Identifying chaff echoes in weather radar data using tree-initialized fuzzy rule-based classifier

In order to produce reliable weather forecasts, it is essential to discriminate non-meteorological targets from rain clouds in weather radar data. Identification of chaff echoes, which is one of the main noise sources, is uncertain and imprecise for skilled weather experts because characteristics of them are similar to those of precipitation echoes. This paper uses tree-initialized fuzzy classifier (FC) to identify chaff echoes. Fuzzy models have been widely applied to the domain of uncertainty and vagueness. Classification and regression tree is used to generate an initial crisp model (a set of crisp rules). The number of the rules, corresponding to complexity of the model, is systematically determined by performance criterion. Finally, after transforming the crisp model to the fuzzy one straightforwardly, parameters of the FCs are optimized by genetic algorithms. FCs have more flexible decision boundaries than binary decision trees with rectangular partitioning. In order to evaluate identification performance, the FCs, and comparison methods are applied to many cases where both chaff and non-chaff echoes occurred simultaneously. The results of experiments show that the FCs achieve the best identification performance.