Logo do repositório
 
Publicação

Deep learning for supervised classification of temporal data in ecology

2021-03Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorCapinha, César
dc.contributor.authorCeia-Hasse, Ana
dc.contributor.authorKramer, Andrew M.
dc.contributor.authorMeijer, Christiaan
dc.contributor.institutionInstituto de Higiene e Medicina Tropical (IHMT)
dc.contributor.institutionGlobal Health and Tropical Medicine (GHTM)
dc.contributor.pblElsevier BV
dc.date.accessioned2025-03-18T21:12:22Z
dc.date.available2025-03-18T21:12:22Z
dc.date.issued2021-03
dc.descriptionFunding Information: We thank two reviewers who helped improve this work. CC and ACH were supported by Portuguese National Funds through Funda??o para a Ci?ncia e a Tecnologia [CC: CEECIND/02037/2017, UIDB/00295/2020 and UIDP/00295/2020; ACH: PTDC/SAU-PUB/30089/2017 and GHTM-UID/Multi/04413/2013]. Funding Information: We thank two reviewers who helped improve this work. CC and ACH were supported by Portuguese National Funds through Fundação para a Ciência e a Tecnologia [CC: CEECIND/02037/2017 , UIDB/00295/2020 and UIDP/00295/2020 ; ACH: PTDC/SAU-PUB/30089/2017 and GHTM- UID/Multi/04413/2013 ]. Publisher Copyright: © 2021 The Authors
dc.description.abstractTemporal data is ubiquitous in ecology and ecologists often face the challenge of accurately differentiating these data into predefined classes, such as biological entities or ecological states. The usual approach consists of transforming the time series into user-defined features and then using these features as predictors in conventional statistical or machine learning models. Here we suggest the use of deep learning models as an alternative to this approach. Recent deep learning techniques can perform the classification directly from the time series, eliminating subjective and resource-consuming data transformation steps, and potentially improving classification results. We describe some of the deep learning architectures relevant for time series classification and show how these architectures and their hyper-parameters can be tested and used for the classification problems at hand. We illustrate the approach using three case studies from distinct ecological subdisciplines: i) insect species identification from wingbeat spectrograms; ii) species distribution modelling from climate time series and iii) the classification of phenological phases from continuous meteorological data. The deep learning approach delivered ecologically sensible and accurate classifications demonstrating its potential for wide applicability across subfields of ecology.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent9
dc.format.extent1659875
dc.identifier.doi10.1016/j.ecoinf.2021.101252
dc.identifier.issn1574-9541
dc.identifier.otherPURE: 33835746
dc.identifier.otherPURE UUID: 05acb9de-1759-4d4c-9d24-7a7754382261
dc.identifier.otherScopus: 85101153503
dc.identifier.otherWOS: 000632605900006
dc.identifier.urihttp://hdl.handle.net/10362/180861
dc.identifier.urlhttps://www.scopus.com/pages/publications/85101153503
dc.language.isoeng
dc.peerreviewedyes
dc.subjectDeep learning
dc.subjectEcological prediction
dc.subjectScalability
dc.subjectSequential data
dc.subjectTemporal ecology
dc.subjectTime series
dc.subjectEcology, Evolution, Behavior and Systematics
dc.subjectEcology
dc.subjectModelling and Simulation
dc.subjectEcological Modelling
dc.subjectComputer Science Applications
dc.subjectComputational Theory and Mathematics
dc.subjectApplied Mathematics
dc.titleDeep learning for supervised classification of temporal data in ecologyen
dc.typejournal article
degois.publication.titleEcological Informatics
degois.publication.volume61
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Deep_learning_for_supervised_classification.pdf
Tamanho:
1.58 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (IHMT)