Prediction of dynamical systems by symbolic regression.
Identifieur interne : 001C16 ( PubMed/Corpus ); précédent : 001C15; suivant : 001C17Prediction of dynamical systems by symbolic regression.
Auteurs : Markus Quade ; Markus Abel ; Kamran Shafi ; Robert K. Niven ; Bernd R. NoackSource :
- Physical review. E [ 2470-0053 ] ; 2016.
Abstract
We study the modeling and prediction of dynamical systems based on conventional models derived from measurements. Such algorithms are highly desirable in situations where the underlying dynamics are hard to model from physical principles or simplified models need to be found. We focus on symbolic regression methods as a part of machine learning. These algorithms are capable of learning an analytically tractable model from data, a highly valuable property. Symbolic regression methods can be considered as generalized regression methods. We investigate two particular algorithms, the so-called fast function extraction which is a generalized linear regression algorithm, and genetic programming which is a very general method. Both are able to combine functions in a certain way such that a good model for the prediction of the temporal evolution of a dynamical system can be identified. We illustrate the algorithms by finding a prediction for the evolution of a harmonic oscillator based on measurements, by detecting an arriving front in an excitable system, and as a real-world application, the prediction of solar power production based on energy production observations at a given site together with the weather forecast.
DOI: 10.1103/PhysRevE.94.012214
PubMed: 27575130
Links to Exploration step
pubmed:27575130Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Prediction of dynamical systems by symbolic regression.</title>
<author><name sortKey="Quade, Markus" sort="Quade, Markus" uniqKey="Quade M" first="Markus" last="Quade">Markus Quade</name>
<affiliation><nlm:affiliation>Universität Potsdam, Institut für Physik und Astronomie, Karl-Liebknecht-Straße 24/25, 14476 Potsdam, Germany and Ambrosys GmbH, David-Gilly-Straße 1, 14469 Potsdam, Germany.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Abel, Markus" sort="Abel, Markus" uniqKey="Abel M" first="Markus" last="Abel">Markus Abel</name>
<affiliation><nlm:affiliation>Universität Potsdam, Institut für Physik und Astronomie, Karl-Liebknecht-Straße 24/25, 14476 Potsdam, Germany and Ambrosys GmbH, David-Gilly-Straße 1, 14469 Potsdam, Germany.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Shafi, Kamran" sort="Shafi, Kamran" uniqKey="Shafi K" first="Kamran" last="Shafi">Kamran Shafi</name>
<affiliation><nlm:affiliation>School of Engineering and Information Technology, University of New South Wales, Canberra ACT 2600, Australia.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Niven, Robert K" sort="Niven, Robert K" uniqKey="Niven R" first="Robert K" last="Niven">Robert K. Niven</name>
<affiliation><nlm:affiliation>School of Engineering and Information Technology, University of New South Wales, Canberra ACT 2600, Australia.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Noack, Bernd R" sort="Noack, Bernd R" uniqKey="Noack B" first="Bernd R" last="Noack">Bernd R. Noack</name>
<affiliation><nlm:affiliation>Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur LIMSI-CNRS, BP 133, 91403 Orsay cedex, France and Institut für Strömungsmechanik, Technische Universität Braunschweig, Hermann-Blenk-Straße 37, 38108 Braunschweig, Germany.</nlm:affiliation>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2016">2016</date>
<idno type="RBID">pubmed:27575130</idno>
<idno type="pmid">27575130</idno>
<idno type="doi">10.1103/PhysRevE.94.012214</idno>
<idno type="wicri:Area/PubMed/Corpus">001C16</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">001C16</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Prediction of dynamical systems by symbolic regression.</title>
<author><name sortKey="Quade, Markus" sort="Quade, Markus" uniqKey="Quade M" first="Markus" last="Quade">Markus Quade</name>
