Forecasting daily potential evapotranspiration using machine learning and limited climatic data

▶ Forecasting ET o models for water managing purposes (1985 Hargreaves ET o). ▶ 2 ET o forecasting approaches using air temperature and Multivariate Relevance Vector Machine. ▶ Ind. Approach provides better and larger forecast lags than Dir. Approach. ▶ Better ET o forecast when using forecasted wea...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Agricultural water management 2011-02, Vol.98 (4), p.553-562
Hauptverfasser: Torres, Alfonso F., Walker, Wynn R., McKee, Mac
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 562
container_issue 4
container_start_page 553
container_title Agricultural water management
container_volume 98
creator Torres, Alfonso F.
Walker, Wynn R.
McKee, Mac
description ▶ Forecasting ET o models for water managing purposes (1985 Hargreaves ET o). ▶ 2 ET o forecasting approaches using air temperature and Multivariate Relevance Vector Machine. ▶ Ind. Approach provides better and larger forecast lags than Dir. Approach. ▶ Better ET o forecast when using forecasted weather variables rather than ET o values. ▶ In study case, ET o is forecasted of up to 4 days using the Ind. Approach. Anticipating, or forecasting near-term irrigation demands is a requirement for improved management of conveyance and delivery systems. The most important component of a forecasting regime for irrigation is a simple, yet reliable, approach for forecasting crop water demands, which in this paper is represented by the reference or potential evapotranspiration (ET o). In most cases, weather data in the area is limited to a reduced number of variables measured, therefore current or future ET o estimation is restricted. This paper summarizes the results of testing of two proposed forecasting ET o schemes under the mentioned conditions. The first or “direct” approach involved forecasting ET o using historically computed ET o values. The second or “indirect” approach involved forecasting the required weather parameters for the ET o calculation based on historical data and then computing ET o. An statistical machine learning algorithm, the Multivariate Relevance Vector Machine (MVRVM) is applied to both of the forecastings schemes. The general ET o model used is the 1985 Hargreaves Equation which requires only minimum and maximum daily air temperatures and is thus well suited to regions lacking more comprehensive climatic data. The utility and practicality of the forecasting methodology is demonstrated with an application to an irrigation project in Central Utah. To determine the advantage and suitability of the applied algorithm, another learning machine, the Multilayer Perceptron (MLP), is used for comparison purposes. The robustness and stability of the proposed schemes are tested by the application of the bootstrap analysis.
doi_str_mv 10.1016/j.agwat.2010.10.012
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_860377442</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0378377410003331</els_id><sourcerecordid>860377442</sourcerecordid><originalsourceid>FETCH-LOGICAL-c456t-1657860c4ad6a57d48999025ff08023f82e7264258f4ecd15ca13ea52e740f803</originalsourceid><addsrcrecordid>eNp9kU1v1DAQhiMEEkvLL-BALohTFn8mzoEDqmgLqtQD9GyNnPHWq6wTbO-i_fdMmqpHDuOxR8-8mnldVR8423LG2y_7Lez-QtkK9lTZMi5eVRtuOtkIYeTrasNkZxrZdept9S7nPWNMMdVtKns9JXSQS4i7eoAwnut5KhhLgLHGE9AjQcxzSFDCFOtjXsADuMcQsR4RUlwKEId6DIdQcKgdXQh2JFfgsnrjYcz4_jlfVA_X339f3TZ39zc_rr7dNU7ptjS81Z1pmVMwtKC7QZm-75nQ3jPDhPRGYCdaJbTxCt3AtQMuETSVFfOGyYvq86o7p-nPEXOxh5AdjiNEnI7ZkviyvRJEypV0aco5obdzooHT2XJmFzft3j65aRc3lyK5SV0_166EM7qXFkSEXVjgk5XQGzrOFNTJKQUKRTFTaC2tboV9LAcS-_Q8LGQHoyeHXcgvokIaIWlX4j6unIeJZkrEPPwibcl4L4xQPRFfVwLJ21PAZLMLGB0Ogb612GEK_13rHwzyrqc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>860377442</pqid></control><display><type>article</type><title>Forecasting daily potential evapotranspiration using machine learning and limited climatic data</title><source>RePEc</source><source>Access via ScienceDirect (Elsevier)</source><creator>Torres, Alfonso F. ; Walker, Wynn R. ; McKee, Mac</creator><creatorcontrib>Torres, Alfonso F. ; Walker, Wynn R. ; McKee, Mac</creatorcontrib><description>▶ Forecasting ET o models for water managing purposes (1985 Hargreaves ET o). ▶ 2 ET o forecasting approaches using air temperature and Multivariate Relevance Vector Machine. ▶ Ind. Approach provides better and larger forecast lags than Dir. Approach. ▶ Better ET o forecast when using forecasted weather variables rather than ET o values. ▶ In study case, ET o is forecasted of up to 4 days using the Ind. Approach. Anticipating, or forecasting near-term irrigation demands is a requirement for improved management of conveyance and delivery systems. The most important component of a forecasting regime for irrigation