Regional Gravity Structure Interpretation for Mineral Resource Prognosis Using Neural Network

In this paper, a correlative structure model based on regional gravity information is generated using back-propagation neural network. The gravity bouguer anomalies of samples are analyzed. The result has been used to process the 1:1,000,000 gravity horizontal derivation maps of the mining areas in the East Kunlun Mountain and the system can automatically extract structure axis from gravity interpretation maps. Comparing with the existent results, our method has the advantage to process non-linear data, and the system is self-adaptive. The resulting structure of gravity bouguer anomalies using neural network is more accurate than the existent results.