River floods short-term forecasting system based on integrated use of space-ground data

In this paper a new approach to construction the short-term forecasting systems of river floods is introduced. It provides highly accurate forecasting results due to operative obtaining and integrated processing the remote sensing and ground-based water flow data in real time. Forecasting of floods areas and depths is performed on a time interval of 6 to 48 hours to be able to take the necessary steps to alert and evacuate the population. Forecast results are available as Web-services. The proposed system extends the traditional approach based on modelling river physical processes by integration of different types of models and technologies such as satellite image processing, input data clustering and filtering, digital maps of a relief and river terrain, data crowdsourcing, heterogeneous data processing, hydrological models for time scale modelling water flows and geo-simulation, inundation visualisation and duly warning on flooding.