Unbiased sensitivity analysis and pruning techniques in neural networks for surface ozone modelling

Ecological Modelling

Volumn 182, Issue 2, 2005, Pages 149-158

  Pastor Barcenas O ^a   Soria Olivas, E ^b   Martin Guerrero J D ^b   Camps Valls, G ^b   Carrasco Rodriguez J L ^a   Del Valle Tascon S ^a  

^a UNIVERSITY OF VALENCIA   (Spain)

^b Digital Signal Processing Group   (Spain)

Author keywords

Forecasting; Neural networks; Non linear models; Sensitivity analysis; Tropospheric ozone

Indexed keywords

PRUNING TECHNIQUES; SURFACE OZONE MODELING;

ECOLOGY; IMPURITIES; MATHEMATICAL MODELS; NEURAL NETWORKS; PROBLEM SOLVING; SENSITIVITY ANALYSIS;

OZONE;

ARTIFICIAL NEURAL NETWORK; FORECASTING METHOD; OZONE; SENSITIVITY ANALYSIS;

EID: 11444255160     PISSN: 03043800     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.ecolmodel.2004.07.015     Document Type: Article

References (48)

1. A.P. Alsthuller Association of oxidant episodes with warm stagnating anticyclones J. Air Pollut. Control Assoc. 28 1978 152 155
2. E. Balaguer, E. Soria, J.L. Carrasco, and S. del Valle Prediction if surface ozone concentrations 24 h in advance using neural networks. In: Advanced in Neural Networks and Applications 2001 World Scientific and Engineering Press EEUU pp. 212-214
3. E. Balaguer, G. Camps, J.L. Carrasco, E. Soria, and S. del Valle Effective 1-day ahead prediction of hourly surface ozone concentrations in eastern Spain using linear models and neural networks Ecol. Modell. 156 2002 27 41
4. P.S. Bradley, U.M. Fayyad, and O.L. Mangasarian Mathematical programming for data mining: formulations and challenges Informs J. Comput. 3 11 1998 217 238
5. Chameides, W.L., Lodge, J.P., 1992. Tropospheric ozone: formation and fate. In: Lefohn, A.S. (Ed.), Surface Level Ozone Exposures and their Effects on Vegetation, pp. 5-30.
6. I. Colbeck Photochemical ozone pollution Weather 40 1985 241 245
7. A.C. Comrie Comparing neural networks and regression models for ozone forecasting J. Air Waste Manag. Assoc. 47 1997 653 663
8. EU, 2002. European Parliament, and the European Council. 2002/3/CE O.D. C 67 E. 9-3-2002, p. 14-20.
9. M.W. Gardner, and S.R. Dorling Statistical surface ozone models: an improved methodology to account for non-linear behaviour Atmospheric Environ. 34 1999 21 34
10. M. Gevrey, L. Dimopoulos, and S. Lek Review and comparison of methods to study the contribution of variables in artificial neural network models Ecol. Modell. 160 2003 249 264
11. Z. Guo, and R.E. Uhrig Using modular neural networks to monitor accident conditions in nuclear power plants, SPIE In: Applications of Artificial Neural Networks III. 1709 1992 pp. 505-516
12. L. Hadjiiski, P. Geladi, and P. Hopke A comparision of modeling nonlinear systems with artificial neural networks and partial least squares Chemom. Intell. Lab. Syst. 49 1999 91 103
13. Hassibi, B., Stork, D.G., 1993. Second order derivatives for network pruning: optimal brain surgeon. In: Hanson, S.J., Cowan, J.D., Giles, C.L. (Eds.), Advances in Neural Information Processing Systems, vol. 5, pp. 164-171.
14. S. Haykin Neural Networks: A Comprehensive Foundation 1999 Prentice Hall New Jersey
15. W.E. Hogsett, J.E. Weber, D. Tingey, A. Herstrom, E.H. Lee, and J.A. Laurence An approach for characterizing tropospheric ozone risk to forests Environ. Manag. 21 1997 105 120
16. C.T. Hsu, Y.M. Tzeng, C.S. Chen, and M.Y. Cho Distribution feeder loss analysis by using an artificial neural network Electric Power Syst. Res. 34 1995 85 90
17. P.L. Kinney, G.D. Thurston, and M. Raizenne The effects of ambient ozone on lung function in children: a reanalysis of six summer camp studies Environ. Health Perspect. 104 1996 170 174
18. M. Kolehmainen, H. Martikainen, and J. Ruuskanen Neural networks and periodic components used in air quality forecasting Atmospheric Environ. 35 2001 815 825
19. S.V. Krupa, W.J. Manning, and M. Nosal Use of tobacco cultivars as biological indicators of ambient ozone pollution: An analysis of exposure-response ralationships Environ. Pollut. 81 1993 137 146
20. S.V. Krupa, M. Nosal, and A.H. Legge Ambient ozone and crop loss: establishing a cause-effect relationship Environ. Pollut. 83 1994 269 276
21. R.I. Larsen, W.F. McDonell, and D.H. Hortsman An air quality data analysis system for interrelating effects, standards, and needed source reductions. Part II: A log-normal model relating human lung function decrease to ozone exposure J. Waste Manag. Assoc. 41 4 1991 455 459
