A Geographic Information Knowledge Discovery Model Based on Rough Set and Neural Network

The paper proposes a model based on rough set theory and neural network technology to discover knowledge from geographic information that has high spatial autocorrelation and fuzzy characteristics. In the model first get the most concise if-then rules by discernibility matrix. Then construct a three-layer neural network to simulate the most concise rules. Inputs and outputs of the neural network are determined by the parameter-training method that is provided in this paper. Finally the paper presents a simulation of its use for judging drought and flood disasters in Songliao River base. The results show that the model can quickly form the most concise rules and make right decision.