Application of the artificial neural network to multivariate anomaly recognition in geochemical exploration for hydrocarbons

作     者：Liuping Zhang~(1,2) & Guoping Bai~(1,2) 1 Basin(?) Reservoir Research Center,University of Petroleum,Changping,Beijing 102249,P.R.China 2 Key Laboratory for Hydrocarbon Accumulation Mechanism of Chinese Ministry of Education,University of Petroleum, Beijing 102249,P.R.China 

会议名称：《中国科学院地质与地球物理研究所2003学术年会》

会议日期：2003年

学科分类：081801[工学-矿产普查与勘探] 081802[工学-地球探测与信息技术] 08[工学] 0818[工学-地质资源与地质工程] 

关 键 词：multivariate anomalies neural network cluster analysis direct hydrocarbon indicators 

摘      要：Traditional methods of multivariate statistical analyses,used to recognize anomalous hydrocarbon signatures in petroleum exploration,have at least four shortcomings:(1) it is difficult to isolate anomalies where the data are not normally distributed;(2) it is difficult to separate distinct anomaly populations corresponding to distinct formation mechanisms while separating anomalies from background;(3) it is not fitting to present illustrations of multivariate anomalies on contour maps;and (4) it is not suitable for preparation for multivariate pattern *** present serious obstacles to the application of exploration geochemistry in hydrocarbon *** study demonstrates that the Back Propagation Artificial Neural Network(BP-ANN) with logic multiplication cluster analysis(a new cluster analysis proposed in this paper) overcomes the difficulties exhibited by traditional multivariate *** logic multiplication cluster analvsis was designed to produce a training set for the *** approach was established on the basis of geochemical characteristics and origin of the various populations in geochemical data,such as background,micro-seepage anomalies and seepage *** topology of the BP-ANN was optimized using the outputs of the BP-ANN and the correct *** order to illustrate the multivariate anomalies recognized using BP-ANN on contour maps,we designed the expression functions for BP-ANN application in this *** traditional methods of anomaly recognition,acid-extractable hydrocarbons in soils have not proven to be efficient indicators for hvdrocarbon potential in East Anan Sag,Inner ***,the BP-ANN has indicated that these indicators are efficient and that areas of East Anan Sag have potential reserves of petroleum.