Forecasting evolutionary dynamics of chaotic systems using advanced non-linear prediction and neural networks methods: Application to hydroecological system pollution dynamics

Authors: O.Yu. Khetselius

Year: 2015

Issue: 19

Pages: 30-35

Abstract

We present an improved generalized approach to the analysis and prediction of the nonlinear dynamics of chaotic systems based on the methods of nonlinear analysis and neural networks. As the object of study are the hydroecological systems (pollution dynamics). Use of the information about the phase space in the simulation of the evolution of the physical process in time can be considered as a major innovation in the modeling of chaotic processes in the hydroecological systems. This concept can be achieved by constructing a parameterized non-linear function F (x, a), which transform y (n) to y(n+1) = F[y(n),a], and then use different criteria for determining the parameters a . Firstly to build the desired functions it is offered using the wavelet expansions. Further, since there is the notion of local neighborhoods, we can create a model of the process occurring in the neighborhood, at the neighborhood and by combining together these local models to construct a global non-linear model to describe most of the structure of the attractor.

Tags: analysis and prediction methods of the theory of chaos; hydroecological systems; pollutants; the ecological state; time series of concentrations

Bibliography

  1. Khetselius О.Yu. Forecasting chaotic processes in hydroecologi-cal systems on the basis of attractors conception and neural networks approach: application. Ukr. gìdrometeorol. ž – Ulrainian Hydrometeorology Journal, 2014, no. 15, pp. 16-21.
  2. Abarbanel H.D.I., Brown R., Sidorowich J.J., Tsimring L.Sh. The analysis of observed chaotic data in physical systems. Rev. Mod. Phys., 1993, vol.65, pp. 1331-1392.
  3. Schreiber T. Interdisciplinary application of nonlinear time series methods. Phys. Rep., 1999, vol. 08(1), pp. 1-64.
  4. Glushkov A.V. Analysis and forecast of the anthropogenic impact on industrial city’s atmosphere based on methods of chaos theory: new general scheme. Ukr. gìdrometeorol. ž – Ulrainian Hydrometeorology Journal, 2014, no. 15, pp. 32-36.
  5. Kennel M., Brown R., Abarbanel H. Determining embedding dimension for phase-space reconstruction using a geometrical construction. Phys. Rev.A, 1992, vol.45, pp. 3403-3411.
  6. Turcotte D.L. Fractals and chaos in geology and geophysics. Cambridge: Cambridge University Press, 1997.
  7. Mañé R. On the dimensions of the compact invariant sets of certain non-linear maps. Lecture Notes in Mathematics. Berlin: Springer), 1981, vol. 898, pp. 230-242.
  8. Grassberger P., Procaccia I. Measuring the strangeness of strange attractors. Physica D., 1983, vol. 9, pp. 189-208.
  9. Bunyakova Yu.Ya., Glushkov A.V. Analysis and forecast of the impact of anthropogenic factors on air basin of an industrial city. Odessa: Ecology, 2010. 256 p.
  10. Glushkov A.V., Khokhlov V.N., Prepelitsa G.P., Tsenenko I.A. Temporal variability of the atmosphere ozone content: Effect of North-Atlantic oscillation. Optics of atmosphere and ocean, 2004, vol.14, no. 7, pp. 219-223.
  11. Glushkov A.V., Svinarenko A.A., Loboda A.V. Theory of neural networks on basis of photon echo and its program realization. Odessa, TES, 2004. 280 p.
