Abstract: The land utilization space structure is based the remote sensing images of the mine area in 2002 and in 2006 and on this base, the land utilization space structures are classified into five types, namely, not destroyed, destroyed but reclaimed, destroyed and to be reclaimed, to be destroyed and reclaimed and other. In view of the deficiency in CA (cellular automata), a CA method for mine area that is based on space dynamic data mining and random forecast is proposed, thus establishing an operable CA forecast method for the forecast and simulation of discrete status attribute. It is used to forecast the land utilization space structure of a mine area in 2010. It is demonstrated by the real case that the method is both feasible and effective and its forecast results can be used as accurate and reliable data for the land use plan of mine area.

Key words: Cellular automata (CA), Conversion rule, Random forecast, Land utilization in mine area, Dynamic forecast