Repository logo
 
Publication

Automated Discovery of Relationships, Models, and Principles in Ecology

dc.contributor.authorCardoso, Pedro
dc.contributor.authorVeiga Branco, Vasco
dc.contributor.authorBorges, Paulo A.V.
dc.contributor.authorCarvalho, José Carlos
dc.contributor.authorRigal, François
dc.contributor.authorGabriel, Rosalina
dc.contributor.authorMammola, Stefano
dc.contributor.authorCascalho, José Manuel
dc.contributor.authorCorreia, Luís
dc.date.accessioned2021-03-10T18:22:41Z
dc.date.available2021-03-10T18:22:41Z
dc.date.issued2020-12
dc.description.abstractEcological systems are the quintessential complex systems, involving numerous high-order interactions and non-linear relationships. The most used statistical modeling techniques can hardly accommodate the complexity of ecological patterns and processes. Finding hidden relationships in complex data is now possible using massive computational power, particularly by means of artificial intelligence and machine learning methods. Here we explored the potential of symbolic regression (SR), commonly used in other areas, in the field of ecology. Symbolic regression searches for both the formal structure of equations and the fitting parameters simultaneously, hence providing the required flexibility to characterize complex ecological systems. Although the method here presented is automated, it is part of a collaborative human–machine effort and we demonstrate ways to do it. First, we test the robustness of SR to extreme levels of noise when searching for the species-area relationship. Second, we demonstrate how SR can model species richness and spatial distributions. Third, we illustrate how SR can be used to find general models in ecology, namely new formulas for species richness estimators and the general dynamic model of oceanic island biogeography. We propose that evolving free-form equations purely from data, often without prior human inference or hypotheses, may represent a very powerful tool for ecologists and biogeographers to become aware of hidden relationships and suggest general theoretical models and principles.en
dc.description.sponsorshipPC and VB were supported by Kone Foundation. PB and FR were partly funded by the project FCT-PTDC/BIABIC/119255/2010 - Biodiversity on oceanic islands: toward a unified theory. LC was supported by FCT through LASIGE Research Unit, ref. UIDB, UIDP/00408/2020. SM acknowledges support from the European Commission through Horizon 2020 Marie Sklodowska-Curie Actions (MSCA) individual fellowships (Grant no. 882221).en
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationCardoso, P., Branco, V.V., Borges, P.A.V., Carvalho, J.C., Rigal, F., Gabriel, R., Mammola, S., Cascalho, J. & Correia, L. (2020). Automated discovery of relationships, models and principles in ecology. "Frontiers in Ecology and Evolution", 8, 530135. DOI:10.3389/fevo.2020.530135en
dc.identifier.doi10.3389/fevo.2020.530135pt_PT
dc.identifier.issn1948-6596
dc.identifier.urihttp://hdl.handle.net/10400.3/5778
dc.identifier.wos000601582100001
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherFrontiers Mediapt_PT
dc.relationBiodiversity on oceanic islands: towards a unified theory
dc.relation.publisherversionhttps://www.frontiersin.org/articles/10.3389/fevo.2020.530135/fullpt_PT
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/pt_PT
dc.subjectArtificial Intelligenceen
dc.subjectEcological Complexityen
dc.subjectEvolutionary Computationen
dc.subjectGenetic Programmingen
dc.subjectSpecies Richness Estimationen
dc.subjectSpecies-area Relationshipen
dc.subjectSpecies Distribution Modelingen
dc.subjectSymbolic Regressionen
dc.titleAutomated Discovery of Relationships, Models, and Principles in Ecologyen
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleBiodiversity on oceanic islands: towards a unified theory
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/3599-PPCDT/PTDC%2FBIA-BIC%2F119255%2F2010/PT
oaire.citation.conferencePlaceSwitzerlanden
oaire.citation.endPage12pt_PT
oaire.citation.startPage1pt_PT
oaire.citation.titleFrontiers in Ecology and Evolutionen
oaire.citation.volume8pt_PT
oaire.fundingStream3599-PPCDT
person.familyNameCardoso
person.familyNameVeiga Branco
person.familyNameBorges
person.familyNameCarvalho
person.familyNameRigal
person.familyNameGabriel
person.familyNameVeiga Ribeiro Cascalho
person.givenNamePedro
person.givenNameVasco
person.givenNamePaulo
person.givenNameJosé Carlos
person.givenNameFrançois
person.givenNameRosalina
person.givenNameJosé Manuel
person.identifier829215
person.identifierhttp://scholar.google.pt/citat
person.identifier.ciencia-id3118-EA4B-B8A3
person.identifier.ciencia-idFA1A-C9CB-9C29
person.identifier.ciencia-idC71D-B386-F49D
person.identifier.ciencia-idE315-82D2-C35D
person.identifier.ciencia-idF212-6D82-7BA9
person.identifier.ciencia-id5E17-CA1F-1397
person.identifier.orcid0000-0001-8119-9960
person.identifier.orcid0000-0001-7797-3183
person.identifier.orcid0000-0002-8448-7623
person.identifier.orcid0000-0001-6852-5207
person.identifier.orcid0000-0001-6882-1591
person.identifier.orcid0000-0002-3550-8010
person.identifier.orcid0000-0002-5176-4882
person.identifier.ridA-8820-2008
person.identifier.ridB-7996-2019
person.identifier.ridB-2780-2008
person.identifier.scopus-author-id36112709400
person.identifier.scopus-author-id7003533390
person.identifier.scopus-author-id55924714000
person.identifier.scopus-author-id7103316062
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublicationc3ff48e6-cddc-453a-8d17-dc37089270c9
relation.isAuthorOfPublication47307c92-6ccd-4a2f-b85c-03d0155acd28
relation.isAuthorOfPublicationd9716a90-cc3e-44d0-adc1-6933e3786278
relation.isAuthorOfPublication5e8bc5d0-ceb7-4863-9a09-59dcbe1fc3bd
relation.isAuthorOfPublication340242ab-3a34-4eef-9c47-12aa6b058bea
relation.isAuthorOfPublication5d291476-f37b-4425-a72e-55c7443d4087
relation.isAuthorOfPublication2ce40ad2-b67a-4797-875c-bba6989fbac4
relation.isAuthorOfPublication.latestForDiscovery5d291476-f37b-4425-a72e-55c7443d4087
relation.isProjectOfPublication06fbea24-58be-4bad-8ec2-4c8d8d5ae0d9
relation.isProjectOfPublication.latestForDiscovery06fbea24-58be-4bad-8ec2-4c8d8d5ae0d9

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
P1657_Cardoso_2020_FrontiersEcologyEvolution.pdf
Size:
817.75 KB
Format:
Adobe Portable Document Format