Artificial Neural Networks for Estimating the Atmospheric Pollutant Sources

  • F. F. Paes
  • H. F. de Campos Velho
  • F. M. Ramos


The increasing concentration of greenhouse effect gases is a central issue nowadays, mainly with regard to the anthropogenic production gases, such as methane (CH4) and carbon dioxide (CO2). Despite the ratification of the Kyoto Protocol, the expectation is the releases of CO2 and CH4 into the atmosphere will continue to increase in next decade (IPCC, 2007). One essential strategy is to monitor the concentration of these gases in the atmosphere. However, in order to understand the bio-geochemical cycle of these gases, it is necessary to estimate the surface emission rates. One procedure to do that is to employ an inverse problem methodology. Here, the artificial neural network is employed to compute the inverse solution with good results.


Inverse Problem Particle Swarm Optimization Hide Layer Neuron Hide Layer Lagrangian Stochastic Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Al74]
    Alifanov, O.: Solution of an inverse problem of heat conduction by iteration methods. Journal of Engineering Physics, 26, n. 11, 471–476 (1974). MathSciNetCrossRefGoogle Scholar
  2. [AnFe97]
    Anfossi, D., Ferrero, E.: Comparison among empirical probability density functions of the vertical velocity in the surface layer based on higher order correlations. Boundary-Layer Meteorol., 82, 193–218 (1997). CrossRefGoogle Scholar
  3. [Bi95]
    Bishop, C.M.: Neural Networks for Pattern Recognition, Oxford University Press, Oxford (1995). Google Scholar
  4. [Bo05]
    Bocquet, M.: Grid resolution dependence in the reconstruction of an atmospheric tracer source. Nonlinear Processes in Geophysics, 12, 219–234 (2005). CrossRefGoogle Scholar
  5. [CaRa97]
    Campos Velho, H.F., Ramos, F.M.: Numerical inversion of two dimensional geoletric conductivity distributions from electromagnetic ground data. Journal of Geophysis, 15, n. 2, 133–143 (1997). Google Scholar
  6. [ChCa06]
    Chiwiaciwsky, L., Campos Velho, H.F.: Different approaches for the solution of a backward heat conduction problem. Inverse Problems in Engineering, 11, n. 6, 471–494 (2006). Google Scholar
  7. [DaBo07]
    Davoine, X., Bocquet, M.: Inverse modelling-based reconstruction of the Chernobyl source term available for long-range transport. Atmospheric Chemistry and Physics, 7, 1549–1564 (2007). CrossRefGoogle Scholar
  8. [De5co00]
    Degrazia, G.A., Anfossi, D., Carvalho, J.C., Mangia, C., Tirabassi, T., Campos Velho, H.F.: Turbulence parameterization for PBL dispersion models in all stability conditions. Atmos. Environ., 34, 3575–3583 (2000). CrossRefGoogle Scholar
  9. [El3co07]
    Elbern, H., Strunk, A., Schmidt, H., Talagrand, O.: Emission rate and chemical state estimation by 4-dimensional variational inversion. Atmospheric Chemistry and Physics, 7, 3749–3769 (2007). CrossRefGoogle Scholar
  10. [En02]
    Enting, I.G.: Inverse Problems in Atmospheric Constituent Transport, University Press, Cambridge (2002). CrossRefGoogle Scholar
  11. [FeAnBr95]
    Ferrero, E., Anfossi, D., Brusasca, G.: Lagrangian particle model lambda: evaluation against tracer data. International Journal of Environment and Pollution, 5, 360–374 (1995). Google Scholar
  12. [FeAn98a]
    Ferrero, E., Anfossi, D.: Sensitivity analysis of Lagrangian stochastic models for CBL with different pdf’s and turbulence parameterizations. Air Pollution Modelling and its Applications, XII, 673–680 (1998a). Google Scholar
  13. [FeAn98b]
    Ferrero, E., Anfossei, D.: Comparison of pdfs, closures schemes and turbulence parameterizations in Lagrangian stochastic models. International Journal of Environment and Pollution, 9, 384–410 (1998b). Google Scholar
  14. [GaDo99]
    Gardner, M.W., Dorling, S.R.: Neural network modeling of hourly NOx and NO2 concentrations in urban air in London. Atmospheric Environment, 33, 709–719 (1999). CrossRefGoogle Scholar
  15. [GiUl03]
    Gimson, N.R., Uliasz, M.: The determination of agricultural methane emissions in New Zealand using inverse modeling techniques. Atmospheric Environment, 37, 3903–3912 (2003). CrossRefGoogle Scholar
  16. [Ha99]