is a simple, yet reliable, approach for forecasting crop water demands, which in this paper is represented by the reference or potential evapotranspiration (ET o). In most cases, weather data in the area is limited to a reduced number of variables measured, therefore current or future ET o estimation is restricted. This paper summarizes the results of testing of two proposed forecasting ET o schemes under the mentioned conditions. The first or “direct” approach involved forecasting ET o using historically computed ET o values. The second or “indirect” approach involved forecasting the required weather parameters for the ET o calculation based on historical data and then computing ET o. An statistical machine learning algorithm, the Multivariate Relevance Vector Machine (MVRVM) is applied to both of the forecastings schemes. The general ET o model used is the 1985 Hargreaves Equation which requires only minimum and maximum daily air temperatures and is thus well suited to regions lacking more comprehensive climatic data. The utility and practicality of the forecasting methodology is demonstrated with an application to an irrigation project in Central Utah. To determine the advantage and suitability of the applied algorithm, another learning machine, the Multilayer Perceptron (MLP), is used for comparison purposes. The robustness and stability of the proposed schemes are tested by the application of the bootstrap analysis.</description><identifier>ISSN: 0378-3774</identifier><identifier>EISSN: 1873-2283</identifier><identifier>DOI: 10.1016/j.agwat.2010.10.012</identifier><identifier>CODEN: AWMADF</identifier><language>eng</language><publisher>Amsterdam: Elsevier B.V</publisher><subject>Agricultural and forest climatology and meteorology. Irrigation. Drainage ; agricultural machinery and equipment ; Agronomy. Soil science and plant productions ; Algorithms ; automatic detection ; Biological and medical sciences ; Canal systems ; climatic factors ; Climatology ; daily potential evapotranspiration forecasting ; data analysis ; Demand ; Evapotranspiration ; Evapotranspiration Forecasting Hargreaves ETo equation Irrigation Canal systems Water management Machine learning ; Forecasting ; Fundamental and applied biological sciences. Psychology ; General agronomy. Plant production ; Hargreaves ET o equation ; Irrigation ; irrigation management ; Machine learning ; Mathematical analysis ; Mathematical models ; prediction ; Water management ; water requirement ; Weather</subject><ispartof>Agricultural water management, 2011-02, Vol.98 (4), p.553-562</ispartof><rights>2010 Elsevier B.V.</rights><rights>2015 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c456t-1657860c4ad6a57d48999025ff08023f82e7264258f4ecd15ca13ea52e740f803</citedby><cites>FETCH-LOGICAL-c456t-1657860c4ad6a57d48999025ff08023f82e7264258f4ecd15ca13ea52e740f803</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.agwat.2010.10.012$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>315,781,785,3551,4009,27929,27930,46000</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=23823425$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttp://econpapers.repec.org/article/eeeagiwat/v_3a98_3ay_3a2011_3ai_3a4_3ap_3a553-562.htm$$DView record in RePEc$$Hfree_for_read</backlink></links><search><creatorcontrib>Torres, Alfonso F.</creatorcontrib><creatorcontrib>Walker, Wynn R.</creatorcontrib><creatorcontrib>McKee, Mac</creatorcontrib><title>Forecasting daily potential evapotranspiration using machine learning and limited climatic data</title><title>Agricultural water management</title><description>▶ Forecasting ET o models for water managing purposes (1985 Hargreaves ET o). ▶ 2 ET o forecasting approaches using air temperature and Multivariate Relevance Vector Machine. ▶ Ind. Approach provides better and larger forecast lags than Dir. Approach. ▶ Better ET o forecast when using forecasted weather variables rather than ET o values. ▶ In study case, ET o is forecasted of up to 4 days using the Ind. Approach. Anticipating, or forecasting near-term irrigation demands is a requirement for improved management of conveyance and delivery systems. The most important component of a forecasting regime for irrigation is a simple, yet reliable, approach for forecasting crop water demands, which in this paper is represented by the reference or potential evapotranspiration (ET o). In most cases, weather data in the area is limited to a reduced number of variables measured, therefore current or future ET o estimation is restricted. This paper summarizes the results of testing of two proposed forecasting ET o schemes under the mentioned conditions. The first or “direct” approach involved forecasting ET o using historically computed ET o values. The second or “indirect” approach involved forecasting the required weather