  12. Glushkov A.V.,Loboda N.S., Khokhlov V.N. Using meteorological data for reconstruction of annual runoff series over ungauged area: Empirical orthogonal functions approach to Moldova- Southwest Ukraine region. Atmospheric Research. Elsevier, 2005, vol. 77, pp. 100-113.
  13. Glushkov A.V., Loboda N.S., Khokhlov V.N., Lovett L. Using non-decimated wavelet decomposition to analyse time variations of North Atlantic Oscillation, eddy kinetic energy, and Ukrainian precipitation. Journal of Hydrology. Elsevier, 2006, vol. 322, no. 1-4, pp. 14-24.
  14. Khokhlov V.N., Glushkov A.V., Loboda N.S., Bunyakova Yu.Ya. Short-range forecast of atmospheric pollutants using non-linear prediction method. Atmospheric Environment. Elsevier, 2008, vol. 42, pp. 7284–7292.
  15. Glushkov A.V., Khetselius O.Yu., Brusentseva S.V., Zaichko P.A., Ternovsky V.B. Adv. in Neural Networks, Fuzzy Systems and Artificial Intelligence, Series: Recent Adv. in Computer Engineering. Gdansk: WSEAS, 2014, vol. 21, pp. 69-75 (Ed.: J. Balicki).
  16. Glushkov A.V., Svinarenko A.A., Buyadzhi V.V., Zaichko P.A., Ternovsky V.B. Adv.in Neural Networks, Fuzzy Systems and Artificial Intelligence, Series: Recent Adv. in Computer Engineering. Gdansk: WSEAS, 2014, vol. 21, pp. 143-150 (Ed.: J. Balicki).
  17. Glushkov A.V., Khetselius O.Yu., Bunyakova Yu.Ya., Grushevsky O.N., Solyanikova E.P. Studying and forecasting the atmospheric and hydroecological systems dynamics by using chaos theory methods. Dynamical Systems Theory. Polland: Lodz, 2013, vol. T1, pp. 249-258. (Eds: J. Awrejcewicz, M. Kazmierczak, P Olejnik, J Mrozowski).
  18. Khetselius O.Yu. Forecasting evolutionary dynamics of chaotic systems using advanced non-linear prediction method. Dynamical Systems Applications. Polland: Lodz, 2013, vol. T2, pp. 145-152 (Eds: J. Awrejcewicz, M. Kazmierczak, P Olejnik, J Mrozowski).
  19. Bunyakova Yu.Ya., Glushkov A.V., Analysis and forecast of the impact of anthropogenic factors on air basein of an industrial city. Odessa: Ecology, 2010. 256 p. (In Russian).
  20. Glushkov A.V., Khokhlov V.N., Serbov N.G., Bunyakova Yu.Ya., Balan A.K., Balanyuk E.P. Low-dimensional chaos in the time series of concentrations of pollutants in an atmosphere and hydrosphere. Vìsn. Odes. derž. ekol. unìv.– Bulletin of Odessa state environmental university, 2007, no. 4, pp. 337-348.
  21. Svinarenko A.A., Khetselius O.Yu., Mansarliysky V.F., Romanenko S.I. Analysis of the fractal structures in turbulent processes. Ukr. gìdrometeorol. ž – Ulrainian Hydrometeorology Journal, 2014, no. 15, pp. 74-78.
  22. Daubechies I. Ten Lectures on Wavelets. Philadelphia: SIAM, 1992.
  23. Morlet J., Arens G., Fourgeau E. and Giard D. Wave propagation and sampling theory. Geophysics, 1982, vol.47, pp. 203-236.
  24. Nason G., von Sachs R., Kroisand G. Wavelet processes and adaptive estimation of the evolutionary wavelet spectrum. J.Royal Stat. Soc., 2000, vol. B62, pp. 271-292.
  25. Glushkov A.V., Khokhlov V.N., Svinarenko A.A., Bunyakova Yu.Ya., Prepelitsa G.P. Wavelet analysis and sensing the total ozone content in the earth atmosphere: Mycros technology “Geomath”. Sensor Electr. and Microsys.Techn., 2005, vol. 2(3), pp. 51-60.
  26. Glushkov A.V., Khokhlov V.N., Tsenenko I.A. Atmospheric teleconnection patterns: wavelet analysis. Nonlin. Proc.in Geophys., 2004, vol. 11, no. 3, pp. 285-293.
Download full text (PDF)