    Haykin, S.: Neural Networks: A Comprehensive Foundation, [S.l.], Prentice Hall (1999). MATHGoogle Scholar
  17. [HiGm96]
    Hidalgo, H., Gmez-Trevin, E.: Application of constructive learning algorithms to the inverse problem. IEEE T. Geosci. Remote, 34, n. 1, 874–885, (1996). CrossRefGoogle Scholar
  18. [IPCC07]
    IPCC. Climate Change 2007: The Physical Science Basis. Contribution of Working Group I to the Fourth Assessment Report of the Intergovernamental Panel on Climate Change, [S.I.], Cambridge University Press (2007). Google Scholar
  19. [Ku10co03]
    Kukkonen, J., et al.: Extensive evaluation of neural network models for the prediction of NO2 and PM10 concentrations, compared with a deterministic modeling system and measurements in central Helsinki. Atmos. Environ., 37, 4539–4550 (2003). CrossRefGoogle Scholar
  20. [LuHsCh06]
    Lu, H.C., Hsieh, J.C., Chang, T.S.: Prediction of daily maximum ozone concentrations from meteorological conditions using a two-stage neural network. Atmos. Res., 81, 124–139 (2006). CrossRefGoogle Scholar
  21. [Lu08]
    Luz, E.F.P.: Estimação de fonte de poluição atmosférica por enxame de partículas. M.Sc. Thesis, Instituto Nacional de Pesquisas Espaciais (2008). Google Scholar
  22. [Lu3co07]
    Luz, E.F.P., Campos Velho, H.F., Becceneri, J.C., Roberti, D.R.: Estimating atmospheric area source strength through particle swarm optimization, in: Inverse Problems, Desing and Optimization Symposium IPDO (2007), April 16–18, Miami (FL), USA. Google Scholar
  23. [PeTi06]
    Pelliccioni, A., Tirabassi, T.: Air dispersion model and neural network: a new perspective for integrated models in the simulation of complex situations. Environmental Modelling & Software, 21, 539–546 (2006). CrossRefGoogle Scholar
  24. [Ro05]
    Roberti, D.R.: Problemas inversos em física da atmosfera, D.Sc. Thesis, Federal University of Santa Maria (Centro de Ciencias Naturais e Exatas) (2005). Google Scholar
  25. [Ro3co05]
    Roberti, D.R., Anfossi, D., Campos Velho, H.F., Degrazia, G.A.: Estimation of location and strength of the pollutant sources. Ciencia e Natura, 131–134 (2005). Google Scholar
  26. [Ro3co07]
    Roberti, D.R., Anfossi, D., Campos Velho, H.F., Degrazia, G.A.: Estimation of emission rate from experimental data. Nuovo Cimento della Società Italiana di Fisica. C, Geophysics and Space Physics, 30, 177–186 (2007). Google Scholar
  27. [Se00]
    Seibert, P.: Inverse modeling of sulfur emissions in Europe based on trajectories inverse Methods in Global Biogeochemical Cycles, American Geophysical Union, 147–154 (2000). Google Scholar
  28. [Se01]
    Seibert, P.: Inverse modelling Lagrangian particle dispersion model: application to point releases over limited time intervals. Air Pollution Modeling and its Application, XIV, 381–389 (2001). Google Scholar
  29. [ShCaSi08]
    Shiguemori, E.H., Campos Velho, H.F., Silva, J.D.S.: Atmospheric temperature retrieval from satellite data: New non-extensive artificial neural network approach, in: Proceedings of the 23rd Annual ACM Symposium on Applied Computing (Symposium on Applied Computing, Fortaleza), Association for Computing Machinery Inc, III, New York, 1688–1692 (2008). Google Scholar
  30. [Ti77]
    Tikhonov, A.N., Arsenin, V.Y.: Solutions of Ill-Posed Problems, Winston & Sons, New York (1977). MATHGoogle Scholar
  31. [Tho87]
    Thomson, D.J.: Criteria for selection of stochastic models of particle trajectories in turbulent flows. Journal of Fluid Mechanics, 180, 529–556 (1987). MATHCrossRefGoogle Scholar
  32. [WeSuHa06]
    Wesolowski, M., Suchacz, B., Halkiewicz, J.: The analysis of seasonal air pollution pattern with application of neural networks. Analytical and Bioanalytical Chemistry, 384, n. 2, 458–467 (2006). CrossRefGoogle Scholar
  33. [Wo00]
    Woodbury, K.: Neural networks and genetic algorithms in the solution of inverse problems. Bulletin of the Brazilian Society for Computational Applied Mathematics (SBMAC), (2000). Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • F. F. Paes
    • 1
  • H. F. de Campos Velho
    • 1
  • F. M. Ramos
    • 1
  1. 1.Instituto Nacional de Pesquisas Espaciais (INPE)São José dos CamposBrazil

Personalised recommendations