|本期目录/Table of Contents|

[1]刘浩男 文晓涛 何 健 陈芊澍 张晓琦.基于随机森林算法的AVO类型判别[J].中国海上油气,2020,32(05):73-81.[doi:10.11935/j.issn.1673-1506.2020.05.009]
 LIU Haonan WEN Xiaotao HE Jian CHEN Qianshu ZHANG Xiaoqi.AVO type discrimination based on random forest algorithm[J].China Offshore Oil and Gas,2020,32(05):73-81.[doi:10.11935/j.issn.1673-1506.2020.05.009]
点击复制

基于随机森林算法的AVO类型判别()

《中国海上油气》[ISSN:1673-1506/CN:11-5339/TE]

卷:
第32卷
期数:
2020年05期
页码:
73-81
栏目:
油气勘探
出版日期:
2020-09-25

文章信息/Info

Title:
AVO type discrimination based on random forest algorithm
文章编号:
1673-1506(2020)05-0073-09
作者:
刘浩男 文晓涛 何 健 陈芊澍 张晓琦
(成都理工大学 四川成都 610059)
Author(s):
LIU Haonan WEN Xiaotao HE Jian CHEN Qianshu ZHANG Xiaoqi
(Chengdu University of Technology, Chengdu, Sichuan 610059, China)
关键词:
AVO类型 随机森林 储层预测 分类判别 形态特征参数
Keywords:
AVO type random forest reservoir prediction classifying discrimination morphological feature parameters
分类号:
TE132.1+4
DOI:
10.11935/j.issn.1673-1506.2020.05.009
文献标志码:
A
摘要:
AVO技术可用于含气储层的识别,对油气勘探具有重要意义。人工识别储层AVO类型人为干扰因素较大,识别精度较低且耗时较长。由此,本文引入随机森林算法,利用Bootstrap重复抽样及枝叶节点分裂等技术生成大量决策树分类器,通过统计所有决策树的分类结果实现对储层AVO类型的判别。首先,基于工区内测井数据建立速度密度模型; 其次,利用Shuey近似公式计算AVO曲线并获得该曲线对应的拟合多项式; 第三,根据拟合多项式提取形态特征参数作为随机森林算法的训练数据集输入参数,将人工AVO类型识别结果作为输出参数,训练并得到决策树分类器; 最后,以实际叠前地震数据的AVO曲线特征参数为输入参数,通过随机森林决策树分类判别得到工区内储层AVO类型。通过与近似支持向量机算法的对比结果可以看出,两种算法对储层AVO类型判别结果相近,都具有较高的准确率,但相比之下随机森林算法所需特征属性较少,泛化性较强,具有更好的普适性
Abstract:
AVO technology can be used to identify gas-bearing reservoirs and is of great significance to oil and gas exploration. However, the manual identification of AVO type of reservoirs is prone to man-made interferences, has low identification accuracy and is time-consuming. Therefore, this paper introduces the random forest algorithm, uses Bootstrap repeated sampling and branch and leaf node splitting techniques to generate a large number of decision tree classifiers, and realizes the identification of the AVO type of the reservoir by summarizing the classification results of all decision trees. First, a velocity density model is established based on logging data in the work area. Second, Shuey approximation formula is used to calculate the AVO curve and obtain the fitting polynomial corresponding to the curve. Third, the morphological feature parameters are extracted according to the fitting polynomial as the input parameters of the training data set of the random forest algorithm, and the artificial AVO type recognition results are used as the output parameters to train and obtain a decision tree classifier. Finally, the characteristic parameters of the AVO curve of the actual pre-stack seismic data are used as input parameters, and the AVO type of the reservoir in the work area is obtained through the classification and discrimination of the random forest decision tree. By comparing the results with those of the approximate support vector machine algorithm, it can be seen that the two algorithms are similar in terms of discrimination results of AVO type of the reservoir, and both have high accuracy, but the random forest algorithm requires fewer feature attributes, shows stronger generalization and has better universality

参考文献/References:

