This study integrates geological and geophysical data for the Baixiangshan iron deposit within the Ningwu Basin of the Middle and Lower Yangtze Metallogenic Belt, China, creates a three dimensional geological model that can describes three dimensional geological structure of Baixiangshan mining area in detail. Based on three dimensional geological models, several quantitative exploration criteria have been extracted by using 3D spatial analysis, which were then used for the prospectivity mapping by using Artificial Neural Networks. The result shows that the prospectivity map can identifies the known orebody very well and highlights some high prospectivity areas in the north and east of known orebody that are favorable for exploration in the Baixiangshan mining area; these areas should be considered as high priority targets for future exploration. In addition, the result shows that 3D localization and quantitative prospectivity mapping by using Artificial Neural Networks is effective for the Baixiangshan Mining area. It can be used for the future mineral exploration in deep and peripheral areas of the new and old mining area and also provide a new localization and quantitative method for predicting the concealed mineralization and optimizing the prospecting target.