ENSO Dynamics, Trends, and Prediction Using Machine Learning
El Niño–Southern Oscillation (ENSO) has global effects on the hydrological cycle, agriculture, ecosystems, health, and society. We present a novel nonhomogeneous hidden Markov model (NHMM) for studying the underlying dynamics of sea surface temperature anomalies (SSTA) over the region 15°N–15°S, 150...
Gespeichert in:
Veröffentlicht in: | Weather and forecasting 2020-10, Vol.35 (5), p.2061-2081 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 2081 |
---|---|
container_issue | 5 |
container_start_page | 2061 |
container_title | Weather and forecasting |
container_volume | 35 |
creator | Rojo Hernández, Julián David Mesa, Óscar José Lall, Upmanu |
description | El Niño–Southern Oscillation (ENSO) has global effects on the hydrological cycle, agriculture, ecosystems, health, and society. We present a novel nonhomogeneous hidden Markov model (NHMM) for studying the underlying dynamics of sea surface temperature anomalies (SSTA) over the region 15°N–15°S, 150°E–80°W from January 1856 to December 2019, using the monthly SSTA data from the Kaplan extended SST v2 product. This nonparametric machine learning scheme dynamically simulates and predicts the spatiotemporal evolution of ENSO patterns, including their asymmetry, long-term trends, persistence, and seasonal evolution. The model identifies five hidden states whose spatial SSTA patterns are similar to the so-called ENSO flavors in the literature. From the fitted NHMM, the model shows that there are systematic trends in the frequency and persistence of the regimes over the last 160 years that may be related to changes in the mean state of basin temperature and/or global warming. We evaluated the ability of NHMM to make out-of-sample probabilistic predictions of the spatial structure of temperature anomalies for the period 1995–2016 using a training period from January 1856 to December 1994. The results show that NHMMs can simulate the behavior of the Niño-3.4 and Niño-1.2 regions quite well. The NHMM results over this period are comparable or superior to the commonly available ENSO prediction models, with the additional advantage of directly providing insights as to the space patterns, seasonal, and longer-term trends of the SSTA in the equatorial Pacific region. |
doi_str_mv | 10.1175/WAF-D-20-0031.1 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2511380143</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2511380143</sourcerecordid><originalsourceid>FETCH-LOGICAL-c310t-f94226c9c05d5b053a3c5c0ac55d6e67d6cf7dba5aaf792d9b57133fd612e5b83</originalsourceid><addsrcrecordid>eNotkM1LAzEUxIMoWKtnrwteTftesm8_wEvphwrVCrZ4DNkkq1tstibtof99t9TTMMMwAz_G7hEGiDkNv0YzPuECOIDEAV6wHtLJpTK9ZD0oCsELpOya3cS4BgBBouyxp-n75yKZHLzeNCY-JsvgvO1Ue5t8BGcbs2tan6xi47-TN21-Gu-SudPBd8Etu6r1b3R3_9pnq9l0OX7h88Xz63g050Yi7HhdpkJkpjRAliogqaUhA9oQ2cxluc1MndtKk9Z1XgpbVpSjlLXNUDiqCtlnD-fdbWj_9i7u1LrdB99dKkGIsgBMZdcanlsmtDEGV6ttaDY6HBSCOiFSHSI1UQLUCZFCeQRISle1</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2511380143</pqid></control><display><type>article</type><title>ENSO Dynamics, Trends, and Prediction Using Machine Learning</title><source>American Meteorological Society</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>Alma/SFX Local Collection</source><creator>Rojo Hernández, Julián David ; Mesa, Óscar José ; Lall, Upmanu</creator><creatorcontrib>Rojo Hernández, Julián David ; Mesa, Óscar José ; Lall, Upmanu</creatorcontrib><description>El Niño–Southern Oscillation (ENSO) has global effects on the hydrological cycle, agriculture, ecosystems, health, and society. We present a novel nonhomogeneous hidden Markov model (NHMM) for studying the underlying dynamics of sea surface temperature anomalies (SSTA) over the region 15°N–15°S, 150°E–80°W from January 1856 to December 2019, using the monthly SSTA