MANNGA: A Robust Method for Gap Filling Meteorological Data

Abstract This paper presents Mannga (Multiple variables with Artificial Neural Network and Genetic Algorithm), a method designed for gap filling meteorological data. The main approach is to estimate the missing data based on values of other meteorological variables measured at the same time in the s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Revista Brasileira de Meteorologia 2019-06, Vol.34 (2), p.315-323
Hauptverfasser: Ventura, Thiago Meirelles, Martins, Claudia Aparecida, Figueiredo, Josiel Maimone de, Oliveira, Allan Gonçalves de, Montanher, Johnata Rodrigo Pinheiro
Format: Artikel
Sprache:eng ; por
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 323
container_issue 2
container_start_page 315
container_title Revista Brasileira de Meteorologia
container_volume 34
creator Ventura, Thiago Meirelles
Martins, Claudia Aparecida
Figueiredo, Josiel Maimone de
Oliveira, Allan Gonçalves de
Montanher, Johnata Rodrigo Pinheiro
description Abstract This paper presents Mannga (Multiple variables with Artificial Neural Network and Genetic Algorithm), a method designed for gap filling meteorological data. The main approach is to estimate the missing data based on values of other meteorological variables measured at the same time in the same local, since the meteorological variables are strongly related. Experimental tests showed the performance of Mannga compared with other two methods typically used by researches in this area. Good results were achieved, with high accuracy even for sequential failures, which is a big challenge for researchers. The core advantages of Mannga are the flexibility of handling different types of meteorological data, the ability of select the best variables to assist the gap filling and the capacity to deal with sequential failures. Moreover, the method is available to public use with the Java programming language. Resumo Este trabalho apresenta o método Mannga (Multiple variables with Artificial Neural Network and Genetic Algorithm), desenvolvido para preencher falhas em dados meteorológicos. A ideia principal é preencher as falhas baseando-se nos valores de outras variáveis meteorológicas medidas no mesmo momento, uma vez que as variáveis meteorológicas possuem forte relação entre si. Testes foram executados para mostrar a performance do Mannga comparado com outros dois métodos comumente utilizados na área. Os resultados alcançados atingiram uma boa precisão, principalmente relacionado ao desafio de preencher valores em dados que ocorrem em sequência. As principais vantagens do Mannga são a sua flexibilidade em manipular diferentes tipos de dados meteorológicos, a habilidade de selecionar as melhores variáveis para auxiliar no preenchimento das falhas e a capacidade de lidar com falhas sequenciais. Além disso, o método está disponível publicamente na linguagem de programação Java.
doi_str_mv 10.1590/0102-77863340035
format Article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_proquest_journals_2283261365</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_4108e5b531144cf194865d0e8fc40f71</doaj_id><sourcerecordid>2283261365</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3335-7c49375092fd47eb60f2b9608227b827a6251eaff6b45ee232f4e73c44439ba33</originalsourceid><addsrcrecordid>eNpNkE1LAzEQhoMoWKt3jwueVyeZfK2elmproa0geg7ZbFK3rE3Nbg_-e1srxdPAOy_PDA8h1xRuqSjgDiiwXCktETkAihMyoIVmOUdBT8nguD4nF123ApBApRiQh3m5WEzK-6zMXmO17fps7vuPWGchpmxiN9m4adtmvdzHPqbYxmXjbJs92t5ekrNg285f_c0heR8_vY2e89nLZDoqZ7lDRJErxwtUAgoWaq58JSGwqpCgGVOVZspKJqi3IciKC-8ZssC9Qsc5x6KyiEMyPXDraFdmk5pPm75NtI35DWJaGpv6xrXecArai0ogpZy7QAuupajB6-A4BEV3rJsDa5Pi19Z3vVnFbVrv3jeMaWSSohS7FhxaLsWuSz4cr1Iwe91m79P8040_wR5tLg</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2283261365</pqid></control><display><type>article</type><title>MANNGA: A Robust Method for Gap Filling Meteorological Data</title><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Ventura, Thiago Meirelles ; Martins, Claudia Aparecida ; Figueiredo, Josiel Maimone de ; Oliveira, Allan Gonçalves de ; Montanher, Johnata Rodrigo Pinheiro</creator><creatorcontrib>Ventura, Thiago Meirelles ; Martins, Claudia Aparecida ; Figueiredo, Josiel Maimone de ; Oliveira, Allan Gonçalves de ; Montanher, Johnata Rodrigo Pinheiro</creatorcontrib><description>Abstract This paper presents Mannga (Multiple variables with Artificial Neural