Real-time wave forecasts off the western Indian coast
The wave observations at three locations off the west coast of India have been analyzed using artificial neural network (ANN) to obtain forecasts of significant wave heights at intervals of 3, 6, 12 and 24 h. The most appropriate training method requiring an input of four observations spread over pr...
Gespeichert in:
Veröffentlicht in: | Applied ocean research 2007-02, Vol.29 (1), p.72-79 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 79 |
---|---|
container_issue | 1 |
container_start_page | 72 |
container_title | Applied ocean research |
container_volume | 29 |
creator | Jain, P. Deo, M.C. |
description | The wave observations at three locations off the west coast of India have been analyzed using artificial neural network (ANN) to obtain forecasts of significant wave heights at intervals of 3, 6, 12 and 24 h. The most appropriate training method requiring an input of four observations spread over previous 24 h has been selected after considerable trials. Further, the networks are trained after filling in the missing information. Larger gaps in data are filled in using spatial mapping involving observations at nearby locations, while relatively smaller gaps are accounted for by the statistical technique of multiple regressions in temporal mode. It is found that by doing so the long-interval forecasting is tremendously improved, with corresponding accuracy levels becoming close to those of the short-interval forecasts. If the amount of gaps is restricted to around 2% per year or so it is possible to obtain 12 h ahead forecasts with 0.08 m accuracy on an average and 24 h ahead forecast with a mean accuracy of 0.13 m. However, in harsher environments the prediction accuracy can change. |
doi_str_mv | 10.1016/j.apor.2007.05.003 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_20553385</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0141118707000417</els_id><sourcerecordid>20553385</sourcerecordid><originalsourceid>FETCH-LOGICAL-c331t-5b7449defd4d32b1a5bfb30baa0ab50d13f3b1220e7959bd6c8b5f47d95a92343</originalsourceid><addsrcrecordid>eNp9kEtLA0EQhAdRMEb_gKc9edu155XdBS8SfAQCguh5mEcPTtjsxJmN4r93Qjx7aqiuaro-Qq4pNBTo4nbT6F1MDQNoG5ANAD8hM9q1fU2l6E_JDKigNS3KObnIeQNAWbfoZkS-oh7qKWyx-tZfWPmY0Oo85Sp6X00fRcY8YRqr1eiCHisby_aSnHk9ZLz6m3Py_vjwtnyu1y9Pq-X9urac06mWphWid-idcJwZqqXxhoPRGrSR4Cj33FDGANte9sYtbGekF63rpe4ZF3xObo53dyl-7ssjahuyxWHQI8Z9Vgyk5LyTxciORptizgm92qWw1elHUVAHQmqjDoTUgZACqQqhEro7hrBU-AqYVLYBR4suFAiTcjH8F_8FWUxu5Q</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>20553385</pqid></control><display><type>article</type><title>Real-time wave forecasts off the western Indian coast</title><source>Access via ScienceDirect (Elsevier)</source><creator>Jain, P. ; Deo, M.C.</creator><creatorcontrib>Jain, P. ; Deo, M.C.</creatorcontrib><description>The wave observations at three locations off the west coast of India have been analyzed using artificial neural network (ANN) to obtain forecasts of significant wave heights at intervals of 3, 6, 12 and 24 h. The most appropriate training method requiring an input of four observations spread over previous 24 h has been selected after considerable trials. Further, the networks are trained after filling in the missing information. Larger gaps in data are filled in using spatial mapping involving observations at nearby locations, while relatively smaller gaps are accounted for by the statistical technique of multiple regressions in temporal mode. It is found that by doing so the long-interval forecasting is tremendously improved, with corresponding accuracy levels becoming close to those of the short-interval forecasts. If the amount of gaps is restricted to around 2% per year or so it is possible to obtain 12 h ahead forecasts with 0.08 m accuracy on an average and 24 h ahead forecast with a mean accuracy of 0.13 m. However, in harsher environments the prediction accuracy can change.</description><identifier>ISSN: 0141-1187</identifier><identifier>EISSN: 1879-1549</identifier><identifier>DOI: 10.1016/j.apor.2007.05.003</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Data buoys ; Data gaps ; Gap in-filling ; Marine ; Neural networks ; Wave forecasting</subject><ispartof>Applied ocean research, 2007-02, Vol.29 (1), p.72-79</ispartof><rights>2007 Elsevier Ltd</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c331t-5b7449defd4d32b1a5bfb30baa0ab50d13f3b1220e7959bd6c8b5f47d95a92343</citedby><cites>FETCH-LOGICAL-c331t-5b7449defd4d32b1a5bfb30baa0ab50d13f3b1220e7959bd6c8b5f47d95a92343</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://dx.doi.org/10.1016/j.apor.2007.05.003$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>314,780,784,3550,27924,27925,45995</link.rule.ids></links><search><creatorcontrib>Jain, P.</creatorcontrib><creatorcontrib>Deo, M.C.