data from the Kaplan extended SST v2 product. This nonparametric machine learning scheme dynamically simulates and predicts the spatiotemporal evolution of ENSO patterns, including their asymmetry, long-term trends, persistence, and seasonal evolution. The model identifies five hidden states whose spatial SSTA patterns are similar to the so-called ENSO flavors in the literature. From the fitted NHMM, the model shows that there are systematic trends in the frequency and persistence of the regimes over the last 160 years that may be related to changes in the mean state of basin temperature and/or global warming. We evaluated the ability of NHMM to make out-of-sample probabilistic predictions of the spatial structure of temperature anomalies for the period 1995–2016 using a training period from January 1856 to December 1994. The results show that NHMMs can simulate the behavior of the Niño-3.4 and Niño-1.2 regions quite well. The NHMM results over this period are comparable or superior to the commonly available ENSO prediction models, with the additional advantage of directly providing insights as to the space patterns, seasonal, and longer-term trends of the SSTA in the equatorial Pacific region.</description><identifier>ISSN: 0882-8156</identifier><identifier>EISSN: 1520-0434</identifier><identifier>DOI: 10.1175/WAF-D-20-0031.1</identifier><language>eng</language><publisher>Boston: American Meteorological Society</publisher><subject>Agricultural ecosystems ; Agriculture ; Anomalies ; Climate change ; Dynamics ; El Nino ; El Nino phenomena ; El Nino-Southern Oscillation event ; Equatorial regions ; Evolution ; Global warming ; Hydrologic cycle ; Hydrological cycle ; Hydrology ; Learning algorithms ; Learning behaviour ; Machine learning ; Markov chains ; Prediction models ; Sea surface ; Sea surface temperature ; Sea surface temperature anomalies ; Southern Oscillation ; Surface temperature ; Temperature anomalies ; Training ; Trends</subject><ispartof>Weather and forecasting, 2020-10, Vol.35 (5), p.2061-2081</ispartof><rights>Copyright American Meteorological Society Oct 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c310t-f94226c9c05d5b053a3c5c0ac55d6e67d6cf7dba5aaf792d9b57133fd612e5b83</citedby><cites>FETCH-LOGICAL-c310t-f94226c9c05d5b053a3c5c0ac55d6e67d6cf7dba5aaf792d9b57133fd612e5b83</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,777,781,3668,27905,27906</link.rule.ids></links><search><creatorcontrib>Rojo Hernández, Julián David</creatorcontrib><creatorcontrib>Mesa, Óscar José</creatorcontrib><creatorcontrib>Lall, Upmanu</creatorcontrib><title>ENSO Dynamics, Trends, and Prediction Using Machine Learning</title><title>Weather and forecasting</title><description>El Niño–Southern Oscillation (ENSO) has global effects on the hydrological cycle, agriculture, ecosystems, health, and society. We present a novel nonhomogeneous hidden Markov model (NHMM) for studying the underlying dynamics of sea surface temperature anomalies (SSTA) over the region 15°N–15°S, 150°E–80°W from January 1856 to December 2019, using the monthly SSTA data from the Kaplan extended SST v2 product. This nonparametric machine learning scheme dynamically simulates and predicts the spatiotemporal evolution of ENSO patterns, including their asymmetry, long-term trends, persistence, and seasonal evolution. The model identifies five hidden states whose spatial SSTA patterns are similar to the so-called ENSO flavors in the literature. From the fitted NHMM, the model shows that there are systematic trends in the frequency and persistence of the regimes over the last 160 years that may be related to changes in the mean state of basin temperature and/or global warming. We evaluated the ability of NHMM to make out-of-sample probabilistic predictions of the spatial structure of temperature anomalies for the period 1995–2016 using a training period from January 1856 to December 1994. The results show that NHMMs can simulate the behavior of the Niño-3.4 and Niño-1.2 regions quite well. The NHMM results over this period are comparable or superior to the commonly available ENSO prediction models, with the additional advantage of directly providing insights as to the space patterns, seasonal, and longer-term trends of the SSTA in the equatorial Pacific region.