Both the Rayleigh and K distributions have been shown to accurately represent the statistics of certain types of active sonar data. While it is common to observe distinct clutters in reverberation data in littoral environment. The mixture of a Rayleigh probability density function (PDF) and a Generalized Pareto (GP) PDF is proposed for representing the heavy-tailed reverberation data within clutters in this study. The Rayleigh-GP mixture model is seen to provide improved fits on the clutter-filled data than Rayleigh or K model. Expectation-maximum (EM) algorithm is proposed and proved to estimate parameters of Rayleigh-GP mixture model well by data analysis.
