdoBUgE_YFvtEnTBHe_5Ap15u82w-Olz9Ppw_7J8qlfrx-fl7ap2jOihdlpa7KXm2FqAVnBGGiEUd9QB8UpYftw5B-llB6TpPBWdbrFwXaO5AjZHV5PvLvX7EfJg3voxxfLSUEUJl5JxWVR0UrnU55zAm10K7zYdDMHmmJ2ZsjMlO_OdnVEFYhOUizhuIP1Z_0N9AeQGcnQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2721466346</pqid></control><display><type>article</type><title>Deep learning-based uncertainty quantification of groundwater level predictions</title><source>SpringerNature Journals</source><creator>Nourani, Vahid ; Khodkar, Kasra ; Paknezhad, Nardin Jabbarian ; Laux, Patrick</creator><creatorcontrib>Nourani, Vahid ; Khodkar, Kasra ; Paknezhad, Nardin Jabbarian ; Laux, Patrick</creatorcontrib><description>Due to the underlying uncertainty in the groundwater level (GWL) modeling, point prediction of the GWLs does not provide sufficient information for decision making and management purposes. Thus, estimating prediction intervals (PIs) for groundwater modeling can be an important step in sustainable water resources management. In this paper, PIs were estimated for GWL of selected piezometers of the Ardebil plain located in northwest of Iran and the Qorveh–Dehgolan plain located in west of Iran, using bootstrap methods based on artificial neural networks (ANNs). For this purpose, the classic feedforward neural network (FFNN) and deep learning (DL)-based long short-term memory (LSTM) were used as ANN bases and the classic bootstrap and moving blocks bootstrap (MBB) as the bootstrap variations. Monthly GWL data of some piezometers as well as hydrologic data of the related stations from both plains were used for the training and validation of the models. The results showed that the LSTM outperforms the seasonal auto regressive integrated moving average model with exogeneous data (SARIMAX), which is a linear model, and classic FFNN in point prediction task. Moreover, in terms of PIs model performance, the LSTM-based MBB (MBLSTM) achieved an average of 30% lower coverage width criterion (CWC) than the FFNN-based MBB (MBFN) and average of 40% lower CWC than the FFNN-based classic bootstrap (BFN). In addition, PIs estimated for piezometers situated in areas with high transmissivity resulted in 55% lower CWC than PIs estimated for piezometers, which are located in areas with lower transmissivity.</description><identifier>ISSN: 1436-3240</identifier><identifier>EISSN: 1436-3259</identifier><identifier>DOI: 10.1007/s00477-022-02181-7</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Aquatic Pollution ; Artificial neural networks ; Chemistry and Earth Sciences ; Computational Intelligence ; Computer Science ; Decision making ; Deep learning ; Earth and Environmental Science ; Earth Sciences ; Environment ; Groundwater ; Groundwater levels ; Hydrologic data ; Hydrology ; Long short-term memory ; Math. Appl. in Environmental Science ; Modelling ; Neural networks ; Original Paper ; Physics ; Piezometers ; Predictions ; Probability Theory and Stochastic Processes ; Statistical methods ; Statistics for Engineering ; Transmissivity ; Uncertainty ; Waste Water Technology ; Water Management ; Water Pollution Control ; Water resources ; Water resources management</subject><ispartof>Stochastic environmental research and risk assessment, 2022-10, Vol.36 (10), p.3081-3107</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022</rights><rights>The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c319t-c96a0f6940aaeeb543185574c2ce1f75a4185544e6f6de18df25d9b05cd8947e3</citedby><cites>FETCH-LOGICAL-c319t-c96a0f6940aaeeb543185574c2ce1f75a4185544e6f6de18df25d9b05cd8947e3</cites><orcidid>0000-0002-6931-7060</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s00477-022-02181-7$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s00477-022-02181-7$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Nourani, Vahid</creatorcontrib><creatorcontrib>Khodkar, Kasra</creatorcontrib><creatorcontrib>Paknezhad, Nardin Jabbarian</creatorcontrib><creatorcontrib>Laux, Patrick</creatorcontrib><title>Deep learning-based uncertainty quantification of groundwater level predictions</title><title>Stochastic environmental research and risk assessment</title><addtitle>Stoch Environ Res Risk Assess</addtitle><description>Due to the underlying uncertainty in the groundwater level (GWL) modeling, point prediction of the GWLs does not provide sufficient information for decision making and management purposes. Thus, estimating prediction intervals (PIs) for groundwater modeling can be an important step in sustainable water resources management. In this paper, PIs were estimated for GWL of selected piezometers of the Ardebil plain located in northwest of Iran and the Qorveh–Dehgolan plain located in west of Iran, using bootstrap methods based on artificial neural networks (ANNs). For this purpose, the classic feedforward neural network (FFNN) and deep learning (DL)-based long short-term memory (LSTM) were used as ANN bases and the classic bootstrap and moving blocks bootstrap (MBB) as the bootstrap variations. Monthly GWL data of some piezometers as well as hydrologic data of the related stations from both plains were used for the training and validation of the models. The results showed that the LSTM outperforms the seasonal auto regressive integrated moving average model with exogeneous data (SARIMAX), which is a linear model, and classic FFNN in point prediction task. Moreover, in terms of PIs model performance, the LSTM-based MBB (MBLSTM) achieved an average of 30% lower coverage width criterion (CWC) than the FFNN-based MBB (MBFN) and average of 40% lower CWC than the FFNN-based classic bootstrap (BFN). In addition, PIs estimated for piezometers situated in areas with high transmissivity resulted in 55% lower CWC than PIs estimated for piezometers, which are located in areas with lower transmissivity.</description><subject>Aquatic Pollution</subject><subject>Artificial neural networks</subject><subject>Chemistry and Earth Sciences</subject><subject>Computational Intelligence</subject><subject>Computer Science</subject><subject>Decision making</subject><subject>Deep learning</subject><subject>Earth and Environmental Science</subject><subject>Earth Sciences</subject><subject>Environment</subject><subject>Groundwater</subject><subject>Groundwater levels</subject><subject>Hydrologic data</subject><subject>Hydrology</subject><subject>Long short-term memory</subject><subject>Math. Appl. in Environmental Science</subject><subject>Modelling</subject><subject>Neural networks</subject><subject>Original Paper</subject><subject>Physics</subject><subject>Piezometers</subject><subject>Predictions</subject><subject>Probability Theory and Stochastic Processes</subject><subject>Statistical methods</subject><subject>Statistics for Engineering</subject><subject>Transmissivity</subject><subject>Uncertainty</subject><subject>Waste Water Technology</subject><subject>Water Management</subject><subject>Water Pollution Control</subject><subject>Water resources</subject><subject>Water resources management</subject><issn>1436-3240</issn><issn>1436-3259</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp9kE1LAzEQhoMoWGr_gKcFz6v5zuYo9RMKveg5ZLOTEqnZNtlV-u9NXdGbh2FmmPd5B16ELgm-Jhirm4wxV6rGlJYiDanVCZoRzmTNqNCnvzPH52iRc2gLJJjWBM_Q-g5gV23Bphjipm5thq4ao4M02BCHQ7UfbRyCD84OoY9V76tN6sfYfdoBUgE_YFvtEnTBHe_5Ap15u82w-Olz9Ppw_7J8qlfrx-fl7ap2jOihdlpa7KXm2FqAVnBGGiEUd9QB8UpYftw5B-llB6TpPBWdbrFwXaO5AjZHV5PvLvX7EfJg3voxxfLSUEUJl5JxWVR0UrnU55zAm10K7zYdDMHmmJ2ZsjMlO_OdnVEFYhOUizhuIP1Z_0N9AeQGcnQ</recordid><startdate>20221001</startdate><enddate>20221001</enddate><creator>Nourani, Vahid</creator><creator>Khodkar, Kasra</creator><creator>Paknezhad, Nardin Jabbarian</creator><creator>Laux, Patrick</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7ST</scope><scope>7XB</scope><scope>88I</scope><scope>8AO</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ATCPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BHPHI</scope><scope>C1K</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FR3</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>KR7</scope><scope>L6V</scope><scope>M2P</scope><scope>M7S</scope><scope>PATMY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope><scope>PYCSY</scope><scope>Q9U</scope><scope>S0W</scope><scope>SOI</scope><orcidid>https://orcid.org/0000-0002-6931-7060</orcidid></search><sort><creationdate>20221001</creationdate><title>Deep learning-based uncertainty quantification of groundwater level predictions</title><author>Nourani, Vahid ; Khodkar, Kasra ; Paknezhad, Nardin Jabbarian ; Laux, Patrick</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c319t-c96a0f6940aaeeb543185574c2ce1f75a4185544e6f6de18df25d9b05cd8947e3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Aquatic Pollution</topic><topic>Artificial neural networks</topic><topic>Chemistry and Earth Sciences</topic><topic>Computational Intelligence</topic><topic>Computer Science</topic><topic>Decision making</topic><topic>Deep learning</topic><topic>Earth and Environmental Science</topic><topic>Earth Sciences</topic><topic>Environment</topic><topic>Groundwater</topic><topic>Groundwater levels</topic><topic>Hydrologic data</topic><topic>Hydrology</topic><topic>Long short-term memory</topic><topic>Math. Appl. in Environmental Science</topic><topic>Modelling</topic><topic>Neural networks</topic><topic>Original Paper</topic><topic>Physics</topic><topic>Piezometers</topic><topic>Predictions</topic><topic>Probability Theory and Stochastic Processes</topic><topic>Statistical methods</topic><topic>Statistics for Engineering</topic><topic>Transmissivity</topic><topic>Uncertainty</topic><topic>Waste Water Technology</topic><topic>Water Management</topic><topic>Water Pollution Control</topic><topic>Water resources</topic><topic>Water resources management</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Nourani, Vahid</creatorcontrib><creatorcontrib>Khodkar, Kasra</creatorcontrib><creatorcontrib>Paknezhad, Nardin