A fifth generation numerical modelling system in coastal zone

Nowadays, artificial intelligence (AI) technology is gradually integrated i nto the numerical modelling system to make the system more intelligent and more user-friendly. The characteristics of the fifth generation numerical m odelling are connected with Al applications. The expert system technology a s a widely applied Al technology is integrated into our modelling system fo r coastal water processes with traditional numerical computational tools an d the data and graphical pre-processing and post-processing techniques. Fiv e kinds of knowledge bases are built in the system to describe the existing expertise knowledge about model parameters, relations between parameters a nd physical conditions, various possible selections for parameters and rule s of inference. The inference engine is designed to be driven by the confid ence of correctness, and the rule base is built with the factor of confiden ce to link the various relations. The decision tree is designed to drive th e inference engine to explore the route of selection procedure of modeling. The decision tree depends on the real problem specifications and can be mo dified during the dialogue between the system and the user. The forward cha ining and backward chaining inference techniques are mixed together in the system to help matching the parameters in the model and the possible select ions with sufficiently high confidence. The expert system technology is suc cessfully integrated into the system to provide help for model parameter se lection or model selection, and to make the numerical model system more acc essible for non-expert users. (C) 2001 Elsevier Science Inc. All rights res erved.