[1] OSTRANDER W J.Plane-wave reflection coefficients for gas sands at non-normal angles of incidence[J].Exploration Geophysics,1984,15(3):193.
[2] RUTHERFORD S R,WILLIAMS R H.Amplitude-versus-offset variations in gas sands[J].Geophysics,1989,54(6):680-688.
[3] CASTAGNA J P,SWAN H W.Principles of AVO cross plotting[J].The Leading Edge,1997,16(4):337-342.
[4] RAMOS A C B,DAVIS T L.3-D AVO analysis and modeling applied to fracture detection in coalbed methane reservoirs[J].Geophysics,1997,62(6):1683-1695.
[5] ADRIANSYAH.Seismic AVO analysis and interpretation:Application to carbonate and clastic reservoirs in the Northwest Java Basin,Indonesia[J].Dissertation Abstracts International,2000,61(6):2954.
[6] MA Jinfeng,MOROZOV I B.Structure of the Wollaston Lake Reflector(Trans-Hudson Orogen,Canada)from reflection AVO analysis:Fractured diabase intrusion,fluids,or silicified shear zone? [J].Tectonophysics,2007, 441(1):97-114.
[7] ADEOTI L,ADELEYE K O,ITSEMODE A,et al.Fluid prediction using AVO analysis and forward modelling of deep reservoirs in Faith Field,Niger Delta,Nigeria[J].Arabian Journal of Geosciences,2015,8(6):4057-4074.
[8] 吴国庆,李刚,董守华.薄煤层赋存不同流体的AVO特征分析[J].工程地球物理学报,2015,12(3):395-400.WU Guoqing,LI Gang,DONG Shouhua.AVO analysis of different occurrence-fluids in thin coal model[J].Chinese Journal of Engineering Geophysics,2015,12(3):395-400.
[9] 张益明,牛聪,韩利,等.频散AVO分析技术及其在南海深水区的应用[J].中国海上油气,2016,28(6):21-27.DOI:10.11935/j.issn.1673-1506.2016.06.004.ZHANG Yiming,NIU Cong,HAN Li,et al.A method of frequency dispersion AVO analysis and its application in deep water area of South China Sea[J].China Offshore Oil and Gas,2016,28(6):21-27.DOI:10.11935/j.issn.1673-1506.2016.06.004.
[10] XIE Jie,ZHU Mingying.Maneuver-based driving behavior classification based on random forest[J].IEEE Sensors Letters,2019,3(11):1-4
[11] 丁雪梅,伦立军,辛英.基于模拟退火算法的证券投资最优组合理论研究[J].哈尔滨师范大学自然科学学报,2003,19(5):54-56.DING Xuemei,LUN Lijun,XIN Ying.The research of portfolio investment based on simulated annealing[J].Natural Science Journal of Harbin Normal University,2003,19(5):54-56.
[12] 钟将,温罗生,冯永,等.基于近似支持向量机的Web文本分类研究[J].计算机科学,2008,35(3):167-169,202.ZHONG Jiang,WEN Luosheng,FENG Yong,et al.Study on the web classification based on proximal support vector machine[J].Computer Science,2008,35(3):167-169,202.
[13] 魏佳明,韩家新.随机森林在储层孔隙度预测中的应用[J].智能计算机与应用,2018,8(5):79-82.WEI Jiaming,HAN Jiaxin.Application of random forest in reservoir porosity prediction[J].Computer Study,2018,8(5):79-82.
[14] 周雪晴,张占松,张超谟,等.基于粗糙集-随机森林算法的复杂岩性识别[J].大庆石油地质与开发,2017,36(6):127-133.ZHOU Xueqing,ZHANG Zhansong,ZHANG Chaomo,et al.Complex lithologic identification based on rough set-random forest algorism[J].Petroleum Geology&Oilfield Development in Daqing,2017,36(6):127-133.
[15] 任雄风,刘杨,张军华,等.基于随机森林的浊积岩储层预测方法[J].科学技术与工程,2019, 19(25):68-74.REN Xiongfeng,LIU Yang,ZHANG Junhua,et al.The method of turbidite reservoir prediction based on random forest[J].Science Technology and Engineering,2019,19(25):68-74.
[16] 李文秀,文晓涛,李天,等.近似支持向量机的AVO类型判别[J].石油地球物理勘探,2018,53(5):969-974.LI Wenxiu,WEN Xiaotao,LI Tian,et al.AVO types discrimination based on a proximal support vector machine[J].Oil Geophysical Prospecting,2018,53(5):969-974.
[17] 方匡南.随机森林组合预测理论及其在金融中的应用[M].厦门:厦门大学出版社,2012:216-217.
[18] BREIMAN L.Bagging predictors[J].Machine Learning,1996,24(2):123-140.
[19] BREIMAN L.Random forests[J].Machine Learning,2001,45(1):5-32.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2019-12-20 改回日期:2020-04-02*国家自然科学基金项目“深层碳酸盐岩储层流体地震预测理论与方法(编号:U1562111)”“基于频变信息的流体识别及流体可动性预测(编号:41774142)”部分研究成果。第一作者简介: 刘浩男,男,在读硕士研究生,主要从事储层预测与流体识别方面的研究。地址:四川省成都市成华区二仙桥东三路一号成都理工大学地球勘探与信息技术教育部重点实验室(邮编:610059)。E-mail:710490592@qq.com。
更新日期/Last Update: 2020-09-20