Mar 19, 2019   11:24 a.m. Jozef
Academic information system

Projects


Analysis, generation and of hydrometeorological time series:nonstationary, heteroskedastic and nonlinear models.

Supervisor: prof. Ing. Ján Szolgay, PhD.


Basic information   Workers      


This page shows details on the project. The primary projects are displayed together with a list of sub-projects.

Project description:Stochastic models of hydrometeorological time series became a standard tool for their analysis, generation and prediction. They are also widely used in the design and optimisation water resource systems, including design storm and flood frequency estimation by continuous simulation for flood defence. Recent global and climatic changes question the validity of the stationarity assumption, on which most of the current stochastic models are based. Models originating mostly from the classical Box-Jenkins methodology have to be therefore reconsidered and substituted by new approaches, which allow for considering nonstationarity, heteroskedasticity and nonlinearities. With respect to the variability in the scenarios describing future conditions, fuzzy methods considering qualitative information accounting for uncertainty of model parameters also offer a potential in model development. The project aims at analysing the properties of various hydrometeorological time series with respect to the changes of their governing conditions and testing of the applicability of ARCH and GARCH models (which allow considering nonstationarity and heteroskedasticity) and SETAR, STAR models considering nonlinearities for the simulation and prediction of these time series. Development of models, which can incorporate fuzzy information and relationships and non-standard methods for data aggregation will be also envisaged. Applications in data generation, forecasting and flood frequency estimation by continuous simulation are foreseen.
Kind of project:VEGA ()
Department:Department of Land and Water Resources Management (FCE)
Project identification:1/2032/05
Project status:Successfully completed
Project start date :01. 01. 2005
Project close date:31. 12. 2007
Number of workers in the project:1
Number of official workers in the project:0