A comparative study of fuzzy logic systems approach for river discharge prediction

In recent years, flood disasters resulting from extreme rainfall have been on the increase in many regions of the world. In developed countries, the usual practice of mitigating flood disasters is by structural means which can reduce infrastructural damages as well as casualties but are unaffordable in most developing countries. The alternative then is to look for non-structural means that involve, among other things, early warning systems which can reduce casualties. The basic technical components of an early warning system involves a measurable input data set that trigger floods, a measurable output data set that quantify the extent of flood and an appropriate mathematical model that transforms the input data set into a corresponding output data set. There are many types of mathematical models that can be used to transform the input data into corresponding output data. The crux of this paper is on one type of data driven mathematical models, namely the use of fuzzy logic approach. The reliability and robustness of the approach are demonstrated with daily and 6-hourly discharge predictions in 4 rivers in 3 countries having contrasting climatological, geographical and land use characteristics. The first application is for two tropical rivers in Sri Lanka using daily upstream rainfall and discharge data to predict downstream discharge with the minimum implication function type Mamdani fuzzy inference system. The second application is for another tropical river in Fiji using similar type of data with daily and 6-h time scales. Both Mamdani type fuzzy inference system with minimum and product implication functions as well as Larsen type inference systems were used. In the third application, daily upstream and tributary discharges were used to predict downstream discharges in a temperate-climate river in China using the TSK type fuzzy inference system with clustering. The methods are robust and the results obtained are within reasonable agreement with observations.