Prediction of maximum of 24-h average of PM10 concentrations 30 h in advance in Santiago, Chile

被引:95
作者
Perez, P [1 ]
Reyes, J [1 ]
机构
[1] Univ Santiago Chile, Dept Fis, Santiago, Chile
关键词
air pollution prediction; particulate matter; PM; 10; neural networks; meteorology forecast;
D O I
10.1016/S1352-2310(02)00419-3
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
We have developed a neural network based model that uses values of PM 10 concentrations measured until 6 p.m. on the present day plus measured and forecasted values of meteorological variables as input in order to predict the level reached by the maximum of the 24-h moving average (24MA) of PM10 concentration on the next day. We have adjusted the parameters of the model using 1998 data to predict 1999 conditions and 1999 data to forecast 2000 maximum concentrations. We have found that among the relevant meteorological input variables, the forecasted difference between maximum and minimum temperature is the most important. Due to the fact that local authorities impose restrictions to emissions on days when the maximum of 24MA of PM10 concentration is expected to exceed 240 mug/m(3), we have corrected the measured concentrations on these days before evaluating the efficacy of the forecasting model. Percent errors in forecasting the numerical value are of the order of 20%. The performance of the neural network is better than that of a linear model with the same inputs, but the difference being not great is an indication that the right choice of input variables may be more important than the decision to use a linear or a nonlinear model. (C) 2002 Elsevier Science Ltd. All rights reserved.
引用
收藏
页码:4555 / 4561
页数:7
相关论文
共 14 条
[1]   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
[2]   A semi-empirical model for urban PM10 concentrations, and its evaluation against data from an urban measurement network [J].
Kukkonen, J ;
Härkönen, J ;
Karppinen, A ;
Pohjola, M ;
Pietarila, H ;
Koskentalo, T .
ATMOSPHERIC ENVIRONMENT, 2001, 35 (26) :4433-4442
[3]   Relationships of mortality with the fine and coarse fractions of long-term ambient PM10 concentrations in nonsmokers [J].
McDonnell, WF ;
Nishino-Ishikawa, N ;
Petersen, FF ;
Chen, LH ;
Abbey, DE .
JOURNAL OF EXPOSURE ANALYSIS AND ENVIRONMENTAL EPIDEMIOLOGY, 2000, 10 (05) :427-436
[4]   The impact of particulate matter on daily mortality in Bangkok, Thailand [J].
Ostro, B ;
Chestnut, L ;
Vichit-Vadakan, N ;
Laixuthai, A .
JOURNAL OF THE AIR & WASTE MANAGEMENT ASSOCIATION, 1999, 49 :100-107
[5]   Air pollution and health effects: A study of medical visits among children in Santiago, Chile [J].
Ostro, BD ;
Eskeland, GS ;
Sanchez, JM ;
Feyzioglu, T .
ENVIRONMENTAL HEALTH PERSPECTIVES, 1999, 107 (01) :69-73
[6]   Prediction of PM2.5 concentrations several hours in advance using neural networks in Santiago, Chile [J].
Pérez, P ;
Trier, A ;
Reyes, J .
ATMOSPHERIC ENVIRONMENT, 2000, 34 (08) :1189-1196
[7]   Prediction of particulate air pollution using neural techniques [J].
Perez, P ;
Reyes, J .
NEURAL COMPUTING & APPLICATIONS, 2001, 10 (02) :165-171
[8]  
Ritter H., 1992, NEURAL COMPUTATION S
[9]  
Rumelhart D. E., 1986, LEARNING INTERNAL RE, P318
[10]  
Silva C, 2001, ENVIRONMETRICS, V12, P147, DOI 10.1002/1099-095X(200103)12:2<147::AID-ENV451>3.3.CO