PREDICCIÓN DE LA CALIDAD DEL AIRE: ESTADO DEL ARTE

Jhon Jairo Anaya Diaz

Resumen


En este artículo se describe la forma y los procedimientos que se utilizan para desarrollar el estado del arte de la predicción de la calidad del aire en una zona específica. Se pretende indagar en las referencias utilizadas comparando los distintos métodos de estudio, y observar cuál de estos ofrece las previsiones elaboradas más óptimas, del comportamiento en el tiempo de estos materiales perjudiciales para salud del Hombre. Se clasificará toda la información estudiada, de acuerdo con el método usado y a los contaminantes a evaluar en cada investigación, determinando cuál de estos métodos usados son más pertinentes y cuáles son los que ofrecen mejor eficiencia en la predicción. En esta revisión se encuentra que los métodos más empleados y eficientes son los no lineales, como son las Redes Neuronales con su topología Perceptrón Multicapa. Aunque las versiones Hibridas, también obtienen excelentes resultados en la predicción. Por lo cual sería un buen punto de partida empezar el estudio utilizando este tipo de métodos para el pronóstico de contaminantes.


Texto completo:

PDF

Referencias


Barai, S.V. et al. 2009. Air Quality Forecaster : Moving Window Based. Applications of Soft Computing.

E.Avineri et al., eds. Springer Berlin / Heidelberg. 137-145.

Benghanem,M. and Mellit, A. 2010. Radial Basis Function Network-based prediction of global solar

radiation data: Application for sizing of a stand-alone

photovoltaic system at Al-Madinah, Saudi Arabia.Energy. 35, 9 (Sep. 2010), 3751-3762.

Box, G.E.P., Jenkins, G.M. 1970. Time Series Analysis, Forecasting and Control.

Caselli, M. et al. 2008. A Simple Feedforward Neural Network for the PM10 Forecasting: Comparison with a Radial Basis Function Network and a Multivariate Linear Regression Model. Water, Air, and Soil Pollution. 201, 1-4 (Dec. 2008), 365-377.

Cobourn, W.G. 2010. An enhanced PM2.5 air quality forecast model based on nonlinear regression

andback-trajectory concentrations. Atmospheric Environment. 44, 25 (Aug. 2010), 3015-3023.

Corani, G. 2005. Air quality prediction in Milan: feed-forward neural networks, pruned neural networks and lazy learning. Ecological Modelling. 185, 2-4 (Jul. 2005), 513-529.

Domańska, D. and Wojtylak, M. 2012. Application of fuzzy time series models for

forecasting pollution concentrations. Expert Systems with Applications. 39, 9 (Jul. 2012), 7673-7679.

Dong, M. et al. 2009. PM2.5 concentration prediction using hidden semi-Markov

model-based times series data mining. Expert Systems with Applications. 36, 5 (Jul. 2009), 9046-9055.

Díaz-Robles, L.A. et al. 2008. A hybrid ARIMA and artificial neural networks model to forecast

particulate matter in urban areas: The case of

Temuco, Chile. Atmospheric Environment. 42, 35 (Nov.2008), 8331-8340.

Ecologístas en Acción: 2006. http://www.ecologistasenaccion.org/spip.php?article5681.

Fernando, H.J.S. et al. 2012. Forecasting PM10 in metropolitan areas: Efficacy of neural networks. Environmental pollution (Barking, Essex : 1987). 163, (Apr. 2012), 62-7.

Gardner, M. W. and Dorling, S.R. 1995. Artificial neural networks (the multi-layer feed-forward neural

networks)– A review of applications in the

atmospheric science. Atmospheric Environment. 30, 14/15 (1995), 2627–2636.

Grivas, G. and Chaloulakou, A. 2006. Artificial neural network models for prediction of PM10 hourly

concentrations, in the Greater Area of Athens, Greece. Atmospheric Environment. 40, 7 (Mar. 2006),

2 1 6 - 1 2 2 9 .

Hooyberghs, J. et al. 2005. A neural network forecast for daily average PM concentrations in Belgium.Atmospheric Environment. 39, 18 (Jun. 2005), 3279-3289.

Ibarra-Berastegi, G. et al. 2008. From diagnosis to prognosis for forecasting air pollution using neural

networks: Air pollution monitoring in Bilbao. Environmental Modelling & Software. 23, 5 (May. 2008), 622-637.

Ii, T. et al. 2009. Libro verde - De medio Ambiente Urbano. Ministerio del Medio Ambiente Español.

Isasi Viñuela, P. and Galván León, I. 2004.Redes de

Neuro nas Artificiales Un Enfoque Práctico. Pearson Prentice Hall.

Kaminski, W. 2001. Evaluation of air pollution level by means of artificial neural n e t w o r k - multilayer perceptron. Handbook of Conveying and Handling or Particulates Solids. A. Levy and H. Kalman, eds. 739-744.

Khashei, M. and Bijari, M. 2010. An artificial neural network (p,d,q) model for timeseries forecasting. Expert Systems with Applications. 37, 1 (Jan. 2010), 479-489.

Kukkonen, J. 2003. Extensive evaluation of neural network models for the prediction

of NO2 and PM10 concentrations, compared with a deterministic modelling system and

measurements in central Helsinki. Atmospheric Environment. 37, 32 (Oct. 2003), 4539-4550. Ingeniería Documentos de 52

Kurt, A. and Oktay, A.B. 2010. Forecasting air pollutant indicator levels with geographic models

days in advance using neural networks. Expert Systems with Applications. 37, 12 (Dec. 2010), 7986-7992.

