Random models of accidents at Baltic Port and sea water areas

The stochastic processes theory provides concepts and theorems that allow to build probabilistic models concerning incidents or (and) accidents in the Baltic Sea waters and ports. A crucial role in construction of the models plays a Poisson process and its extensions; especially a nonhomogeneous Poisson process and nonhomogeneous compound Poisson process. The nonhomogeneous Poisson process allows to build models of accidents number in the sea and seaports. The nonhomogeneous compound Poisson process creates the possibility of constructing models describing the consequences of dangerous events and marine accidents. Moreover some procedures of the model parameters identification are presented in the paper. Estimation of model parameters was made based on data from reports of HELCOM (2014) and Interreg project Baltic LINes (2016). The expected number of accidents often depends on changing randomly external conditions. Thus it can be assumed that the parameter γ is a random variable. In the paper is assumed that this random variable has a gamma distribution.