Floods belong to the most hazardous natural disasters and their disaster management heavily relies on precise forecasts. These\r\nforecasts are provided by physical models based on differential equations. However, these models do depend on unreliable inputs\r\nsuch as measurements or parameter estimations which causes undesirable inaccuracies.Thus, an appropriate data-mining analysis\r\nof the physical model and its precision based on features that determine distinct situations seems to be helpful in adjusting the\r\nphysical model. An application of fuzzy GUHA method in flood peak prediction is presented.Measured water flow rate data from\r\na system for flood predictions were used in order to mine fuzzy association rules expressed in natural language. The provided data\r\nwas firstly extended by a generation of artificial variables (features).Theresulting variableswere later on translated into fuzzyGUHA\r\ntables with help of Evaluative Linguistic Expressions in order to mine associations.Thefound associations were interpreted as fuzzy\r\nIF-THEN rules and used jointly with the Perception-based Logical Deduction inference method to predict expected time shift of\r\nflow rate peaks forecasted by the given physical model. Results obtained from this adjusted model were statistically evaluated and\r\nthe improvement in the forecasting accuracy was confirmed.
Loading....