</creatorcontrib><title>Real-time wave forecasts off the western Indian coast</title><title>Applied ocean research</title><description>The wave observations at three locations off the west coast of India have been analyzed using artificial neural network (ANN) to obtain forecasts of significant wave heights at intervals of 3, 6, 12 and 24 h. The most appropriate training method requiring an input of four observations spread over previous 24 h has been selected after considerable trials. Further, the networks are trained after filling in the missing information. Larger gaps in data are filled in using spatial mapping involving observations at nearby locations, while relatively smaller gaps are accounted for by the statistical technique of multiple regressions in temporal mode. It is found that by doing so the long-interval forecasting is tremendously improved, with corresponding accuracy levels becoming close to those of the short-interval forecasts. If the amount of gaps is restricted to around 2% per year or so it is possible to obtain 12 h ahead forecasts with 0.08 m accuracy on an average and 24 h ahead forecast with a mean accuracy of 0.13 m. However, in harsher environments the prediction accuracy can change.</description><subject>Data buoys</subject><subject>Data gaps</subject><subject>Gap in-filling</subject><subject>Marine</subject><subject>Neural networks</subject><subject>Wave forecasting</subject><issn>0141-1187</issn><issn>1879-1549</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2007</creationdate><recordtype>article</recordtype><recordid>eNp9kEtLA0EQhAdRMEb_gKc9edu155XdBS8SfAQCguh5mEcPTtjsxJmN4r93Qjx7aqiuaro-Qq4pNBTo4nbT6F1MDQNoG5ANAD8hM9q1fU2l6E_JDKigNS3KObnIeQNAWbfoZkS-oh7qKWyx-tZfWPmY0Oo85Sp6X00fRcY8YRqr1eiCHisby_aSnHk9ZLz6m3Py_vjwtnyu1y9Pq-X9urac06mWphWid-idcJwZqqXxhoPRGrSR4Cj33FDGANte9sYtbGekF63rpe4ZF3xObo53dyl-7ssjahuyxWHQI8Z9Vgyk5LyTxciORptizgm92qWw1elHUVAHQmqjDoTUgZACqQqhEro7hrBU-AqYVLYBR4suFAiTcjH8F_8FWUxu5Q</recordid><startdate>20070201</startdate><enddate>20070201</enddate><creator>Jain, P.</creator><creator>Deo, M.C.</creator><general>Elsevier Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7TG</scope><scope>7TN</scope><scope>F1W</scope><scope>H96</scope><scope>KL.</scope><scope>L.G</scope></search><sort><creationdate>20070201</creationdate><title>Real-time wave forecasts off the western Indian coast</title><author>Jain, P. ; Deo, M.C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c331t-5b7449defd4d32b1a5bfb30baa0ab50d13f3b1220e7959bd6c8b5f47d95a92343</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2007</creationdate><topic>Data buoys</topic><topic>Data gaps</topic><topic>Gap in-filling</topic><topic>Marine</topic><topic>Neural networks</topic><topic>Wave forecasting</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Jain, P.</creatorcontrib><creatorcontrib>Deo, M.C.</creatorcontrib><collection>CrossRef</collection><collection>Meteorological & Geoastrophysical Abstracts</collection><collection>Oceanic Abstracts</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources</collection><collection>Meteorological & Geoastrophysical Abstracts - Academic</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) Professional</collection><jtitle>Applied ocean research</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jain, P.</au><au>Deo, M.C.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Real-time wave forecasts off the western Indian coast</atitle><jtitle>Applied ocean research</jtitle><date>2007-02-01</date><risdate>2007</risdate><volume>29</volume><issue>1</issue><spage>72</spage><epage>79</epage><pages>72-79</pages><issn>0141-1187</issn><eissn>1879-1549</eissn><abstract>The wave observations at three locations off the west coast of India have been analyzed using artificial neural network (ANN) to obtain forecasts of significant wave heights at intervals of 3, 6, 12 and 24 h. The most appropriate training method requiring an input of four observations spread over previous 24 h has been selected after considerable trials. Further, the networks are trained after filling in the missing information. Larger gaps in data are filled in using spatial mapping involving observations at nearby locations, while relatively smaller gaps are accounted for by the statistical technique of multiple regressions in temporal mode. It is found that by doing so the long-interval forecasting is tremendously improved, with corresponding accuracy levels becoming close to those of the short-interval forecasts. If the amount of gaps is restricted to around 2% per year or so it is possible to obtain 12 h ahead forecasts with 0.08 m accuracy on an average and 24 h ahead forecast with a mean accuracy of 0.13 m. However, in harsher environments the prediction accuracy can change.</abstract><pub>Elsevier Ltd</pub><doi>10.1016/j.apor.2007.05.003</doi><tpages>8</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0141-1187 |
ispartof | Applied ocean research, 2007-02, Vol.29 (1), p.72-79 |
issn | 0141-1187 1879-1549 |
language | eng |
recordid | cdi_proquest_miscellaneous_20553385 |
source | Access via ScienceDirect (Elsevier) |
subjects | Data buoys Data gaps Gap in-filling Marine Neural networks Wave forecasting |
title | Real-time wave forecasts off the western Indian coast |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T04%3A04%3A46IST&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=Real-time%20wave%20forecasts%20off%20the%20western%20Indian%20coast&rft.jtitle=Applied%20ocean%20research&rft.au=Jain,%20P.&rft.date=2007-02-01&rft.volume=29&rft.issue=1&rft.spage=72&rft.epage=79&rft.pages=72-79&rft.issn=0141-1187&rft.eissn=1879-1549&rft_id=info:doi/10.1016/j.apor.2007.05.003&rft_dat=%3Cproquest_cross%3E20553385%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=20553385&rft_id=info:pmid/&rft_els_id=S0141118707000417&rfr_iscdi=true |