</description><subject>Agricultural ecosystems</subject><subject>Agriculture</subject><subject>Anomalies</subject><subject>Climate change</subject><subject>Dynamics</subject><subject>El Nino</subject><subject>El Nino phenomena</subject><subject>El Nino-Southern Oscillation event</subject><subject>Equatorial regions</subject><subject>Evolution</subject><subject>Global warming</subject><subject>Hydrologic cycle</subject><subject>Hydrological cycle</subject><subject>Hydrology</subject><subject>Learning algorithms</subject><subject>Learning behaviour</subject><subject>Machine learning</subject><subject>Markov chains</subject><subject>Prediction models</subject><subject>Sea surface</subject><subject>Sea surface temperature</subject><subject>Sea surface temperature anomalies</subject><subject>Southern Oscillation</subject><subject>Surface temperature</subject><subject>Temperature anomalies</subject><subject>Training</subject><subject>Trends</subject><issn>0882-8156</issn><issn>1520-0434</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNotkM1LAzEUxIMoWKtnrwteTftesm8_wEvphwrVCrZ4DNkkq1tstibtof99t9TTMMMwAz_G7hEGiDkNv0YzPuECOIDEAV6wHtLJpTK9ZD0oCsELpOya3cS4BgBBouyxp-n75yKZHLzeNCY-JsvgvO1Ue5t8BGcbs2tan6xi47-TN21-Gu-SudPBd8Etu6r1b3R3_9pnq9l0OX7h88Xz63g050Yi7HhdpkJkpjRAliogqaUhA9oQ2cxluc1MndtKk9Z1XgpbVpSjlLXNUDiqCtlnD-fdbWj_9i7u1LrdB99dKkGIsgBMZdcanlsmtDEGV6ttaDY6HBSCOiFSHSI1UQLUCZFCeQRISle1</recordid><startdate>20201001</startdate><enddate>20201001</enddate><creator>Rojo Hernández, Julián David</creator><creator>Mesa, Óscar José</creator><creator>Lall, Upmanu</creator><general>American Meteorological Society</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QH</scope><scope>7TG</scope><scope>7TN</scope><scope>7UA</scope><scope>C1K</scope><scope>F1W</scope><scope>H96</scope><scope>KL.</scope><scope>L.G</scope><scope>U9A</scope></search><sort><creationdate>20201001</creationdate><title>ENSO Dynamics, Trends, and Prediction Using Machine Learning</title><author>Rojo Hernández, Julián David ; Mesa, Óscar José ; Lall, Upmanu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c310t-f94226c9c05d5b053a3c5c0ac55d6e67d6cf7dba5aaf792d9b57133fd612e5b83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Agricultural ecosystems</topic><topic>Agriculture</topic><topic>Anomalies</topic><topic>Climate change</topic><topic>Dynamics</topic><topic>El Nino</topic><topic>El Nino phenomena</topic><topic>El Nino-Southern Oscillation event</topic><topic>Equatorial regions</topic><topic>Evolution</topic><topic>Global warming</topic><topic>Hydrologic cycle</topic><topic>Hydrological cycle</topic><topic>Hydrology</topic><topic>Learning algorithms</topic><topic>Learning behaviour</topic><topic>Machine learning</topic><topic>Markov chains</topic><topic>Prediction models</topic><topic>Sea surface</topic><topic>Sea surface temperature</topic><topic>Sea surface temperature anomalies</topic><topic>Southern Oscillation</topic><topic>Surface temperature</topic><topic>Temperature anomalies</topic><topic>Training</topic><topic>Trends</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Rojo Hernández, Julián David</creatorcontrib><creatorcontrib>Mesa, Óscar José</creatorcontrib><creatorcontrib>Lall, Upmanu</creatorcontrib><collection>CrossRef</collection><collection>Aqualine</collection><collection>Meteorological & Geoastrophysical Abstracts</collection><collection>Oceanic Abstracts</collection><collection>Water