Neural Networks for Characterization and Forecasting in the Boundary Layer via Radon Data

  • Antonello PasiniEmail author

The complexity of air-pollution physical-chemical processes in the boundary layer (BL) is well known: see, for instance, Stull (1988) and Seinfeld and Pandis (1998). In this framework, we do not make any attempt at reviewing the manifold use of neural networks (NNs) for air-pollution assessments and forecasting. Instead, we focus just on the (complex) physics of the BL and discuss the coupled use of an original index of the BL properties (radon concentration) and of NN modeling in order to obtain interesting results for characterizing and/or forecasting important variables in the BL, like the concentration of a dangerous primary pollutant (benzene) and the 2-h evolution of stable layer depth. In this scenario, the particular strategies for applying a NN model are described, showing how they lead to important original results, for grasping the BL physical behavior. In doing so, one can discover the usefulness of an empirical AI data-driven approach to investigating a complex system that is very difficult to deal with in terms of dynamical models.

In the next section, a brief introduction to fundamentals of radon detection will be presented and the qualitative and quantitative relevance of radon concentration for summarizing the physical state of the BL will be discussed. In particular, we will present the structure of a box model (based on radon data) for estimating the nocturnal stable layer depth.


Radon Concentration Benzene Concentration Residual Series Primary Pollutant Radon Progeny 
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. Allegrini, I., Febo, A., Pasini, A., & Schiarini, S. (1994). Monitoring of the nocturnal mixed layer by means of particulate radon progeny measurement. Journal of Geophysical Research 99(D9), 18765–18777CrossRefGoogle Scholar
  2. Guedalia, D., Ntsila, A., Druihlet, A., & Fontan, J. (1980). Monitoring of the atmospheric stability above an urban and suburban site using sodar and radon measurements. Journal of Applied Meteorology 19 839–848CrossRefGoogle Scholar
  3. Lopez, A., Guedalia, D., Servant, J., & Fontan, J. (1974). Advantages of the use of radioactive tracers 222 Rn and 212 Pb for the study of Aitken nuclei within the low troposphere. Journal of Geophysical Research 79 1243–1252CrossRefGoogle Scholar
  4. Mahrt, L. (1998). Stratified atmospheric boundary layers and breakdown of models. Theoretical and Computational Fluid Dynamics 11 263–279CrossRefGoogle Scholar
  5. Marzban, C. (1998). Scalar measures of performance in rareevent situations. Weather Forecasting 13, 753–763CrossRefGoogle Scholar
  6. Pasini, A., & Ameli, F. (2003). Radon short range forecasting through time series preprocessing and neural network modeling. Geophysical Research Letters 30(7), 1386. Doi:10.1029/2002GL016726CrossRefGoogle Scholar
  7. Pasini, A., Pelino, V., & Potesta, S. (2001). A neural network model for visibility nowcasting from surface observations: Results and sensitivity to physical input variables. Journal of Geophysical Research 106(D14), 14951–14959CrossRefGoogle Scholar
  8. Pasini, A., Ameli, F., & Febo, A. (2002). Estimation and shortrange forecast of the mixing height by means of box and neural-network models using radon data. In S. Anić (Ed.), Physical chemistry 2002: Proceedings volumes (pp. 607– 614). Society of Physical Chemists of Serbia: Belgrade, SerbiaGoogle Scholar
  9. Pasini, A., Ameli, F., & Lorè, M. (2003a). Mixing height short range forecasting through neural network modeling applied to radon and meteorological data. Proceedings of the 3rd Conference on Artificial Intelligence Applications to Environmental Sciences, 83rd Annual Meeting of the American Meteorological Society. AMS: Long Beach, CA, CD ROMGoogle Scholar
  10. Pasini, A., Ameli, F., & Lorè, M. (2003b). Short range forecast of atmospheric radon concentration and stable layer depth by neural network modelling. Proceedings of the IEEE International Symposium on Computational Intelligence for Measurement Systems and Applications (pp. 85–90). Lugano, Switzerland: IEEEGoogle Scholar
  11. Pasini, A., Perrino, C., & Žujić, A. (2003c). Non-linear atmospheric stability indices by neural-network modelling. Nuovo Cimento 26C 633–638Google Scholar
  12. Perrino, C., Pietrodangelo, A., & Febo, A. (2001). An atmospheric stability index based on radon progeny measurements for the evaluation of primary urban pollution. Atmospheric Environment 35 5235–5244CrossRefGoogle Scholar
  13. Porstendörfer, J. (1994). Properties and behaviour of radon and thoron and their decay products in the air. Journal of Aerosol Science 25 219–263CrossRefGoogle Scholar
  14. Seinfeld, J. H., & Pandis, S. N. (1998). Atmospheric chemistry and physics: From air pollution to climate change (1326 pp.). New York: WileyGoogle Scholar
  15. Stull, R. B. (1988). An introduction to boundary layer meteorology (666 pp.). Dordrecht: KluwerGoogle Scholar
  16. Vinod Kumar, A., Sitaraman, V., Oza, R. B., & Krishnamoorthy, T. (1999). Application of a numerical model for the planetary boundary layer to the vertical distribution of radon and its daughter products. Atmospheric Environment 33 4717– 4726CrossRefGoogle Scholar
  17. Weigend, A. S., & Gershenfeld, N. A. (Eds.) (1993). Time series prediction: Forecasting the future and understanding the past (664 pp.). New York: Addison-WesleyGoogle Scholar

Copyright information

© Springer Science+Business Media B.V 2009

Authors and Affiliations

  1. 1.CNR — Institute of Atmospheric PollutionRomeItaly

Personalised recommendations