运用多地震属性和神经网络预测岩性

英文篇名：Litholoy Prediction with Multiple Seismic Attributes and Neural Network
中文刊名：南开大学学报(自然科学版)
英文刊名：Acta Scientiarum Naturalium Universitatis Nankaiensis
作者：崔丽玲 ; 齐龙瑜 ; 刘松芬 ; 胡北来
英文作者：Cui Liling Qi Longyu Liu Songfen Hu Beilai (College of Physics Science ; Nankai University ; Tianjin 300071 ; China)
中文关键词：地震属性 ; 岩性预测 ; 神经网络 ; 岩性标定
英文关键词：seismic attributes ; lithology prediction ; neural network ; litholoy calibration
出版日期：2007-04-20
机构：南开大学物理科学学院,南开大学物理科学学院,南开大学物理科学学院,南开大学物理科学学院天津 300071,天津 300071,天津 300071,天津 300071
年：2007
期：02
出版单位：南开大学学报(自然科学版)

摘要

利用多地震属性和 BP 神经网络可以得到胜利油田垦71地区的岩性预测,由井附近的地震道中可以提取井数据和多地震属性,并由此得到岩性信息,再用 BP 网络对岩性信息进行标定,岩性分布是基于训练好的网络和该地区的多地震属性进行计算的,结果与该区域未参加训练的井资料相比符合率为75%。
The lithology prediction in the Ken-71 area of Shengli Oil Field is achieved by multiple seismic at- tributes and Backpropagation(BP)neural network.We use BP neural network to calibrate the lithology infor- mation extracted from the well logs and multiple seismic attributes extracted from the trace near the well.The lithology distributions are calculated based on well trained network and multiple seismic attributes of the area. The calculated results are about 75% agreement with the data of the wells in the area which are not in the training network.

引文

1 Basu T,Claverie M,Nolan D,et al.Facies analysis:integration of core and log data using a neural network as input for reservoir modeling in Betty Field[J].The Leading Edge,2004,23(8) :794-797．
    2 Walls J D,Taner M T,Guidish T,et al.North sea reservoir characterization using rock physics,seismic attributes,and neural networks;a case history[C/OL]//SEG Technical Program Expanded Abstracts,Society of Exploration Geophysicists,1999,18:1 572-1 575． http://scitation.aup.org/getabs/servlet/GetabsServlet?prog=normal&id=SEGEAB000018000001001572000001&idtype=cvips&gifs=yes.
    3 Herrera V M,Russell B,Flores A.Neural networks in reservoir characterization[J].The Leading Edge,2006,25(4) :402-411．
    4 韩力群.人工神经网络理论设计及应用[M].北京:化学工业出版社,2002．
    5 闻新,周露,王丹力,等.MATLAB 神经网络应用设计[M].北京:科学出版社,2001．