parameters for the ET o calculation based on historical data and then computing ET o. An statistical machine learning algorithm, the Multivariate Relevance Vector Machine (MVRVM) is applied to both of the forecastings schemes. The general ET o model used is the 1985 Hargreaves Equation which requires only minimum and maximum daily air temperatures and is thus well suited to regions lacking more comprehensive climatic data. The utility and practicality of the forecasting methodology is demonstrated with an application to an irrigation project in Central Utah. To determine the advantage and suitability of the applied algorithm, another learning machine, the Multilayer Perceptron (MLP), is used for comparison purposes. The robustness and stability of the proposed schemes are tested by the application of the bootstrap analysis.</description><subject>Agricultural and forest climatology and meteorology. Irrigation. Drainage</subject><subject>agricultural machinery and equipment</subject><subject>Agronomy. Soil science and plant productions</subject><subject>Algorithms</subject><subject>automatic detection</subject><subject>Biological and medical sciences</subject><subject>Canal systems</subject><subject>climatic factors</subject><subject>Climatology</subject><subject>daily potential evapotranspiration forecasting</subject><subject>data analysis</subject><subject>Demand</subject><subject>Evapotranspiration</subject><subject>Evapotranspiration Forecasting Hargreaves ETo equation Irrigation Canal systems Water management Machine learning</subject><subject>Forecasting</subject><subject>Fundamental and applied biological sciences. Psychology</subject><subject>General agronomy. Plant production</subject><subject>Hargreaves ET o equation</subject><subject>Irrigation</subject><subject>irrigation management</subject><subject>Machine learning</subject><subject>Mathematical analysis</subject><subject>Mathematical models</subject><subject>prediction</subject><subject>Water management</subject><subject>water requirement</subject><subject>Weather</subject><issn>0378-3774</issn><issn>1873-2283</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2011</creationdate><recordtype>article</recordtype><sourceid>X2L</sourceid><recordid>eNp9kU1v1DAQhiMEEkvLL-BALohTFn8mzoEDqmgLqtQD9GyNnPHWq6wTbO-i_fdMmqpHDuOxR8-8mnldVR8423LG2y_7Lez-QtkK9lTZMi5eVRtuOtkIYeTrasNkZxrZdept9S7nPWNMMdVtKns9JXSQS4i7eoAwnut5KhhLgLHGE9AjQcxzSFDCFOtjXsADuMcQsR4RUlwKEId6DIdQcKgdXQh2JFfgsnrjYcz4_jlfVA_X339f3TZ39zc_rr7dNU7ptjS81Z1pmVMwtKC7QZm-75nQ3jPDhPRGYCdaJbTxCt3AtQMuETSVFfOGyYvq86o7p-nPEXOxh5AdjiNEnI7ZkviyvRJEypV0aco5obdzooHT2XJmFzft3j65aRc3lyK5SV0_166EM7qXFkSEXVjgk5XQGzrOFNTJKQUKRTFTaC2tboV9LAcS-_Q8LGQHoyeHXcgvokIaIWlX4j6unIeJZkrEPPwibcl4L4xQPRFfVwLJ21PAZLMLGB0Ogb612GEK_13rHwzyrqc</recordid><startdate>20110201</startdate><enddate>20110201</enddate><creator>Torres, Alfonso F.</creator><creator>Walker, Wynn R.</creator><creator>McKee, Mac</creator><general>Elsevier B.V</general><general>Amsterdam; New York: Elsevier</general><general>Elsevier</general><scope>FBQ</scope><scope>IQODW</scope><scope>DKI</scope><scope>X2L</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FD</scope><scope>FR3</scope><scope>KR7</scope></search><sort><creationdate>20110201</creationdate><title>Forecasting daily potential evapotranspiration using machine learning and limited climatic data</title><author>Torres, Alfonso F. ; Walker, Wynn R. ; McKee, Mac</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c456t-1657860c4ad6a57d48999025ff08023f82e7264258f4ecd15ca13ea52e740f803</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Agricultural and forest climatology and meteorology. Irrigation. Drainage</topic><topic>agricultural machinery and equipment</topic><topic>Agronomy. Soil science and plant productions</topic><topic>Algorithms</topic><topic>automatic detection</topic><topic>Biological and medical sciences</topic><topic>Canal systems</topic><topic>climatic factors</topic><topic>Climatology</topic><topic>daily potential evapotranspiration forecasting</topic><topic>data analysis</topic><topic>Demand</topic><topic>Evapotranspiration</topic><topic>Evapotranspiration Forecasting Hargreaves ETo equation Irrigation Canal systems Water management Machine learning</topic><topic>Forecasting</topic><topic>Fundamental and applied biological sciences. Psychology</topic><topic>General agronomy. Plant production</topic><topic>Hargreaves ET o equation</topic><topic>Irrigation</topic><topic>irrigation management</topic><topic>Machine learning</topic><topic>Mathematical analysis</topic><topic>Mathematical models</topic><topic>prediction</topic><topic>Water management</topic><topic>water requirement</topic><topic>Weather</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Torres, Alfonso F.</creatorcontrib><creatorcontrib>Walker, Wynn R.