ANALYSES ON REGIONAL CULTIVATED LAND CHANGE BASED ON QUANTITATIVE METHOD Taking Reservoir Area of Three Gorges as Example

Three Gorges Project is the great project in the world, which accelerates economic development in the reservoir area of Three Gorges Project. In the process of development in the reservoir area of Three Gorges Project, cultivated land has become the important resources, a lot of cultivated land has been occupied and become the constructing land. In the same time, a lot of cultivated land has been flooded because of the rising of the water level. This paper uses the cultivated land areas and social economic indicators of reservoir area of Three Gorges in 1990-2004, takes the statistic analyses and example research in order to analyze the process of cultivated land, get the driving forces of cultivated land change, find the new methods to stimulate and forecast the cultivated land areas in the future, and serve for the cultivated land protection and successive development in reservoir area of Three Gorges. The results indicate as follow, firstly, in the past 15 years, the cultivated land areas has decreased 200142 hm(2), the decreasing quantity per year is 13343 hm(2). The whole reservoir area is divided into three different areas, they are upper reaches area, belly area and lower reaches area. The trends of cultivated land change in different reservoir areas are similar to the whole reservoir area. Secondly, the curve of cultivated land areas and per capita GDP takes on the reverse U, and the steps between the change I-ate of cultivated land and the change rate of GDP are different in some years, which indicates that change of cultivated land and change of GDP are decoupling, besides that, change of cultivated land is connection with the development of urbanization and the policy of returning forestry greatly. Lastly, the precision of multi-regression is lower than the BP neural network in the stimulation of cultivated land, then takes use of the BP neural network to forecast the cultivated land areas in 2005, 2010 and 2015, and the forecasting results are reasonable.