Mining environmental data in hydrological scenarios

We present data mining methods which are used in a hydro-meteorological scenarios within the FP7 project ADMIRE1. The scenarios uses data mining techniques instead of more common physical models in order to predict phenomena which are not being ordinarily solved in Slovakia - water temperature, discharge wave propagation downstream of a major water reservoir and short-term rainfall prediction by analyzing radar imagery. These scenarios are one of a set of use cases, which form the Flood Forecasting Simulation Cascade - a pilot application of ADMIRE project. We describe the variables used in data mining training of these scenarios and also an introduction to the data integration methodology approach we have devised.