<affiliation><nlm:affiliation>Universität Potsdam, Institut für Physik und Astronomie, Karl-Liebknecht-Straße 24/25, 14476 Potsdam, Germany and Ambrosys GmbH, David-Gilly-Straße 1, 14469 Potsdam, Germany.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Abel, Markus" sort="Abel, Markus" uniqKey="Abel M" first="Markus" last="Abel">Markus Abel</name>
<affiliation><nlm:affiliation>Universität Potsdam, Institut für Physik und Astronomie, Karl-Liebknecht-Straße 24/25, 14476 Potsdam, Germany and Ambrosys GmbH, David-Gilly-Straße 1, 14469 Potsdam, Germany.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Shafi, Kamran" sort="Shafi, Kamran" uniqKey="Shafi K" first="Kamran" last="Shafi">Kamran Shafi</name>
<affiliation><nlm:affiliation>School of Engineering and Information Technology, University of New South Wales, Canberra ACT 2600, Australia.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Niven, Robert K" sort="Niven, Robert K" uniqKey="Niven R" first="Robert K" last="Niven">Robert K. Niven</name>
<affiliation><nlm:affiliation>School of Engineering and Information Technology, University of New South Wales, Canberra ACT 2600, Australia.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Noack, Bernd R" sort="Noack, Bernd R" uniqKey="Noack B" first="Bernd R" last="Noack">Bernd R. Noack</name>
<affiliation><nlm:affiliation>Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur LIMSI-CNRS, BP 133, 91403 Orsay cedex, France and Institut für Strömungsmechanik, Technische Universität Braunschweig, Hermann-Blenk-Straße 37, 38108 Braunschweig, Germany.</nlm:affiliation>
</affiliation>
</author>
</analytic>
<series><title level="j">Physical review. E</title>
<idno type="eISSN">2470-0053</idno>
<imprint><date when="2016" type="published">2016</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">We study the modeling and prediction of dynamical systems based on conventional models derived from measurements. Such algorithms are highly desirable in situations where the underlying dynamics are hard to model from physical principles or simplified models need to be found. We focus on symbolic regression methods as a part of machine learning. These algorithms are capable of learning an analytically tractable model from data, a highly valuable property. Symbolic regression methods can be considered as generalized regression methods. We investigate two particular algorithms, the so-called fast function extraction which is a generalized linear regression algorithm, and genetic programming which is a very general method. Both are able to combine functions in a certain way such that a good model for the prediction of the temporal evolution of a dynamical system can be identified. We illustrate the algorithms by finding a prediction for the evolution of a harmonic oscillator based on measurements, by detecting an arriving front in an excitable system, and as a real-world application, the prediction of solar power production based on energy production observations at a given site together with the weather forecast.</div>
</front>
</TEI>
<pubmed><MedlineCitation Status="In-Data-Review" Owner="NLM"><PMID Version="1">27575130</PMID>
<DateCreated><Year>2016</Year>
<Month>08</Month>
<Day>31</Day>
</DateCreated>
<DateRevised><Year>2016</Year>
<Month>08</Month>
<Day>31</Day>
</DateRevised>
<Article PubModel="Print-Electronic"><Journal><ISSN IssnType="Electronic">2470-0053</ISSN>
<JournalIssue CitedMedium="Internet"><Volume>94</Volume>
<Issue>1-1</Issue>
<PubDate><Year>2016</Year>
<Month>Jul</Month>
</PubDate>
</JournalIssue>
<Title>Physical review. E</Title>
<ISOAbbreviation>Phys Rev E</ISOAbbreviation>
</Journal>
<ArticleTitle>Prediction of dynamical systems by symbolic regression.</ArticleTitle>
<Pagination><MedlinePgn>012214</MedlinePgn>
</Pagination>
<ELocationID EIdType="doi" ValidYN="Y">10.1103/PhysRevE.94.012214</ELocationID>