Network and Genetic Algorithm), a method designed for gap filling meteorological data. The main approach is to estimate the missing data based on values of other meteorological variables measured at the same time in the same local, since the meteorological variables are strongly related. Experimental tests showed the performance of Mannga compared with other two methods typically used by researches in this area. Good results were achieved, with high accuracy even for sequential failures, which is a big challenge for researchers. The core advantages of Mannga are the flexibility of handling different types of meteorological data, the ability of select the best variables to assist the gap filling and the capacity to deal with sequential failures. Moreover, the method is available to public use with the Java programming language. Resumo Este trabalho apresenta o método Mannga (Multiple variables with Artificial Neural Network and Genetic Algorithm), desenvolvido para preencher falhas em dados meteorológicos. A ideia principal é preencher as falhas baseando-se nos valores de outras variáveis meteorológicas medidas no mesmo momento, uma vez que as variáveis meteorológicas possuem forte relação entre si. Testes foram executados para mostrar a performance do Mannga comparado com outros dois métodos comumente utilizados na área. Os resultados alcançados atingiram uma boa precisão, principalmente relacionado ao desafio de preencher valores em dados que ocorrem em sequência. As principais vantagens do Mannga são a sua flexibilidade em manipular diferentes tipos de dados meteorológicos, a habilidade de selecionar as melhores variáveis para auxiliar no preenchimento das falhas e a capacidade de lidar com falhas sequenciais. Além disso, o método está disponível publicamente na linguagem de programação Java.</description><identifier>ISSN: 0102-7786</identifier><identifier>ISSN: 1982-4351</identifier><identifier>EISSN: 1982-4351</identifier><identifier>DOI: 10.1590/0102-77863340035</identifier><language>eng ; por</language><publisher>Rio de Janeiro: Sociedade Brasileira de Meteorologia</publisher><subject>Algorithms ; algoritmos genéticos ; Artificial neural networks ; dados multivariados ; Failures ; Genetic algorithms ; Handling ; Java ; Lidar ; Meteorological data ; Missing data ; Neural networks ; redes neurais artificiais ; software livre</subject><ispartof>Revista Brasileira de Meteorologia, 2019-06, Vol.34 (2), p.315-323</ispartof><rights>Copyright Sociedade Brasileira de Meteorologia Apr-Jun 2019</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3335-7c49375092fd47eb60f2b9608227b827a6251eaff6b45ee232f4e73c44439ba33</citedby><cites>FETCH-LOGICAL-c3335-7c49375092fd47eb60f2b9608227b827a6251eaff6b45ee232f4e73c44439ba33</cites><orcidid>0000-0002-3758-5466 ; 0000-0001-7861-8896 ; 0000-0002-6352-9548 ; 0000-0003-4827-1048 ; 0000-0001-8569-7684</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,860,27901,27902</link.rule.ids></links><search><creatorcontrib>Ventura, Thiago Meirelles</creatorcontrib><creatorcontrib>Martins, Claudia Aparecida</creatorcontrib><creatorcontrib>Figueiredo, Josiel Maimone de</creatorcontrib><creatorcontrib>Oliveira, Allan Gonçalves de</creatorcontrib><creatorcontrib>Montanher, Johnata Rodrigo Pinheiro</creatorcontrib><title>MANNGA: A Robust Method for Gap Filling Meteorological Data</title><title>Revista Brasileira de Meteorologia</title><description>Abstract This paper presents Mannga (Multiple variables with Artificial Neural Network and Genetic Algorithm), a method designed for gap filling meteorological data. The main approach is to estimate the missing data based on values of other meteorological variables measured at the same time in the same local, since the meteorological variables are strongly related. Experimental tests showed the performance of Mannga compared with other two methods typically used by researches in this area. Good results were achieved, with high accuracy even for sequential failures, which is a big challenge for researchers. The core advantages of Mannga are the flexibility of handling different types of meteorological data, the ability of select the best variables to assist the gap filling and the capacity to deal with sequential failures. Moreover, the method is available to public use with the Java programming language. Resumo Este trabalho apresenta o método Mannga (Multiple variables with Artificial