Resources Abstracts</collection><collection>Environmental Sciences and Pollution Management</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>Weather and forecasting</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Rojo Hernández, Julián David</au><au>Mesa, Óscar José</au><au>Lall, Upmanu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ENSO Dynamics, Trends, and Prediction Using Machine Learning</atitle><jtitle>Weather and forecasting</jtitle><date>2020-10-01</date><risdate>2020</risdate><volume>35</volume><issue>5</issue><spage>2061</spage><epage>2081</epage><pages>2061-2081</pages><issn>0882-8156</issn><eissn>1520-0434</eissn><abstract>El Niño–Southern Oscillation (ENSO) has global effects on the hydrological cycle, agriculture, ecosystems, health, and society. We present a novel nonhomogeneous hidden Markov model (NHMM) for studying the underlying dynamics of sea surface temperature anomalies (SSTA) over the region 15°N–15°S, 150°E–80°W from January 1856 to December 2019, using the monthly SSTA data from the Kaplan extended SST v2 product. This nonparametric machine learning scheme dynamically simulates and predicts the spatiotemporal evolution of ENSO patterns, including their asymmetry, long-term trends, persistence, and seasonal evolution. The model identifies five hidden states whose spatial SSTA patterns are similar to the so-called ENSO flavors in the literature. From the fitted NHMM, the model shows that there are systematic trends in the frequency and persistence of the regimes over the last 160 years that may be related to changes in the mean state of basin temperature and/or global warming. We evaluated the ability of NHMM to make out-of-sample probabilistic predictions of the spatial structure of temperature anomalies for the period 1995–2016 using a training period from January 1856 to December 1994. The results show that NHMMs can simulate the behavior of the Niño-3.4 and Niño-1.2 regions quite well. The NHMM results over this period are comparable or superior to the commonly available ENSO prediction models, with the additional advantage of directly providing insights as to the space patterns, seasonal, and longer-term trends of the SSTA in the equatorial Pacific region.</abstract><cop>Boston</cop><pub>American Meteorological Society</pub><doi>10.1175/WAF-D-20-0031.1</doi><tpages>21</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0882-8156 |
ispartof | Weather and forecasting, 2020-10, Vol.35 (5), p.2061-2081 |
issn | 0882-8156 1520-0434 |
language | eng |
recordid | cdi_proquest_journals_2511380143 |
source | American Meteorological Society; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; Alma/SFX Local Collection |
subjects | Agricultural ecosystems Agriculture Anomalies Climate change Dynamics El Nino El Nino phenomena El Nino-Southern Oscillation event Equatorial regions Evolution Global warming Hydrologic cycle Hydrological cycle Hydrology Learning algorithms Learning behaviour Machine learning Markov chains Prediction models Sea surface Sea surface temperature Sea surface temperature anomalies Southern Oscillation Surface temperature Temperature anomalies Training Trends |
title | ENSO Dynamics, Trends, and Prediction Using Machine Learning |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T22%3A44%3A43IST&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=ENSO%20Dynamics,%20Trends,%20and%20Prediction%20Using%20Machine%20Learning&rft.jtitle=Weather%20and%20forecasting&rft.au=Rojo%20Hern%C3%A1ndez,%20Juli%C3%A1n%20David&rft.date=2020-10-01&rft.volume=35&rft.issue=5&rft.spage=2061&rft.epage=2081&rft.pages=2061-2081&rft.issn=0882-8156&rft.eissn=1520-0434&rft_id=info:doi/10.1175/WAF-D-20-0031.1&rft_dat=%3Cproquest_cross%3E2511380143%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=2511380143&rft_id=info:pmid/&rfr_iscdi=true |