Jabbarian</creatorcontrib><creatorcontrib>Laux, Patrick</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Environment Abstracts</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Science Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Agricultural &amp; Environmental Science Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>Natural Science Collection</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>Civil Engineering Abstracts</collection><collection>ProQuest Engineering Collection</collection><collection>Science Database</collection><collection>Engineering Database</collection><collection>Environmental Science Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection><collection>Environmental Science Collection</collection><collection>ProQuest Central Basic</collection><collection>DELNET Engineering &amp; Technology Collection</collection><collection>Environment Abstracts</collection><jtitle>Stochastic environmental research and risk assessment</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Nourani, Vahid</au><au>Khodkar, Kasra</au><au>Paknezhad, Nardin Jabbarian</au><au>Laux, Patrick</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep learning-based uncertainty quantification of groundwater level predictions</atitle><jtitle>Stochastic environmental research and risk assessment</jtitle><stitle>Stoch Environ Res Risk Assess</stitle><date>2022-10-01</date><risdate>2022</risdate><volume>36</volume><issue>10</issue><spage>3081</spage><epage>3107</epage><pages>3081-3107</pages><issn>1436-3240</issn><eissn>1436-3259</eissn><abstract>Due to the underlying uncertainty in the groundwater level (GWL) modeling, point prediction of the GWLs does not provide sufficient information for decision making and management purposes. Thus, estimating prediction intervals (PIs) for groundwater modeling can be an important step in sustainable water resources management. In this paper, PIs were estimated for GWL of selected piezometers of the Ardebil plain located in northwest of Iran and the Qorveh–Dehgolan plain located in west of Iran, using bootstrap methods based on artificial neural networks (ANNs). For this purpose, the classic feedforward neural network (FFNN) and deep learning (DL)-based long short-term memory (LSTM) were used as ANN bases and the classic bootstrap and moving blocks bootstrap (MBB) as the bootstrap variations. Monthly GWL data of some piezometers as well as hydrologic data of the related stations from both plains were used for the training and validation of the models. The results showed that the LSTM outperforms the seasonal auto regressive integrated moving average model with exogeneous data (SARIMAX), which is a linear model, and classic FFNN in point prediction task. Moreover, in terms of PIs model performance, the LSTM-based MBB (MBLSTM) achieved an average of 30% lower coverage width criterion (CWC) than the FFNN-based MBB (MBFN) and average of 40% lower CWC than the FFNN-based classic bootstrap (BFN). In addition, PIs estimated for piezometers situated in areas with high transmissivity resulted in 55% lower CWC than PIs estimated for piezometers, which are located in areas with lower transmissivity.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s00477-022-02181-7</doi><tpages>27</tpages><orcidid>https://orcid.org/0000-0002-6931-7060</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1436-3240
ispartof Stochastic environmental research and risk assessment, 2022-10, Vol.36 (10), p.3081-3107
issn 1436-3240
1436-3259
language eng
recordid cdi_proquest_journals_2721466346
source SpringerNature Journals
subjects Aquatic Pollution
Artificial neural networks
Chemistry and Earth Sciences
Computational Intelligence
Computer Science
Decision making
Deep learning
Earth and Environmental Science
Earth Sciences
Environment
Groundwater
Groundwater levels
Hydrologic data
Hydrology
Long short-term memory
Math. Appl. in Environmental Science
Modelling
Neural networks
Original Paper
Physics
Piezometers
Predictions
Probability Theory and Stochastic Processes
Statistical methods
Statistics for Engineering
Transmissivity
Uncertainty
Waste Water Technology
Water Management
Water Pollution Control
Water resources
Water resources management
title Deep learning-based uncertainty quantification of groundwater level predictions
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T21%3A00%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20learning-based%20uncertainty%20quantification%20of%20groundwater%20level%20predictions&rft.jtitle=Stochastic%20environmental%20research%20and%20risk%20assessment&rft.au=Nourani,%20Vahid&rft.date=2022-10-01&rft.volume=36&rft.issue=10&rft.spage=3081&rft.epage=3107&rft.pages=3081-3107&rft.issn=1436-3240&rft.eissn=1436-3259&rft_id=info:doi/10.1007/s00477-022-02181-7&rft_dat=%3Cproquest_cross%3E2721466346%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2721466346&rft_id=info:pmid/&rfr_iscdi=true