Correlation of air pollution and meteorological data using neural networks

被引:11
作者
Slini, T [1 ]
Karatzas, K [1 ]
Moussiopoulos, N [1 ]
机构
[1] Aristotle Univ Thessaloniki, Lab Heat Transfer & Environm Engn, GR-54124 Thessaloniki, Greece
关键词
forecasting; neural networks; environmental informatics; multi-layer perceptons;
D O I
10.1504/IJEP.2003.004279
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
In order to develop an environmental forecasting tool, the Neural Network method of computational intelligence is investigated. For this purpose, hourly and daily time series of CO, NO2 and O-3, as well as a variety of meteorological variables are employed in various multi-layer percepton (MLP) models, in order to provide reliable air quality forecasts, using as a test case the city of Athens, Greece. The performance of the two most satisfactory models are presented thoroughly and compared using certain statistical indices. Results verify both the potential and the complicated nature of the method.
引用
收藏
页码:218 / 229
页数:12
相关论文
共 21 条
[1]  
BALKIN SD, 2000, THESIS BUSINESS ADM
[2]   Prediction of ambient PM10 and toxic metals using artificial neural networks [J].
Chelani, AB ;
Gajghate, DG ;
Hasan, MZ .
JOURNAL OF THE AIR & WASTE MANAGEMENT ASSOCIATION, 2002, 52 (07) :805-810
[3]   A comparison of nonlinear regression and neural network models for ground-level ozone forecasting [J].
Cobourn, WG ;
Dolcine, L ;
French, M ;
Hubbard, MC .
JOURNAL OF THE AIR & WASTE MANAGEMENT ASSOCIATION, 2000, 50 (11) :1999-2009
[4]   Comparing neural networks and regression models for ozone forecasting [J].
Comrie, AC .
JOURNAL OF THE AIR & WASTE MANAGEMENT ASSOCIATION, 1997, 47 (06) :653-663
[5]   Moderating the influence of meteorological conditions on ambient ozone concentrations [J].
Flaum, JB ;
Rao, ST ;
Zurbenko, IG .
JOURNAL OF THE AIR & WASTE MANAGEMENT ASSOCIATION, 1996, 46 (01) :35-46
[6]   Artificial neural networks (the multilayer perceptron) - A review of applications in the atmospheric sciences [J].
Gardner, MW ;
Dorling, SR .
ATMOSPHERIC ENVIRONMENT, 1998, 32 (14-15) :2627-2636
[7]   MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].
HORNIK, K ;
STINCHCOMBE, M ;
WHITE, H .
NEURAL NETWORKS, 1989, 2 (05) :359-366
[8]   Neural networks and periodic components used in air quality forecasting [J].
Kolehmainen, M ;
Martikainen, H ;
Ruuskanen, J .
ATMOSPHERIC ENVIRONMENT, 2001, 35 (05) :815-825
[9]  
LIPPMAN RP, 1987, IEEE ASSP MAGAZINE
[10]   Neural network model for predicting peak photochemical pollutant levels [J].
Melas, D ;
Kioutsioukis, I ;
Ziomas, IC .
JOURNAL OF THE AIR & WASTE MANAGEMENT ASSOCIATION, 2000, 50 (04) :495-501