Chaos-geometric, neural networks and system analysis and modelling of chaotic pollution dynamics of the complex hydroecological systems

An advanced combined neural networks and chaos-geometric method for analysis, modelling, and forecasting of the chaotic pollution dynamics of complex hydroecological systems is presented. The method is based on the use of advanced methods of the theory of chaos and dynamic systems for the analysis of time series of pollutants concentrations. The general approach includes the Gottwald-Melbourne test, the correlation integral method , fractal and multifractal formalism, average mutual information, false nearest neighbours, surrogate data algorithms, analysis on the basis of the Lyapunov's exponents, Kolmogorov entropy, nonlinear forecast models based on algorithms of optimized predicted trajectories, neural networks modelling. As an illustrative example, a chaotic dynamics of the nitrates concentrations in the Small Carpathians river’s watersheds in the Earthen Slovakia during 1969-1996 years is considered. The data of calculations of the dynamical and topological invariants are presented.