</creatorcontrib><creatorcontrib>McKee, Mac</creatorcontrib><collection>AGRIS</collection><collection>Pascal-Francis</collection><collection>RePEc IDEAS</collection><collection>RePEc</collection><collection>CrossRef</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Civil Engineering Abstracts</collection><jtitle>Agricultural water management</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Torres, Alfonso F.</au><au>Walker, Wynn R.</au><au>McKee, Mac</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Forecasting daily potential evapotranspiration using machine learning and limited climatic data</atitle><jtitle>Agricultural water management</jtitle><date>2011-02-01</date><risdate>2011</risdate><volume>98</volume><issue>4</issue><spage>553</spage><epage>562</epage><pages>553-562</pages><issn>0378-3774</issn><eissn>1873-2283</eissn><coden>AWMADF</coden><abstract>▶ Forecasting ET o models for water managing purposes (1985 Hargreaves ET o). ▶ 2 ET o forecasting approaches using air temperature and Multivariate Relevance Vector Machine. ▶ Ind. Approach provides better and larger forecast lags than Dir. Approach. ▶ Better ET o forecast when using forecasted weather variables rather than ET o values. ▶ In study case, ET o is forecasted of up to 4 days using the Ind. Approach. Anticipating, or forecasting near-term irrigation demands is a requirement for improved management of conveyance and delivery systems. The most important component of a forecasting regime for irrigation is a simple, yet reliable, approach for forecasting crop water demands, which in this paper is represented by the reference or potential evapotranspiration (ET o). In most cases, weather data in the area is limited to a reduced number of variables measured, therefore current or future ET o estimation is restricted. This paper summarizes the results of testing of two proposed forecasting ET o schemes under the mentioned conditions. The first or “direct” approach involved forecasting ET o using historically computed ET o values. The second or “indirect” approach involved forecasting the required weather parameters for the ET o calculation based on historical data and then computing ET o. An statistical machine learning algorithm, the Multivariate Relevance Vector Machine (MVRVM) is applied to both of the forecastings schemes. The general ET o model used is the 1985 Hargreaves Equation which requires only minimum and maximum daily air temperatures and is thus well suited to regions lacking more comprehensive climatic data. The utility and practicality of the forecasting methodology is demonstrated with an application to an irrigation project in Central Utah. To determine the advantage and suitability of the applied algorithm, another learning machine, the Multilayer Perceptron (MLP), is used for comparison purposes. The robustness and stability of the proposed schemes are tested by the application of the bootstrap analysis.</abstract><cop>Amsterdam</cop><pub>Elsevier B.V</pub><doi>10.1016/j.agwat.2010.10.012</doi><tpages>10</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0378-3774
ispartof Agricultural water management, 2011-02, Vol.98 (4), p.553-562
issn 0378-3774
1873-2283
language eng
recordid cdi_proquest_miscellaneous_860377442
source RePEc; Access via ScienceDirect (Elsevier)
subjects Agricultural and forest climatology and meteorology. Irrigation. Drainage
agricultural machinery and equipment
Agronomy. Soil science and plant productions
Algorithms
automatic detection
Biological and medical sciences
Canal systems
climatic factors
Climatology
daily potential evapotranspiration forecasting
data analysis
Demand
Evapotranspiration
Evapotranspiration Forecasting Hargreaves ETo equation Irrigation Canal systems Water management Machine learning
Forecasting
Fundamental and applied biological sciences. Psychology
General agronomy. Plant production
Hargreaves ET o equation
Irrigation
irrigation management
Machine learning
Mathematical analysis
Mathematical models
prediction
Water management
water requirement
Weather
title Forecasting daily potential evapotranspiration using machine learning and limited climatic data
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-11T11%3A20%3A37IST&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=Forecasting%20daily%20potential%20evapotranspiration%20using%20machine%20learning%20and%20limited%20climatic%20data&rft.jtitle=Agricultural%20water%20management&rft.au=Torres,%20Alfonso%20F.&rft.date=2011-02-01&rft.volume=98&rft.issue=4&rft.spage=553&rft.epage=562&rft.pages=553-562&rft.issn=0378-3774&rft.eissn=1873-2283&rft.coden=AWMADF&rft_id=info:doi/10.1016/j.agwat.2010.10.012&rft_dat=%3Cproquest_cross%3E860377442%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=860377442&rft_id=info:pmid/&rft_els_id=S0378377410003331&rfr_iscdi=true