A rigorous inter-comparison of ground-level ozone predictions

Atmospheric Environment

Volumn 37, Issue 23, 2003, Pages 3237-3253

  Schlink, Uwe ^a   Dorling, Stephen ^b   Pelikan, Emil ^c   Nunnari, Giuseppe ^d   Cawley, Gavin ^b   Junninen, Heikki ^e   Greig, Alison ^f   Foxall, Rob ^b   Eben, Krystof ^c   Chatterton, Tim ^b   Vondracek, Jiri ^c   Richter, Matthias ^a   Dostal, Michal ^c   Bertucco, Libero ^d   Kolehmainen, Mikko ^e   Doyle, Martin ^b  

^a HELMHOLTZ CENTRE FOR ENVIRONMENTAL RESEARCH UFZ   (Germany)

^b UNIVERSITY OF EAST ANGLIA   (United Kingdom)

^c INSTITUTE OF COMPUTER SCIENCE   (Czech Republic)

^d UNIVERSITY OF CATANIA   (Italy)

^e UNIVERSITY OF EASTERN FINLAND   (Finland)

^f ANGLIA RUSKIN UNIVERSITY   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER SIMULATION; FORECASTING; INDUSTRIAL EMISSIONS; METEOROLOGY; NEURAL NETWORKS; STATISTICAL METHODS;

PERFORMANCE INDICES;

OZONE;

OZONE;

MONITORING; OZONE; POLLUTION; STATISTICAL ANALYSIS;

COMPARATIVE STUDY; FORECASTING METHOD; OZONE; POLLUTION MONITORING; STATISTICAL ANALYSIS;

ACCURACY; ARTICLE; CONCENTRATION (PARAMETERS); EXERCISE; FORECASTING; INTERMETHOD COMPARISON; METEOROLOGY; NERVE CELL NETWORK; PERFORMANCE; POLLUTION MONITORING; PRIORITY JOURNAL; STATISTICAL MODEL;

EUROPE;

EID: 0037899217     PISSN: 13522310     EISSN: None     Source Type: Journal    
DOI: 10.1016/S1352-2310(03)00330-3     Document Type: Article

References (66)

