Artificial neural network models for prediction of daily fine particulate matter concentrations in Algiers

被引：0
作者：
M. R. Chellali
H. Abderrahim
A. Hamou
A. Nebatti
J. Janovec
机构：
[1] Slovak University of Technology in Bratislava,Faculty of Materials Science and Technology
[2] University of Oran 1-Ahmed Benbella,Laboratory of Environmental Science and Material Studies
[3] Hydrometeorological Institute for Training and Research-IHFR,Institute of Science and Technology
[4] University Center Ain Témouchent,undefined
来源：
Environmental Science and Pollution Research | 2016年 / 23卷
关键词：
Neural network; Particulate matter; Air pollution; PM; emission forecasting;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Neural network (NN) models were evaluated for the prediction of suspended particulates with aerodynamic diameter less than 10-μm (PM10) concentrations. The model evaluation work considered the sequential hourly concentration time series of PM10, which were measured at El Hamma station in Algiers. Artificial neural network models were developed using a combination of meteorological and time-scale as input variables. The results were rather satisfactory, with values of the coefficient of correlation (R2) for independent test sets ranging between 0.60 and 0.85 and values of the index of agreement (IA) between 0.87 and 0.96. In addition, the root mean square error (RMSE), the mean absolute error (MAE), the normalized mean squared error (NMSE), the absolute relative percentage error (ARPE), the fractional bias (FB), and the fractional variance (FS) were calculated to assess the performance of the model. It was seen that the overall performance of model 3 was better than models 1 and 2.
引用
收藏
页码：14008 / 14017
页数：9
相关论文
共 182 条
[31]  
Dockery DW(2008)Artificial neural network estimation of soil erosion and nutrient concentrations in runoff from land application areas Environ Int 34 592-1411
[32]  
Schwartz J(2006)Forecasting air quality parameters using hybrid neural network modelling Int Tuberc Lung Dis 10 1406-1157
[33]  
Spengler JD(2002)Neural networks and periodic components used in air quality forecasting J Environ Eng 128 1146-124
[34]  
Fontes T(2000)Extensive evaluation of neural network models for the prediction of NO Environ Model Softw 15 101-494
[35]  
Silva LM(2004) and PM Environ Model Softw 19 485-1101
[36]  
Silva MP(2000) concentrations, compared with a deterministic modelling system and measurements in central Helsinki J Air Waste Manage Assoc 52 1096-680
[37]  
Barros N(2004)An online air pollution forecasting system using neural networks J Air Waste Manage Assoc 54 644-910
[38]  
Carvalho AC(2013)Health effects of PM Aerosol Air Qual Res 13 901-334
[39]  
Fuller GW(2007) air pollution in a low-income country: the case of Algiers Water Air Soil Pollut 182 325-327
[40]  
Carslaw DC(2011)Prediction of pollutant levels in Causeway bay area of Hong Kong using an improved neural network model Environ Sci Pollut Res 18 316-1196
12345678910