Logo do repositório
 
Publicação

Artificial intelligence for biodiversity: Exploring the potential of recurrent neural networks in forecasting arthropod dynamics based on time series

2025-02-01Artigo de investigação Acesso aberto
Ver registo simples
datacite.subject.fosCiências Naturais::Ciências Biológicas
datacite.subject.sdg15:Proteger a Vida Terrestre
dc.contributor.authorLhoumeau, Sébastien Georges André
dc.contributor.authorPinelo, João
dc.contributor.authorBorges, P.A.V.
dc.date.accessioned2026-01-26T10:05:36Z
dc.date.available2026-01-26T10:05:36Z
dc.date.issued2025-02-01
dc.description.abstractABSTRACT: In the current biodiversity crisis, the increasing demand for effective conservation tools aligns with significant advancements in artificial intelligence (AI). There is the need for the development of more robust and accurate forecasting methods, ultimately enhancing our understanding of ecological dynamics and supporting the formulation of effective conservation strategies. This research conducted a comparative analysis of Local Polynomial Regression (LOESS), Seasonal Autoregressive Integrated Moving Average (SARIMA), and Recurrent Neural Network (RNN) models for time-series prediction. Using a unique Long-Term Monitoring Program for island forest arthropods (2012–2023), wherein we selected the 39 most prevalent species collected using SLAM (Sea Land Air Malaise) traps within a native forest fragment on Terceira Island in the Azores archipelago. The results indicate that RNN outperformed LOESS in terms of both goodness of fit and overall accuracy. Although RNN did not surpass classical SARIMA in data prediction, it demonstrated superior goodness-of-fit on the training dataset. Furthermore, we investigated extinction and invasion scenarios within the Terceira arthropod assemblage, providing insight into broader implications and avenues for future research. This study discusses the utility and limitations of RNN models in biodiversity conservation through various scenarios. It contributes to the ongoing discourse at the convergence of conservation, ecology, and artificial intelligence (AI), highlighting advancements and innovative solutions crucial for the effective implementation of conservation strategies.eng
dc.identifier.citationLhoumeau, S., Pinelo, J., & Borges, P. A. V. (2025). Artificial intelligence for biodiversity: exploring the potential of recurrent neural networks in rorecasting arthropod dynamics based on time series. Ecological Indicators, 171, 113119. DOI:10.1016/j.ecolind.2025.113119
dc.identifier.doi10.1016/j.ecolind.2025.113119
dc.identifier.eissn1872-7034
dc.identifier.issn1470-160X
dc.identifier.urihttp://hdl.handle.net/10400.3/8801
dc.language.isoeng
dc.peerreviewedyes
dc.publisherElsevier
dc.relation.hasversionhttps://www.sciencedirect.com/science/article/pii/S1470160X25000482?via%3Dihub
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectConservation scenario
dc.subjectEcological modelling
dc.subjectAzores arthropods
dc.subjectMachine learning
dc.subjectLong-term ecological data
dc.subjectModel comparison
dc.titleArtificial intelligence for biodiversity: Exploring the potential of recurrent neural networks in forecasting arthropod dynamics based on time serieseng
dc.typeresearch article
dcterms.referenceshttps://doi. org/10.1016/j.ecolind.2025.113119
dspace.entity.typePublication
oaire.citation.endPage14
oaire.citation.issue113119
oaire.citation.startPage1
oaire.citation.titleEcological Indicators
oaire.citation.volume171
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameLhoumeau
person.familyNameBorges
person.givenNameSébastien Georges André
person.givenNamePaulo
person.identifier829215
person.identifier.ciencia-id9711-DA5E-9A4A
person.identifier.ciencia-idFA1A-C9CB-9C29
person.identifier.orcid0000-0002-8448-7623
person.identifier.ridB-2780-2008
person.identifier.scopus-author-id7003533390
relation.isAuthorOfPublication92eb17df-9912-4f7b-997a-c9b5d08ed739
relation.isAuthorOfPublicationd9716a90-cc3e-44d0-adc1-6933e3786278
relation.isAuthorOfPublication.latestForDiscovery92eb17df-9912-4f7b-997a-c9b5d08ed739

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
P2805_LHOUMEAU_2025_Artificial intelligence for biodiversity exploring the potential of recurrent neural networks in rorecasting a.pdf
Tamanho:
14.35 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
1.73 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

GBA - Artigos em Revistas Internacionais / Articles in International Journals