1. van Aalst, R.M., de Leeuw, FAAM 1997. European Topic Centre on Air Quality (RIVM, NILU, NOA, DNMI) National Ozone Forecasting Systems and International Data Exchange in Northwest Europe, Report of the Technical Working Group on Data Exchange and Forecasting for Ozone Episodes in Northwest Europe (TWG-DFO), see http://www.etcaq.rivm.nl/publications.html .
2. Alperovich L., Zheludev V., Hayakawa M. Application of a Wavelet technique to detection of earthquake signatures in the geomagnetic field. Natural Hazards and Earth System Sciences. 1:2001;75-81.
3. Arroyo-Lopez, P.E., Jaramillo-Osorio, A., Gaytan-Iniestra, J., Wojcik-Rojek, A.R., 1999. Using transfer function methodology for ozone forecasting in Toluca city. Proceedings of the Second International Conference on Urban Air Quality, Madrid, pp. 130-131.
4. Arthanari T., Dodge Y. Mathematical Programming in Statistics. 1981;Wiley, New York.
5. Benveniste, A., Juditsky, A., Delion, B., Zhang, Q., Glorennec, P.Y., 1994. Wavelets in identification. Proceedings of the SYSIS '94, Vol. 2, pp. 27-48.
6. Bishop C.M. Neural Networks for Pattern Recognition. 1995;Clarendon Press, Oxford.
7. Box, G.E.P, Jenkins, G.M., 1976. Time Series Analysis - Forecasting and Control. Prentice-Hall, Englewood Cliffs, NJ, Revised Edition.
8. Buntine W.L., Weigend A.S. Bayesian back-propagation. Complex Systems. 5:1991;603-643.
9. Chen J.-L., Islam S., Biswas P. Nonlinear dynamics of hourly ozone concentrations. nonparametric short term prediction Atmospheric Environment. 3211:1998;1839-1848.
10. Community Legislation in Force, Document 392L0072 1992. Council Directive 92/72/EEC of 21 September 1992 on air pollution by ozone, see http://europa.eu.int/eur-lex/en/lif/dat/1992/en_392L0072.html .
11. Community Legislation in Force, Document 396L0062 1996. Council Directive 96/62/EC of 27 September 1996 on ambient air quality assessment and management, see http://europa.eu.int/eur-lex/en/lif/dat/1996/en_396L0062.html.
12. Community Legislation: Directive 2002/3/EC of the European Parliament and of the Council of 12 February 2002 relating to ozone in ambient air, see http://europa.eu.int/eur-lex/pri/en/oj/dat/2002/l_067/ l_06720020309en00140030.pdf .
13. Cybenko G. Approximation by super precision of a sigmoidal function. Mathematics of Control Signals and Systems. 2:1989;303-314.
14. Davis J.M., Speckman P. A model for predicting maximum and 8. h average ozone in Houston Atmospheric Environment. 33:1999;2487-82500.
15. Davis J.M., Eder B.K., Nychka D., Yang Q. Modeling the effects of meteorology on ozone in Houston using cluster analysis and generalised models. Atmospheric Environment. 32(14/15):1998;2505-2520.
16. Demuth, H., Beale, M., 1998. Neural Network Toolbox for Use with MATLAB, User's Guide, Version 3. The Mathworks Inc., Natick, MA.
17. Dorling, S., Foxall, R., Mandic, D., Cawley, G., 2002. Penalised maximum-likelihood cost functions for neural network models of air quality data. Atmospheric Environment, in press, Xref: doi: 10.1016/S1352-2310(03)00323-6.
18. Fawcett, T., 2001. Using Rule Sets to Maximize ROC Performance. Proceedings of the IEEE International Conference on Data Mining ICDM-01.
19. Finzi, G., Nucifora, A., Nunnari, G., Volta, L., 1998. Real time episode forecast: a comparison between neural network and grey box models. Proceedings of the International ICSC/IFAC Symposium on Neural Computation, Vienna, pp. 854-860.
20. Fletcher R. Practical Methods of Optimization. 1987;Wiley, New York.
21. Foxall, R., Krcmar, I., Cawley, G., Dorling, S., Mandic, D.P., 2001. On nonlinear processing of air pollution data. Proceedings of the Fifth International Conference on Artificial Neural Networks and Genetic Algorithms ICANNGA2001. Springer, Prague, ISBN 3-211-83651-9, pp. 477-480.
22. Gardner M.W., Dorling S.R. Artificial neural networks the multilayer perceptron - a review of applications in the atmospheric sciences. Atmospheric Environment. 32(14/15):1998;2627-2636.
23. Gardner M.W., Dorling S.R. Statistical surface ozone models. an improved methodology to account for non-linear behaviour Atmospheric Environment. 341:2000;21-34.
24. Gardner M.W., Dorling S.R. Meteorologically adjusted trends in UK daily maximum surface ozone concentrations. Atmospheric Environment. 34:2000;171-176.
25. Geman S., Bienenstock E., Doursat R. Neural networks and the bias/variance dilemma. Neural Computation. 4:1992;1-58.
26. Harvey A.C. Forecasting, Structural Time Series Models and the Kalman Filter. 1989;Cambridge University Press, New York.
27. Hastie T.J., Tibshirani R.J. Generalised Additive Models, Monographs on Statistics and Applied Probability. Vol. 43:1990;Chapman & Hall, London.
28. Hoek G., Schwartz J.D., Groot B., Eilers P. Effects of ambient particulate matter and ozone on daily mortality in Rotterdam. Archives of Environmental Health. 526:1997;455-463.
29. Hubbard M.C., Cobourn W.G. Development of a regression model to forecast ground-level ozone concentration in Louisville, KY. Atmospheric Environment. 32(14/15):1998;2637-2647.
30. Jain, A.K., Mao, J., Mohiuddin, K.M., 1996. Artificial neural networks - a tutorial. Computer March, pp. 31-44.
31. Junninen, H., Niska, H., Ruuskanen, A., Patama, T., Tuppurainen, K., Kolehmainen, M., Ruuskanen, J., 2002. The performance of different imputation methods for air quality data with missing values. Atmospheric Environment, submitted for publication.
32. Kelsall J.E., Samet J.M., Zeger S.L., Xu J. Air pollution and mortality in Philadelphia 1974-1988. American Journal of Epidemiology. 1469:1997;750-762.
33. Kendall, M., Ord, J.K., 1990. Time Series. Edward Arnold, Sevenoaks 3rd Edition, 1993.
