PLSR and ANN estimation models for PM10-bound heavy metals in Dunkerque (Northern France)

Ver/Abrir
Identificadores
URI: http://hdl.handle.net/10902/7726
ISSN: 2283-5954
Compartir
Estadísticas
Ver Estadísticas
Google Scholar
Registro completo
Mostrar el registro completo DC
Autoría
Santos Bregel, GermánAutoridad Unican; Fernández Olmo, IgnacioAutoridad Unican; Irabien Gulías, ÁngelAutoridad Unican; Ledoux, Frédéric; Courcot, Dominique
Fecha
2014-12-15
Derechos
© Los autores. The policy of ProScience is to provide full access to the bibliographic contents if a correct citation to the original publication is given (rules as in CC0). Therefore, the authors authorize to i) print the articles; ii) redistribute or republish (e.g., display in repositories, web platforms, etc.) the articles; iii) translate the article; iv) reuse portions of the article (text, data, tables, figures) in other publications (articles, book, etc.).
Publicado en
ProScience, 2014, 1, 100-105
1st International Conference on Atmospheric Dust (DUST 2014), Castellaneta Marina, Italy
Editorial
Digilabs
Palabras clave
Partial least squares regression (PLSR)
Artificial neural networks (ANN)
Statistical models
Particulate matter
PM10
Heavy metals
Resumen/Abstract
The aim of this work is to develop statistical estimation models of some EU regulated heavy metal levels (Pb, Ni) and some non-regulated heavy metal levels (Mn, V and Cr) in the ambient air of the city of Dunkerque (Northern France) so that they might be used for air quality assessment as an alternative to experimental measurements, since these levels are relatively low compared to the EU limit/target values and other air quality guidelines. Three different approaches were considered: Partial Least Squares Regression (PLSR), Artificial Neural Networks (ANN) and Principal Component Analysis (PCA) coupled with ANN. External validation results evidence that PLSR and ANN-based statistical models for regulated metals and for Mn and V provide adequate mean values estimations while fulfill the EU uncertainty requirements.
Colecciones a las que pertenece