Logo do repositório
 
Publicação

Integrating portable x-ray fluorescence and machine learning for soil texture prediction in mangrove ecosystems

2025-10-22Artigo científico Acesso restrito
Ver registo simples
datacite.subject.sdg15:Proteger a Vida Terrestre
datacite.subject.sdg14:Proteger a Vida Marinha
datacite.subject.sdg13:Ação Climática
dc.contributor.authorNunes, Luís
dc.contributor.authorBomfim, Marcela R.
dc.contributor.authorConceição, Joseane N.
dc.contributor.authorCosta, Oldair A. V.
dc.contributor.authorGloaguen, Thomas V.
dc.contributor.authorAlmeida, Maria C.
dc.contributor.authorCruz, Manoel J. M.
dc.contributor.authorJúnior, António B. S. R.
dc.contributor.authorSantos, Jorge A. G.
dc.date.accessioned2026-05-12T08:58:41Z
dc.date.available2026-05-12T08:58:41Z
dc.date.issued2025-10-22
dc.description.abstractThis study investigated the application of portable X-ray fluorescence (pXRF) spectrometry integrated with machine learning (ML) algorithms to predictict soil texture in mangrove ecosystems. This method is a rapid and environmentally friendly alternative to traditional wet chemistry techniques. A total of 360 soil samples were collected from six mangrove sites in Baía de Todos os Santos, Brazil, which including areas influenced by both marine and riverine processes. Particle size distribution (PSD) was analyzed using laser diffraction, and pXRF was employed to quantify the elemental composition of the samples. Nine ML models were evaluated, with Neural Boosted, Boosted Tree, and K-Nearest Neighbors exhibiting superior predictive performance, characterized by a ratio of performance to deviation (RPD) greater than 2.0, a root mean square error (RMSE) below a specified threshold, and a coefficient of determination (R2) reaching up to 0.99. The critical predictors identified included rubidium (Rb), iron (Fe), zinc (Zn), and molybdenum (Mo), which correspond to the unique geochemical processes present in mangrove soils. This study underscores the effectiveness of integrating pXRF with ML for precise soil texture prediction, facilitating the large-scale monitoring of mangrove ecosystems in terms of carbon storage, nutrient cycling, and conservation initiatives. The proposed approach overcomes the limitations associated with conventional methods, offering a cost-effective and non-destructive solution for environmental assessments, which is particularly vital for quantifying ecosystem services in developing countries.eng
dc.identifier.doi10.1007/s41748-025-00812-x
dc.identifier.eissn2509-9434
dc.identifier.issn2509-9426
dc.identifier.urihttp://hdl.handle.net/10400.1/28927
dc.language.isoeng
dc.peerreviewedyes
dc.publisherSpringer
dc.relation.ispartofEarth Systems and Environment
dc.rights.uriN/A
dc.subjectSoil texture
dc.subjectGreen chemistry
dc.subjectEx-site analysis
dc.subjectMachine learning
dc.subjectpXRF
dc.titleIntegrating portable x-ray fluorescence and machine learning for soil texture prediction in mangrove ecosystemseng
dc.typejournal article
dspace.entity.typePublication
oaire.citation.titleEarth Systems and Environment
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameNunes
person.givenNameLuís
person.identifier93800
person.identifier.ciencia-id3112-1FCD-6685
person.identifier.orcid0000-0001-5606-970X
person.identifier.ridM-4647-2013
person.identifier.scopus-author-id7102529511
relation.isAuthorOfPublicationd32d0ac6-6cb6-4f03-afcf-3c80978d469f
relation.isAuthorOfPublication.latestForDiscoveryd32d0ac6-6cb6-4f03-afcf-3c80978d469f

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
s41748-025-00812-x.pdf
Tamanho:
2.49 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
3.46 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções