A MINERAL RESOURCE POTENTIAL MAPPING MODEL BESED ON RBF NEURAL NETWORKS
DAI Liming 1,2,CHEN Yongliang 3,LIU Xin 1,2,ZHOU Juntai 1,2,ZHAO Fengmei 1,2,SUO Yanhui 1,2,GAO Wubin 4,LOU Da 5
1. College of Marine Geosciences, Ocean University of China, Qingdao266100, China;2. Key Lab of Submarine Geosciences and Prospecting Techniques,Ministry of Education, Qingdao266100, China; 3. College of Earth Sciences, Jilin University, Changchun130026, China;4. Troops 57015, Chinese People's Liberation Army, Beijing100082, China;5. Dagang OilGas Company, CNPC, Dagang300280, China
A new RBF neural networks model for mineral resource potential mapping is proposed in this paper. For the purpose of applying this new model, a threestep procedure is needed as follows: the first step is to get training samples from the study area; the second step is to abstract the structure of spatial information of training samples and then to construct a RBF networks; the last step is to generate the distributive map of mineral resource potentials. In this paper, the model was employed to predict multimetallogenetic prospecting targets in the area from Duolanasayi to Ashele in northern Xinjiang. The predicted targets by the model were compared with the CF model. The two model results are very similar to each other, suggesting that the new model is effective and practical.
戴黎明, 陈永良, 刘鑫, 周均太, 赵峰梅, 索艳慧, 高武斌, 楼达. 基于RBF神经网络的矿产资源潜力预测模型[J]. 物探与化探, 2011, 35(1): 103-108.
DAI Li-Ming, CHEN Yong-Liang, LIU Xin, ZHOU Jun-Tai, ZHAO Feng-Mei, SUO Yan-Hui, GAO Wu-Bin, LOU Da. A MINERAL RESOURCE POTENTIAL MAPPING MODEL BESED ON RBF NEURAL NETWORKS. Geophysical and Geochemical Exploration, 2011, 35(1): 103-108.
[1]Agertberg F P.Combining indicator patterns for mineral resource evaluation[C]//Proceedings of International Workshop on Statistical Prediction of Mineral Resources,Wuhan,China,1990:1.
[2]Agertberg F P.Combining indicator patterns in weights of evidence modeling for resource evaluation[J].Nonrenewable Resources,1992,1(1): 39.
[3]Pan G C.Extended weights of evidence modeling for the pseudo-estimation of metal grades[J].Nonrenewable Resources,1996, 5(1):53.
[4]Chen Y L.Indicator pattern combination for mineral resource potential mapping with the general CF model[J].Mathematical Geology,2003,35(3):301.
[5]Chen Y L.MRPM: Integrated three Visual Basic programs for mineral resource potential mapping[J].Computers & Geosciences, 2004,30(7): 969.
[6]戴黎明,陈永良,周永刚,等.基于决策树的矿产资源潜力制图模型[J].地球物理学进展,2009,24(3):1081.
[7]Martin T H,Howard B D,Mark H B.Neural Network Design[M].Beijing:China Machine Press,227.
[8]谭章禄.人工神经网络在矿业工程中的应用[M].北京:煤炭工业出版社, 1998;47.
[9]Shi D.Sensitivity analysis applied to the construction of radial basis function networks[J].Neural Networks,2005,18(7):951.
[10] Manolis W.Intelligent initialization of resource allocating RBF networks[J].Neural Networks,2004,18 (2):117.
[11] 边馥苓.地理信息系统原理与方法[M].北京:测绘出版社,1996:149.
[12] Poggio T,Girosi F.Networks for approximation and learning[J].Proceedings of the IEEE,1990,78(9):1481.
[13] Espositoa A,Marinarob M.Approximation of continuous and discontinuous mappings by a growing neural RBFbased algorithm[J].Neural Networks,2000,13(6):651.
[14] 王世称,范继璋,陈永良,等.新疆阿勒泰多金属成矿带综合信息成矿预测[J].长春科技大学学报, 1998,28(数学地质专集):12.
[15] 赵文,陈永良,宫辉力.一种基于图层综合的矿产资源潜力制图模型[J].地质科学,2003,38(2):267.
[16] 陈永良,刘大有.一种基于GIS的矿产资源潜力评价的自动制图模型[J].地质论评,2002,48(3):324.
[17] 王仁铎.线性地质统计学[M].武汉:中国地质大学出版社,1985.