A machine learning algorithm for predicting naturalized flow duration curves at human influenced sites and multiple catchment scales
Regional flow duration curves (FDCs) often reflect streamflow influenced by human activities. We propose a new machine learning algorithm to predict naturalized FDCs at human influenced sites and multiple catchment scales. Separate Meta models are developed to predict probable flow at discrete excee...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-09 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Friedel, Michael J Stewart, Dave Xiao Feng Lu Stevenson, Pete Manly, Helen Dyer, Tom |
description | Regional flow duration curves (FDCs) often reflect streamflow influenced by human activities. We propose a new machine learning algorithm to predict naturalized FDCs at human influenced sites and multiple catchment scales. Separate Meta models are developed to predict probable flow at discrete exceedance probabilities across catchments spanning multiple stream orders. Discrete exceedance flows reflect the stacking of k-fold cross-validated predictions from trained base ensemble machine learning models with and without hyperparameter tuning. The quality of individual base models reflects random stratified shuffling of spilt catchment records for training and testing. A Meta model is formed by retraining minimum variance base models that are bias corrected and used to predict final flows at selected percentiles that quantify uncertainty. Separate Meta models are developed and used to predict naturalised stochastic flows at other discrete exceedance probabilities along the duration curve. Efficacy of the new method is demonstrated for predicting naturalized stochastic FDCs at human influenced gauged catchments and ungauged stream reaches of unknown influences across Otago New Zealand. Important findings are twofold. First, independent observations of naturalised Median flows compare within few percent of the 50th percentile predictions from the FDC models. Second, the naturalised Meta models predict FDCs that outperform the calibrated SWAT model FDCs at gauge sites in the Taieri Freshwater Management Unit: Taieri at Tiroiti, Taieri at Sutton Creek, and Taieri River at Outram. Departures in the naturalised reference state are interpreted as flow regime changes across the duration curves. We believe these Meta models will be useful in predicting naturalised catchment FDCs across other New Zealand regions using physical catchment features available from the national data base. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3109530563</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3109530563</sourcerecordid><originalsourceid>FETCH-proquest_journals_31095305633</originalsourceid><addsrcrecordid>eNqNysFKAzEQxvEgFFps32HAcyFN3NoeRRQfwHsZsrPdlMlkm0wUPPvgbsEH8PTx8fvfmZXzfrc9PDq3NJtaL9Zat39yXedX5ucZEoYxCgETFolyBuRzLlHHBEMuMBXqY9AbCGoryPGbehg4f0E_X41ZILTySRVQYWwJBaIM3EjCHNaoN5EeUmONExME1DAmEoUakKmuzWJArrT523vz8Pb68fK-nUq-Nqp6uuRWZKaT39lj52239_5_1S83OlNp</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3109530563</pqid></control><display><type>article</type><title>A machine learning algorithm for predicting naturalized flow duration curves at human influenced sites and multiple catchment scales</title><source>Free E- Journals</source><creator>Friedel, Michael J ; Stewart, Dave ; Xiao Feng Lu ; Stevenson, Pete ; Manly, Helen ; Dyer, Tom</creator><creatorcontrib>Friedel, Michael J ; Stewart, Dave ; Xiao Feng Lu ; Stevenson, Pete ; Manly, Helen ; Dyer, Tom</creatorcontrib><description>Regional flow duration curves (FDCs) often reflect streamflow influenced by human activities. We propose a new machine learning algorithm to predict naturalized FDCs at human influenced sites and multiple catchment scales. Separate Meta models are developed to predict probable flow at discrete exceedance probabilities across catchments spanning multiple stream orders. Discrete exceedance flows reflect the stacking of k-fold cross-validated predictions from trained base ensemble machine learning models with and without hyperparameter tuning. The quality of individual base models reflects random stratified shuffling of spilt catchment records for training and testing. A Meta model is formed by retraining minimum variance base models that are bias corrected and used to predict final flows at selected percentiles that quantify uncertainty. Separate Meta models are developed and used to predict naturalised stochastic flows at other discrete exceedance probabilities along the duration curve. Efficacy of the new method is demonstrated for predicting naturalized stochastic FDCs at human influenced gauged catchments and ungauged stream reaches of unknown influences across Otago New Zealand. Important findings are twofold. First, independent observations of naturalised Median flows compare within few percent of the 50th percentile predictions from the FDC models. Second, the naturalised Meta models predict FDCs that outperform the calibrated SWAT model FDCs at gauge sites in the Taieri Freshwater Management Unit: Taieri at Tiroiti, Taieri at Sutton Creek, and Taieri River at Outram. Departures in the naturalised reference state are interpreted as flow regime changes across the duration curves. We believe these Meta models will be useful in predicting naturalised catchment FDCs across other New Zealand regions using physical catchment features available from the national data base.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Catchments ; Flow duration curves ; Machine learning ; Predictions ; Regional development</subject><ispartof>arXiv.org, 2024-09</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by-nc-sa/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Friedel, Michael J</creatorcontrib><creatorcontrib>Stewart, Dave</creatorcontrib><creatorcontrib>Xiao Feng Lu</creatorcontrib><creatorcontrib>Stevenson, Pete</creatorcontrib><creatorcontrib>Manly, Helen</creatorcontrib><creatorcontrib>Dyer, Tom</creatorcontrib><title>A machine learning algorithm for predicting naturalized flow duration curves at human influenced sites and multiple catchment scales</title><title>arXiv.org</title><description>Regional flow duration curves (FDCs) often reflect streamflow influenced by human activities. We propose a new machine learning algorithm to predict naturalized FDCs at human influenced sites and multiple catchment scales. Separate Meta models are developed to predict probable flow at discrete exceedance probabilities across catchments spanning multiple stream