BACKWARD MONTE-CARLO FOR PROBABILISTIC DYNAMICS

Probabilistic dynamics studies the behavior of a system constituted of components and physical variables interacting together. Monte Carlo s imulation is one way to solve the associated mathematical problem for a realistic system; however, Monte Carlo simulations are inefficient a nd biasing techniques are needed. Mast research efforts have been aime d at the improvement of forward Monte Carlo schemes. A backward Monte Carlo simulation associated to the adjoint problem is studied in this paper. It can use any approximate forward solution to perform the impo rtance biasing and can be exploited as a diagnostic approach. The meth od is illustrated on an example. (C) 1998 IMACS/Elsevier Science B.V.