Comparison of several linear statistical models to predict tropospheric ozone concentrations

• Tipo: Artigo em Revista Científica Internacional
• Data: 2012

Autores

J. C. M. Pires (Autor) FEUP; M. C. M. Alvim Ferraz (Autor) FEUP; M. C. Pereira (Autor) FEUP; F. G. Martins (Autor) FEUP

Revista

Título: Journal of Statistical Computation and Simulation

Vol. 82 Nº 2

Páginas: 183-192

ISSN: 0094-9655

Editora: Taylor & Francis

Indexação

ISI Web of Knowledge - 7 Citações

ISI Web of Science

Scopus - 9 Citações

Classificação Científica

FOS: Ciências exactas e naturais > Ciências da terra e ciências do ambiente

CORDIS: Ciências Naturais > Ciências do ambiente

Projetos Associados

PEst-C/EQB/UI0511/2011 - PROJECTO ESTRATÉGICO - UI 511 - 2011-2012

Outras Informações

ID Authenticus: P-002-GQ1

DOI: 10.1080/00949655.2011.623233

Abstract (EN): This study aims to evaluate the performance of five linear statistical models in the prediction of the next-day hourly average ozone concentrations. The selected models are as follows: (i) multiple linear regression, (ii) principal component regression, (iii) independent component regression (ICR), (iv) quantile regression (QR) and (v) partial least squares regression (PLSR). As far as it has been known, no study comparing the performance of these five linear models for predicting tropospheric ozone concentrations has been presented. Moreover, it is the first time that ICR is applied with this aim. The considered ozone predictors are meteorological data (hourly averages of temperature, relative humidity and wind speed) and environmental data (hourly average concentrations of sulphur dioxide, carbon monoxide, nitrogen oxide, nitrogen dioxide and ozone) of the previous day collected at an urban site with traffic influences. The analysed periods were May and June 2003. The QR model, which tries to model the entire distribution of the O-3 concentrations, presents a better performance in the training step, because it tries to model the entire distribution of the O-3 concentrations. However, it presents worst predictions in the test step. This means that a new procedure that is better than the one applied (k-nearest neighbours algorithm) and can estimate the percentiles of the output variable in the test data set with more precision should be found. From the five statistical models tested in this study, the PLSR model presents the best predictions of the tropospheric ozone concentrations.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 10