Neural Network and Genetic Algorithm), desenvolvido para preencher falhas em dados meteorológicos. A ideia principal é preencher as falhas baseando-se nos valores de outras variáveis meteorológicas medidas no mesmo momento, uma vez que as variáveis meteorológicas possuem forte relação entre si. Testes foram executados para mostrar a performance do Mannga comparado com outros dois métodos comumente utilizados na área. Os resultados alcançados atingiram uma boa precisão, principalmente relacionado ao desafio de preencher valores em dados que ocorrem em sequência. As principais vantagens do Mannga são a sua flexibilidade em manipular diferentes tipos de dados meteorológicos, a habilidade de selecionar as melhores variáveis para auxiliar no preenchimento das falhas e a capacidade de lidar com falhas sequenciais. Além disso, o método está disponível publicamente na linguagem de programação Java.</description><subject>Algorithms</subject><subject>algoritmos genéticos</subject><subject>Artificial neural networks</subject><subject>dados multivariados</subject><subject>Failures</subject><subject>Genetic algorithms</subject><subject>Handling</subject><subject>Java</subject><subject>Lidar</subject><subject>Meteorological data</subject><subject>Missing data</subject><subject>Neural networks</subject><subject>redes neurais artificiais</subject><subject>software livre</subject><issn>0102-7786</issn><issn>1982-4351</issn><issn>1982-4351</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>DOA</sourceid><recordid>eNpNkE1LAzEQhoMoWKt3jwueVyeZfK2elmproa0geg7ZbFK3rE3Nbg_-e1srxdPAOy_PDA8h1xRuqSjgDiiwXCktETkAihMyoIVmOUdBT8nguD4nF123ApBApRiQh3m5WEzK-6zMXmO17fps7vuPWGchpmxiN9m4adtmvdzHPqbYxmXjbJs92t5ekrNg285f_c0heR8_vY2e89nLZDoqZ7lDRJErxwtUAgoWaq58JSGwqpCgGVOVZspKJqi3IciKC-8ZssC9Qsc5x6KyiEMyPXDraFdmk5pPm75NtI35DWJaGpv6xrXecArai0ogpZy7QAuupajB6-A4BEV3rJsDa5Pi19Z3vVnFbVrv3jeMaWSSohS7FhxaLsWuSz4cr1Iwe91m79P8040_wR5tLg</recordid><startdate>20190601</startdate><enddate>20190601</enddate><creator>Ventura, Thiago Meirelles</creator><creator>Martins, Claudia Aparecida</creator><creator>Figueiredo, Josiel Maimone de</creator><creator>Oliveira, Allan Gonçalves de</creator><creator>Montanher, Johnata Rodrigo Pinheiro</creator><general>Sociedade Brasileira de Meteorologia</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7QH</scope><scope>7TG</scope><scope>7UA</scope><scope>C1K</scope><scope>F1W</scope><scope>H96</scope><scope>H97</scope><scope>KL.</scope><scope>L.G</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-3758-5466</orcidid><orcidid>https://orcid.org/0000-0001-7861-8896</orcidid><orcidid>https://orcid.org/0000-0002-6352-9548</orcidid><orcidid>https://orcid.org/0000-0003-4827-1048</orcidid><orcidid>https://orcid.org/0000-0001-8569-7684</orcidid></search><sort><creationdate>20190601</creationdate><title>MANNGA: A Robust Method for Gap Filling Meteorological Data</title><author>Ventura, Thiago Meirelles ; Martins, Claudia Aparecida ; Figueiredo, Josiel Maimone de ; Oliveira, Allan Gonçalves de ; Montanher, Johnata Rodrigo Pinheiro</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3335-7c49375092fd47eb60f2b9608227b827a6251eaff6b45ee232f4e73c44439ba33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng ; por</language><creationdate>2019</creationdate><topic>Algorithms</topic><topic>algoritmos genéticos</topic><topic>Artificial neural networks</topic><topic>dados multivariados</topic><topic>Failures</topic><topic>Genetic algorithms</topic><topic>Handling</topic><topic>Java</topic><topic>Lidar</topic><topic>Meteorological data</topic><topic>Missing data</topic><topic>Neural networks</topic><topic>redes neurais artificiais</topic><topic>software livre</topic><toplevel>online_resources</toplevel><creatorcontrib>Ventura, Thiago Meirelles</creatorcontrib><creatorcontrib>Martins, Claudia Aparecida</creatorcontrib><creatorcontrib>Figueiredo, Josiel Maimone de</creatorcontrib><creatorcontrib>Oliveira, Allan Gonçalves de</creatorcontrib><creatorcontrib>Montanher, Johnata Rodrigo Pinheiro</creatorcontrib><collection>CrossRef</collection><collection>Aqualine</collection><collection>Meteorological &amp; Geoastrophysical 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 &amp; Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy &amp; Non-Living Resources</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) 3: Aquatic Pollution &amp; Environmental