<Abstract><AbstractText>We study the modeling and prediction of dynamical systems based on conventional models derived from measurements. Such algorithms are highly desirable in situations where the underlying dynamics are hard to model from physical principles or simplified models need to be found. We focus on symbolic regression methods as a part of machine learning. These algorithms are capable of learning an analytically tractable model from data, a highly valuable property. Symbolic regression methods can be considered as generalized regression methods. We investigate two particular algorithms, the so-called fast function extraction which is a generalized linear regression algorithm, and genetic programming which is a very general method. Both are able to combine functions in a certain way such that a good model for the prediction of the temporal evolution of a dynamical system can be identified. We illustrate the algorithms by finding a prediction for the evolution of a harmonic oscillator based on measurements, by detecting an arriving front in an excitable system, and as a real-world application, the prediction of solar power production based on energy production observations at a given site together with the weather forecast.</AbstractText>
</Abstract>
<AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Quade</LastName>
<ForeName>Markus</ForeName>
<Initials>M</Initials>
<AffiliationInfo><Affiliation>Universität Potsdam, Institut für Physik und Astronomie, Karl-Liebknecht-Straße 24/25, 14476 Potsdam, Germany and Ambrosys GmbH, David-Gilly-Straße 1, 14469 Potsdam, Germany.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Abel</LastName>
<ForeName>Markus</ForeName>
<Initials>M</Initials>
<AffiliationInfo><Affiliation>Universität Potsdam, Institut für Physik und Astronomie, Karl-Liebknecht-Straße 24/25, 14476 Potsdam, Germany and Ambrosys GmbH, David-Gilly-Straße 1, 14469 Potsdam, Germany.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Shafi</LastName>
<ForeName>Kamran</ForeName>
<Initials>K</Initials>
<AffiliationInfo><Affiliation>School of Engineering and Information Technology, University of New South Wales, Canberra ACT 2600, Australia.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Niven</LastName>
<ForeName>Robert K</ForeName>
<Initials>RK</Initials>
<AffiliationInfo><Affiliation>School of Engineering and Information Technology, University of New South Wales, Canberra ACT 2600, Australia.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Noack</LastName>
<ForeName>Bernd R</ForeName>
<Initials>BR</Initials>
<AffiliationInfo><Affiliation>Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur LIMSI-CNRS, BP 133, 91403 Orsay cedex, France and Institut für Strömungsmechanik, Technische Universität Braunschweig, Hermann-Blenk-Straße 37, 38108 Braunschweig, Germany.</Affiliation>
</AffiliationInfo>
</Author>
</AuthorList>
<Language>eng</Language>
<PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType>
</PublicationTypeList>
<ArticleDate DateType="Electronic"><Year>2016</Year>
<Month>07</Month>
<Day>13</Day>
</ArticleDate>
</Article>
<MedlineJournalInfo><Country>United States</Country>
<MedlineTA>Phys Rev E</MedlineTA>
<NlmUniqueID>101676019</NlmUniqueID>
<ISSNLinking>2470-0045</ISSNLinking>
</MedlineJournalInfo>
<CitationSubset>IM</CitationSubset>
</MedlineCitation>
<PubmedData><History><PubMedPubDate PubStatus="received"><Year>2016</Year>
<Month>02</Month>
<Day>15</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="entrez"><Year>2016</Year>
<Month>8</Month>
<Day>31</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="pubmed"><Year>2016</Year>
<Month>8</Month>
<Day>31</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="medline"><Year>2016</Year>
<Month>8</Month>
<Day>31</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
</History>
<PublicationStatus>ppublish</PublicationStatus>
<ArticleIdList><ArticleId IdType="pubmed">27575130</ArticleId>
<ArticleId IdType="doi">10.1103/PhysRevE.94.012214</ArticleId>
</ArticleIdList>
</PubmedData>
</pubmed>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Asie/explor/AustralieFrV1/Data/PubMed/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001C16 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 001C16 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Asie |area= AustralieFrV1 |flux= PubMed |étape= Corpus |type= RBID |clé= pubmed:27575130 |texte= Prediction of dynamical systems by symbolic regression. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i -Sk "pubmed:27575130" \ | HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd \ | NlmPubMed2Wicri -a AustralieFrV1
This area was generated with Dilib version V0.6.33. |