34. 3 concentration in Istanbul. Atmospheric Environment. 34:2000;1267-1271.
35. Kolehmainen M., Martikainen H., Ruuskanen J. Neural networks and periodic components used in air quality forecasting. Atmospheric Environment. 35(5):2001;815-825.
36. Koopman S.J., Shephard N., Doornik J.A. Statistical algorithms for models in state space form using SsfPack 2.2 with discussion. Econometrics Journal. 2:1999;107-160.
37. Metz C.E. Basic principles of ROC analysis. Seminars in Nuclear Medicine. 8:1978;283-298.
38. Milionis A.E., Davies T.D. Regression and stochastic models for air pollution-I. Review, comments and suggestions. Atmospheric Environment. 28:1994;2801-2810.
39. Nunnari, G., Bertucco, L., 2001. Modelling Air Pollution Time-Series by Using Wavelet Functions and Genetic Algorithms. Proceedings of ICANNGA 2001 Fifth International Conference on Artificial Neural Networks and Genetic Algorithm, Prague, Czech Republic, 22-25 April.
40. Nunnari G., Nucifora A.F.M., Randieri C. The application of neural techniques to the modelling of time-series of atmospheric pollution data. Ecological Modelling. 111:1998;187-205.
41. NRC National Research Council, 1991. Rethinking the Ozone Problem in Urban and Regional Air Pollution. National Academy Press, Washington (Chapter 4).
42. Paluš, M., Pelikán, E., Eben, K., Krejčíǐ, P., Juruš, P., 2001. Nonlinearity and prediction of air pollution. Proceedings of the Fifth International Conference on Artificial Neural Networks and Genetic Algorithms ICANNGA2001, Springer, Prague, ISBN 3-211-83651-9, pp. 473-476.
43. Pelikan, E., Novak, M., 1998. Traffic flow forecasting with neural networks. Proceedings of the International Conference on Complex and Intelligent Systems and Interfaces. Nimes, France, pp. 233-235.
44. Pelikan E., Eben K., Petrak L. One-day prediction of electric load reflecting future RCS schedule. Journal of Forecasting. 15:1996;427-436.
45. Robeson S.M., Steyn D.G. Evaluation and comparison of statistical forecast models for daily maximum ozone concentrations. Atmospheric Environment. 24B2:1990;303-312.
46. Rodrigues, A.J., 1996. Dynamic Regression and Supervised Learning Methods in Time Series Modelling and Forecasting. Ph.D.Thesis, Lancaster University, November 1996.
47. Sarle, W.S., 1995. Stopped training and other remedies for overfitting. Proceedings of the 27th Symposium on the Interface of Computing Science and Statistics, pp. 352-360.
48. Scheffer, T., Herbrich, R., 1997. Unbiased assessment of learning algorithms. Proceedings of the IJCAI, available at http://ki.cs.tu-berlin.de/∼scheffer/artikel/ijcai97.ps .
49. Schlink, U., Haase, P., 2001. Application of the surrogate test to detect dynamic non-linearity in ground-level ozone time-series from Berlin. Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithms ICANNGA 2001, pp. 469-472.
50. Schlink U., Volta M. Grey box and component models to forecast ozone episodes. a comparison study Environmental Monitoring and Assessment. 65(1/2):2000;313-321.
51. Schwartz J. Harvesting and long term exposure effects in the relation between air pollution and mortality. American Journal of Epidemiology. 151(5):2000;440-451.
52. Schwartz J., Dockery D.W., Neas L.M., Wypij J.H., Spengler J.D., Koutrakis P., Speizer F.E., Ferris B.G. Jr. Acute effects of summer air pollution on respiratory symptom reporting in children. American Journal of Respiratory and Critical Care Medicine. 150(5):1994;1234-1242.
53. Saerens M. Building cost functions minimizing to some summary statistics. IEEE Transactions on Neural Networks. 116:2000;1263-1271.
54. Spix C. Ozone is bad for health - but only for some? Thorax. 5211:1997;938-939.
55. Stedman J.R., Williams M.L. A trajectory model of the relationship between ozone and precursor emissions. Atmospheric Environment. 26A(7):1991;1271-1281.
56. Stedman, J.R., Willis, P.G., 1994. Air Quality Forecasting in the United Kingdom, 1992-1993, Warren Spring Laboratory, Department of the Environment Contract PECD 7/12/119, March 1994.
57. Thompson M.L., Reynolds J., Lawrence H.C., Guttorp P., Sampson P.D. A review of statistical methods for the meteorological adjustment of tropospheric ozone. Atmospheric Environment. 35:2001;617-630.
58. Williams P.M. Bayesian regularization and pruning using a Laplace prior. Neural Computation. 71:1995;117-143.
59. Williams P.M. Using neural networks to model conditional multivariate densities. Neural Computation. 8:1996;843-854.
60. Willis, P., Jones, B., Charlton, A., 2001. Air Pollution Forecasting in the United Kingdom: 1998-2000. AEA Technology, Report Number AEAT/ENV/R/0505/ISSUE2.
61. Willmott C.J. Some comments on the evaluation of model performance. Bulletin American Meteorological Society. 63(11):1982;1309-1313.
62. Willmott C.J.et al. Statistics for the evaluation and comparison of models. Journal of Geophysical Research. 90(C5):1985;8995-9005.
63. Wolff G.T., Lioy P.J. An empirical model for forecasting maximum daily ozone levels in the north-eastern US. Journal of the Air Pollution Control Association. 28:1978;1035-1038.
64. Yi J., Prybutok R. A neural network model forecasting for prediction of daily maximum ozone concentration in an industrialised urban area. Environmental Pollution. 923:1996;349-357.
65. Youden W.J. Index for rating diagnostic tests. Cancer. 50:1950;32-35.
66. Zmirou D., Schwartz J., Saez M., Zanobetti A., Wojtyniak B., Touloumi G., Spix C., Ponce de Leon A., LeMoullec Y., Bacharova L., Schouten J., Ponka A., Katsouyanni K. Time-series analysis of air pollution and cause-specific mortality. Epidemiology. 95:1998;495-503.