RT journal article
T1 Forecasting PM10 in the Bay of Algeciras Based on Regression Models
A1 Palomares Salas, José Carlos
A1 González de la Rosa, Juan José
A1 Agüera Pérez, Agustín
A1 Sierra Fernández, José María
A1 Florencias Oliveros, Olivia
A2 Ingeniería de Sistemas y AutomáticaTecnología Electrónica y Electrónica
K1 time-series forecasting
K1 regression models
K1 artificial neural networks
K1 on-site measurements
K1 exogenous information
AB Different forecasting methodologies, classified into parametric and nonparametric, werestudied in order to predict the average concentration of PM10 over the course of 24 h. The comparisonof the forecasting models was based on four quality indexes (Pearson’s correlation coefficient,the index of agreement, the mean absolute error, and the root mean squared error). The proposedexperimental procedure was put into practice in three urban centers belonging to the Bay of Algeciras(Andalusia, Spain). The prediction results obtained with the proposed models exceed those obtainedwith the reference models through the introduction of low-quality measurements as exogenousinformation. This proves that it is possible to improve performance by using additional informationfrom the existing nonlinear relationships between the concentration of the pollutants and themeteorological variables.
PB MDPI
SN 2071-1050
YR 2019
FD 2019-02
LK http://hdl.handle.net/10498/21174
UL http://hdl.handle.net/10498/21174
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 21-sep-2026