orders. Discrete exceedance flows reflect the stacking of k-fold cross-validated predictions from trained base ensemble machine learning models with and without hyperparameter tuning. The quality of individual base models reflects random stratified shuffling of spilt catchment records for training and testing. A Meta model is formed by retraining minimum variance base models that are bias corrected and used to predict final flows at selected percentiles that quantify uncertainty. Separate Meta models are developed and used to predict naturalised stochastic flows at other discrete exceedance probabilities along the duration curve. Efficacy of the new method is demonstrated for predicting naturalized stochastic FDCs at human influenced gauged catchments and ungauged stream reaches of unknown influences across Otago New Zealand. Important findings are twofold. First, independent observations of naturalised Median flows compare within few percent of the 50th percentile predictions from the FDC models. Second, the naturalised Meta models predict FDCs that outperform the calibrated SWAT model FDCs at gauge sites in the Taieri Freshwater Management Unit: Taieri at Tiroiti, Taieri at Sutton Creek, and Taieri River at Outram. Departures in the naturalised reference state are interpreted as flow regime changes across the duration curves. We believe these Meta models will be useful in predicting naturalised catchment FDCs across other New Zealand regions using physical catchment features available from the national data base.</description><subject>Algorithms</subject><subject>Catchments</subject><subject>Flow duration curves</subject><subject>Machine learning</subject><subject>Predictions</subject><subject>Regional development</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNysFKAzEQxvEgFFps32HAcyFN3NoeRRQfwHsZsrPdlMlkm0wUPPvgbsEH8PTx8fvfmZXzfrc9PDq3NJtaL9Zat39yXedX5ucZEoYxCgETFolyBuRzLlHHBEMuMBXqY9AbCGoryPGbehg4f0E_X41ZILTySRVQYWwJBaIM3EjCHNaoN5EeUmONExME1DAmEoUakKmuzWJArrT523vz8Pb68fK-nUq-Nqp6uuRWZKaT39lj52239_5_1S83OlNp</recordid><startdate>20240909</startdate><enddate>20240909</enddate><creator>Friedel, Michael J</creator><creator>Stewart, Dave</creator><creator>Xiao Feng Lu</creator><creator>Stevenson, Pete</creator><creator>Manly, Helen</creator><creator>Dyer, Tom</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240909</creationdate><title>A machine learning algorithm for predicting naturalized flow duration curves at human influenced sites and multiple catchment scales</title><author>Friedel, Michael J ; Stewart, Dave ; Xiao Feng Lu ; Stevenson, Pete ; Manly, Helen ; Dyer, Tom</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31095305633</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Catchments</topic><topic>Flow duration curves</topic><topic>Machine learning</topic><topic>Predictions</topic><topic>Regional development</topic><toplevel>online_resources</toplevel><creatorcontrib>Friedel, Michael J</creatorcontrib><creatorcontrib>Stewart, Dave</creatorcontrib><creatorcontrib>Xiao Feng Lu</creatorcontrib><creatorcontrib>Stevenson, Pete</creatorcontrib><creatorcontrib>Manly, Helen</creatorcontrib><creatorcontrib>Dyer, Tom</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content 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>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Friedel, Michael J</au><au>Stewart, Dave</au><au>Xiao Feng Lu</au><au>Stevenson, Pete</au><au>Manly, Helen</au><au>Dyer, Tom</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A machine learning algorithm for predicting naturalized flow duration curves at human influenced sites and multiple catchment scales</atitle><jtitle>arXiv.org</jtitle><date>2024-09-09</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Regional flow duration curves (FDCs) often reflect streamflow influenced by human activities. We propose a new machine learning algorithm to predict naturalized FDCs at human influenced sites and multiple catchment scales. Separate Meta models are developed to predict probable flow at discrete exceedance probabilities across catchments spanning multiple stream orders. Discrete exceedance flows reflect the stacking of k-fold cross-validated predictions from trained base ensemble machine learning models with and without hyperparameter tuning. The quality of individual base models reflects random stratified shuffling of spilt catchment records for training and testing. A Meta model is formed by retraining minimum variance base models that are bias corrected and used to predict final flows at selected percentiles that quantify uncertainty. Separate Meta models are developed and used to predict naturalised stochastic flows at other discrete exceedance probabilities along the duration curve. Efficacy of the new method is demonstrated for predicting naturalized stochastic FDCs at human influenced gauged catchments and ungauged stream reaches of unknown influences across Otago New Zealand. Important findings are twofold. First, independent observations of naturalised Median flows compare within few percent of the 50th percentile predictions from the FDC models. Second, the naturalised Meta models predict FDCs that outperform the calibrated SWAT model FDCs at gauge sites in the Taieri Freshwater Management Unit: Taieri at Tiroiti, Taieri at Sutton Creek, and Taieri River at Outram. Departures in the naturalised reference state are interpreted as flow regime changes across the duration curves. We believe these Meta models will be useful in predicting naturalised catchment FDCs across other New Zealand regions using physical catchment features available from the national data base.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2024-09 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_3109530563 |
source | Free E- Journals |
subjects | Algorithms Catchments Flow duration curves Machine learning Predictions Regional development |
title | A machine learning algorithm for predicting naturalized flow duration curves at human influenced sites and multiple catchment scales |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T22%3A44%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=A%20machine%20learning%20algorithm%20for%20predicting%20naturalized%20flow%20duration%20curves%20at%20human%20influenced%20sites%20and%20multiple%20catchment%20scales&rft.jtitle=arXiv.org&rft.au=Friedel,%20Michael%20J&rft.date=2024-09-09&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3109530563%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3109530563&rft_id=info:pmid/&rfr_iscdi=true |