Lee, J.K. and Yum, C.S. 1998. Judgmental adjustment in time series

forecasting using neural networks. Decision Support Systems. 22, 2 (Feb. 1998), 135-154.

Lu, W.-Z. and Wang, D. 2008. Ground-level ozone prediction by support vector machine approach with

a cost-sensitive classification scheme. The Science of the total environment. 395, 2-3 (Jun. 2008), 109-16.

Lu, W.-Z. and Wang, W.-J. 2005. Potential assessment of the “support vector machine” method in

forecasting ambient air pollutant trends. Chemosphere. 59, 5 (Apr. 2005), 693-701.

Lu, W.Z. et al. 2003. Using Improved Neural Networkmodel To Analyze Rsp, Nox And No2 Levels

In Urban Air Inmong Kok, Hong Kong. Environmental Monitoring and Assessment. 87, 2 (2003), 235-254.

Melanie, M. 1996. An Introduction to Genetic Algorithms. Massachusetts Institute of Technology.

Mitchell, T. 1997. Machine Learning.

Mohandes, M. et al. 2000. Use of radial basis functions for estimating monthly mean daily solar radiation. Solar Energy. 68, 2 (Feb. 2000), 161-168.

Moustris, K.P. et al. 2010. 3-Day-Ahead Forecasting of Regional Pollution Index for the Pollutants NO 2 , CO ,

SO 2 , and O 3 Using Artificial Neural Networks in Athens , Greece. Water, Air, & Soil Pollution. 209, 1 (2010), 29-43.

Nilsson, N.J. 2005. Introduction To Machine Learning An Early Draft Of A Proposed Textbook Department of Computer Science. Standorf University.

Niska, H. et al. 2005. Evaluation of an integrated modelling system containing a multi-layer

perceptron model and the numerical weather prediction model HIRLAM for the forecasting of urban airborne pollutant concentrations. Atmospheric Environment. 39, 35 (Nov. 2005), 6524-6536.

Palma, J.T. and Marín, R. 2008. Inteligencia Artificial: Método, técnicas y aplicaciones. McGraw-Hill.

Paschalidou, A.K. et al. 2009. A comparative study on various statistical techniques predicting ozone concentrations : implications to environmental management. Environmental Monitoring and Assessment. 148, 1 (2009), 277-289.

Paschalidou, A.K. and Karakitsios, S. 2011. Forecasting hourly PM 10 concentration in Cyprus through artificial neural networks and multiple regression models : implications to local

environmental management. Environmental Science and Pollution Research. 18, 2 (2011), 316-327.

Perez, P. et al. 2004. Carbon monoxide concentration forecasting in Santiago, Chile. Journal of the Air & Waste Management Association (1995). 54, 8 (Aug. 2004), 908-13. Environment. 40, 16 (May. 2006), 2845-2851.

Perez, P. et al. 2000. Prediction of PM concentrations several hours in advance using neural networks in Santiago, Chile. Atmospheric Environment. 34, (2000), 1189-1196.

Perez, P. 2002. Prediction of maximum of 24-h average of PM10 concentrations

h in advance in Santiago, Chile. Atmospheric Environment. 36, (2002), 4555-4561.

Perez, P. and Reyes, J. 2006. An integrated neural network model for PM10 forecasting. Atmospheric

Shekarrizfard, M. and Hadad, K. 2012. Wavelet transform-based artificial neural networks ( WT-ANN )

in PM 10 pollution level estimation , based on circular variables. Environmental Science and Pollution

Research 19, 1 (2012), 256-268.

Sistema de Informacion Ambiental de Colombia - SIAC: 2012. http://www.siac.gov.co/contenido/

contenido.aspx?catID=585&conID=620. Accessed: 2012-06-28.

Siwek, K. and Osowski, S. 2011. Improving the accuracy of prediction of PM10 pollution by the wavelet

transformation and an ensemble of neural predictors.

Engineering Applications of Artificial Intelligence. 2 (Nov. 2011), 1-13.

Slini, T. et al. 2006. PM10 forecasting for Thessaloniki, Greece. Environmental Modelling & Software.

, 4 (Apr. 2006), 559-565. Ingeniería Documentos de 53

Universidad Industrial de Santander - Corpocesar 2012. Informe De Operación Del

Sistema De Vigilancia De Calidad De Aire De La Ciudad De Valledupar, Departamento Del Cesar.

Witten, I.H. et al. 2011. Data Mining Practical Machine Learning Tools and Techniques. Morgan Kauf mann.

Word Heald Organitation (WHO): 2011. http://www.who.int/mediacentre/factsheets/fs313/en/index.html.

World Health Organization 2005. Guías de calidad del aire actualización mundial - Reporte de la reunión

de un grupo de trabajo en Bonn - Alemania.

World Health Organization - WHO 2000. Air Quality Guidelines. WHO Library Cataloguing in Publication Data.

World Health Organization - WHO 2005. Guías de calidad del aire de la OMS

relativas al material particulado, el ozono, el dióxido de nitrógeno y el dióxido de azufre.

Yeganeh, B. et al. 2012. Prediction of CO concentrations based on a hybrid Partial Least

Square and Support Vector Machine model. Atmospheric Environment. 55, (Aug. 2012), 357-365.

Zolghadri, A. and Cazaurang, F. 2006. Adaptive nonlinear state-space modelling for the

prediction of daily mean PM10 concentrations. Environmental Modelling & Software. 21, 6 (Jun. 2006), 885-894.


Enlaces refback

  • No hay ningún enlace refback.