Quality</collection><collection>Meteorological &amp; Geoastrophysical Abstracts - Academic</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) Professional</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Revista Brasileira de Meteorologia</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ventura, Thiago Meirelles</au><au>Martins, Claudia Aparecida</au><au>Figueiredo, Josiel Maimone de</au><au>Oliveira, Allan Gonçalves de</au><au>Montanher, Johnata Rodrigo Pinheiro</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>MANNGA: A Robust Method for Gap Filling Meteorological Data</atitle><jtitle>Revista Brasileira de Meteorologia</jtitle><date>2019-06-01</date><risdate>2019</risdate><volume>34</volume><issue>2</issue><spage>315</spage><epage>323</epage><pages>315-323</pages><issn>0102-7786</issn><issn>1982-4351</issn><eissn>1982-4351</eissn><abstract>Abstract This paper presents Mannga (Multiple variables with Artificial Neural Network and Genetic Algorithm), a method designed for gap filling meteorological data. The main approach is to estimate the missing data based on values of other meteorological variables measured at the same time in the same local, since the meteorological variables are strongly related. Experimental tests showed the performance of Mannga compared with other two methods typically used by researches in this area. Good results were achieved, with high accuracy even for sequential failures, which is a big challenge for researchers. The core advantages of Mannga are the flexibility of handling different types of meteorological data, the ability of select the best variables to assist the gap filling and the capacity to deal with sequential failures. Moreover, the method is available to public use with the Java programming language. Resumo Este trabalho apresenta o método Mannga (Multiple variables with Artificial Neural Network and Genetic Algorithm), desenvolvido para preencher falhas em dados meteorológicos. A ideia principal é preencher as falhas baseando-se nos valores de outras variáveis meteorológicas medidas no mesmo momento, uma vez que as variáveis meteorológicas possuem forte relação entre si. Testes foram executados para mostrar a performance do Mannga comparado com outros dois métodos comumente utilizados na área. Os resultados alcançados atingiram uma boa precisão, principalmente relacionado ao desafio de preencher valores em dados que ocorrem em sequência. As principais vantagens do Mannga são a sua flexibilidade em manipular diferentes tipos de dados meteorológicos, a habilidade de selecionar as melhores variáveis para auxiliar no preenchimento das falhas e a capacidade de lidar com falhas sequenciais. Além disso, o método está disponível publicamente na linguagem de programação Java.</abstract><cop>Rio de Janeiro</cop><pub>Sociedade Brasileira de Meteorologia</pub><doi>10.1590/0102-77863340035</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0002-3758-5466</orcidid><orcidid>https://orcid.org/0000-0001-7861-8896</orcidid><orcidid>https://orcid.org/0000-0002-6352-9548</orcidid><orcidid>https://orcid.org/0000-0003-4827-1048</orcidid><orcidid>https://orcid.org/0000-0001-8569-7684</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0102-7786
ispartof Revista Brasileira de Meteorologia, 2019-06, Vol.34 (2), p.315-323
issn 0102-7786
1982-4351
1982-4351
language eng ; por
recordid cdi_proquest_journals_2283261365
source DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals
subjects Algorithms
algoritmos genéticos
Artificial neural networks
dados multivariados
Failures
Genetic algorithms
Handling
Java
Lidar
Meteorological data
Missing data
Neural networks
redes neurais artificiais
software livre
title MANNGA: A Robust Method for Gap Filling Meteorological Data
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T10%3A46%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=MANNGA:%20A%20Robust%20Method%20for%20Gap%20Filling%20Meteorological%20Data&rft.jtitle=Revista%20Brasileira%20de%20Meteorologia&rft.au=Ventura,%20Thiago%20Meirelles&rft.date=2019-06-01&rft.volume=34&rft.issue=2&rft.spage=315&rft.epage=323&rft.pages=315-323&rft.issn=0102-7786&rft.eissn=1982-4351&rft_id=info:doi/10.1590/0102-77863340035&rft_dat=%3Cproquest_doaj_%3E2283261365%3C/proquest_doaj_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2283261365&rft_id=info:pmid/&rft_doaj_id=oai_doaj_org_article_4108e5b531144cf194865d0e8fc40f71&rfr_iscdi=true