22. LeCun, Y., Denker, J., Solla, S., Howard, R.E., Jackel, L.D., 1990. Optimal Brain Damage. In: Touretzky, D.S. (Ed.), Advances in Neural Information Processing Systems (II).
23. A.H. Legge, L. Grünhage, M. Nosal, H.J. Jägger, and S.V. Krupa Qambient ozone and adverse crop response: an evaluation of North American and European data as they relate to exposure indices and critical levels J. Appl. Bot. 69 1995 192 205
24. S. Lek, M. Delacoste, P. Baran, I. Dimopoulus, J. Lauga, and S. Aulagnier Application of neural networks to modelling non-linear relationship in ecology Ecol. Modell. 90 1 1996 39 52
25. P. Leray, and P. Gallinari Feature selection with neural networks Behaviormetrika 1999 p. 26
26. J.D. Martín, E. Soria, G. Camps, A.J. Serrano, J.J. Pérez, and N.V. Jiménez Dosage individualization of erythropoietin using a profile-dependent support vector regression IEEE Trans. Biomed. Eng. 50 2003 1136 1142
27. G.M. McCollister, and K.R. Wilson Linear stochastic models for forecasting daily maxima and hourly concentrations of air pollutants Atmospheric Environ. 9 1975 417 423
28. G. Nunnari, A.F.M. Nucifiora, and C. Radineri The application of neural techniques to the modelling of time series of atmospheric pollution data Ecol. Modell. 111 1998 187 205
29. D.O. Olden, and D.A. Jackson Illuminating the "black-box": a randomisation approach for understanding variable contributions in artificial neural networks Ecol. Modell. 154 2002 135 150
30. G.B. Orr, and K.R. Müller Neural Networks: Tricks of the Trade 1998 Springer-Verlag Berlin, Heidenberg
31. N.R. Pal Soft computing for feature analysis Fuzzy Sets Syst. 103 1999 201 221
32. J.M. Paruelo, and F. Tomasel Prediction of functional characteristics of ecosystems: a comparison of artificial neural networks and regression models Ecol. Modell. 98 2-3 1997 173 186
33. S.M. Roberson, and D.G. Steyn Evaluation and comparison of statistical forecast models for daily maximum concentrations Atmospheric Environ. 24B 1990 303 312
34. D.W. Ruck, S.K. Rogers, and M. Kabrisky Feature selection using a multilayer perceptron J. Neural Network Comput. 2 2 1990 40 48
35. Sarle, W.S., 2000. How to measure importance of inputs? SAS Institute Inc., Cary, NC, USA. Available at ftp://ftp.sas.com/pub/neural/importance.html.
36. R. Simpson, R. Williams, R. Ellis, and P.F. Culverhouse Biological pattern recognition by neural networks Mar. Ecol. Prog. 79 1992 303 308
37. L.H. Slaughter, C.L. Mulchi, and E.H. Lee Wheat-kernel growth characteristics during exposure to chronic ozone pollution 80 1993 73 79
38. G. Soja, and A.M. Soja Ozone indices based on simple meteorological parametres: potencial and limitations of regression and neural network models Atmospheric Environ. 33 1999 4229 4307
39. D.M. Spekton, G.D. Thurston, J. Mao, D. He, C. Hayes, and M. Lippman Effects of single and multiday ozone exposures on respiratory function in active normal children Environ. Res. 55 1991 107 122
40. G. Spellman Analysing air pollution meteorology Weather 53 1998 34 42
41. G. Spellman An application of artificial neural networks to the prediction of surface ozone concentrations in the United Kingdom Appl. Geography 19 2 1999 123 136
42. Stockwell, W.R., kramm, G., Scheel, H.E., Mohnen, V.A., Seiler, W., 1997. Ozone formation, destruction and exposure in Europe and the United Estates. In: Sandermann, H., Wellburn, A.R., Heath, R.L. (Eds.), Forest Decline and Ozone, pp. 1-38.
43. Tresp, V., Neuneier, R., Zimmermann H.G., 1997. Early brain damage. In: Mozer, M.C., Jordan, M.I., Petsche, T (Eds.), Advances in Neural Information Processing Systems, vol. 9, p. 669.
44. U.S. Environmental Protection Agency, 1996. Air quality criteria for ozone and related photochemical oxidants. EPA 600/8-84/020cF. U.S. Environmental Protection Agency, North Caroline.
45. Wan, E., 1993. Time series prediction using a neural network with embedded tapped delay-lines. In: Weigend, A., Gershenfeld, N. (Eds.), Predicting the Future and Understanding the Past, SFI Studies in the Science of Complexity, Addison-Wesley.
46. C.J. Wilmott On the validation of models Phys. Geography 2 1981 184 194
47. B.M. Wise, B.R. Holt, N.B. Gallagher, and S. Lee A comparison of neural networks, non-linear biased regression and a genetic algorithm for dynamic model identification Chemom. Intell. Lab. Syst. 30 1 1995 81 89
48. Zurada, J.M., Malinowski, A., Cloete, I., 1994. Sensitivity análisis for minimization of input data dimension for feedforward neural network. In: ISCAS'94 IEEE International Symposium on Circuits and Systems, vol. 6, IEE Press, London, pp. 447-450.