Multilayer feedforward networks are universal approximators
Neural Networks
Environmental Modelling & Software
Environmental Modelling & Software
Environmental Modelling & Software
A deterministic air quality forecasting system for Torino urban area, Italy
Environmental Modelling & Software
Environmental Modelling & Software
Artificial Intelligence techniques: An introduction to their use for modelling environmental systems
Mathematics and Computers in Simulation
Forecasting peak air pollution levels using NARX models
Engineering Applications of Artificial Intelligence
A feature selection method for air quality forecasting
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Sparse episode identification in environmental datasets: The case of air quality assessment
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
The present research aims at developing an efficient and reliable module, for operational concentration levels of particulate matter with aerodynamic diameter up to 10@mm (PM"1"0) for the city of Thessaloniki. The Thessaloniki urban area is very densely built, with a high degree of motorisation and industrial activities concentration. The increase of emissions mainly from traffic and industry are responsible for the increase in atmospheric pollution levels during the last years. The air quality data sets examined in the current study are collected by a network of monitoring stations operated by the Municipality of Thessaloniki and correspond to PM"1"0 concentrations for the years 1994-2000. In order to provide with an operational air quality forecasting module for PM"1"0, statistical methods are investigated and applied. The presented results demonstrate that CART and Neural Network (NN) methods are capable of capturing PM"1"0 concentration trends, while CART may have a better performance concerning the index of agreement. Methods studied (including linear regression and principal component analysis) demonstrate promising operational forecasting capabilities.