AVO types discrimination based on a proximal support vector machine
Li Wenxiu1,2,3, Wen Xiaotao1,2, Li Tian3, Li Leihao1, Liu Songming1, Yang Jixin1
1. Institute of Geophysics, Chengdu University of Technology, Chengdu, Sichuan 610059, China; 2. State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Chengdu University of Technology, Chengdu, Sichuan 610059, China; 3. First Investigation and Design Co., Yunnan Construction Investment LTD, Kunming, Yunnan 650031, China
Abstract:AVO is an important approach for reservoir oil and gas analysis.It can qualitatively describe oil reservoirs.The AVO conventional classification depends mainly on human discrimination so that the discrimination result is often inaccurate and the workload is heavy.In this paper,we extract feature parameters from four types of AVO curves as a training set,and introduce the proximal support vector machine method to AVO types discrimination.Based on the shape of four types of gas AVO curves,taking the morphological features of pre-stack seismic data as input parameters,AVO types of the reservoir in a survey area are obtained.This method is applied to the automatic identification of AVO types in a clastic-rock gas field in the South China Sea,and more accurate results are obtained.The proposed method provides a reliable and convenient tool for AVO types discrimination in reservoirs.
李文秀, 文晓涛, 李天, 李雷豪, 刘松鸣, 杨吉鑫. 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, Li Leihao, Liu Songming, Yang Jixin. AVO types discrimination based on a proximal support vector machine. Oil Geophysical Prospecting, 2018, 53(5): 969-974.
Rutherford S R,Williams R H.Amplitude versus offset variations in gas sands.Geophysics,1989,54(6):680-688.
[2]
Castagna J P,Swan H W.Principles of AVO cross plotting.The Leading Edge,1997,16(4):337-342.
[3]
Mahob P N and Castagna J P.AVO hodogram and polarization attributes.The Leading Edge,2002,21(1):18-27.
[4]
Yoo S,Gibson Jr R L.Frequency dependent AVO analysis after target oriented stretch correction.SEG Technical Program Expanded Abstracts,2005,24:293-296.
[5]
Chapman M,Liu E,Li X.The influence of fluid-sensitive dispersion and attenuation on AVO analysis.Geophysical Journal International,2010,167(1):89-105.
[6]
钟晗,刘洋.频变AVO影响因素分析.石油地球物理勘探,2017,52(4):783-796.Zhong Han,Liu Yang.Influnce factor on frequency-dependent AVO.OGP,2017,52(4):783-796.
[7]
Li J,Castagna J.Support vector pattern recognition and AVO classification.SEG Technical Program Expanded Abstracts,2003,22:262-265.
[8]
Russell B,Ross C,Lines L.Neural networks and AVO.The Leading Edge,2002,21(3):268-314.
[9]
Vapnik V,Golowich S E,Smola A.Support vector method for function approximation,regression estimation,and signal processing.Advances in Neural Information Processing Systems,1996,281-287.
Vapnik V,Ladimir N.The nature of statistical learning theory.IEEE Transactions on Neural Networks,2002,8(6):1564-1564.
[12]
邴萍萍,曹思远,路交通.基于支持向量机的非线性AVO反演.地球物理学报,2012,55(3):1025-1032.Bing Pingping,Cao Siyuan,Lu Jiaotong.Non-linear AVO inversion based on support vector machine.Chinese Journal of Geophysics,2012,55(3):1025-1032.
[13]
杨培杰,印兴耀.基于支持向量机的叠前地震反演方法.中国石油大学学报(自然科学版),2008,32(1):37-41.Yang Peijie,Yin Xingyao.Prestack seismic inversion method based on support vector machine.Journal of China University of Petroleum(Natural Science Edtion),2008,32(1):37-41.
[14]
苏建龙,米鸿,王彦春等.基于支持向量机的非线性弹性阻抗反演方法.石油地球物理勘探,2014,49(4):751-758.Su Jianlong,Mi Hong,Wang Yanchun et al.Non-linear elastic impedance inversion method supported by vector machines.OGP,2014,49(4):751-758.
[15]
张长开,姜秀娣,朱振宇等.基于支持向量机的属性优选和储层预测.石油地球物理勘探,2012,47(2):282-285.Zhang Changkai,Jiang Xiudi,Zhu Zhenyu et al.Attributes selection and reservoir prediction based on support vector machine.OGP,2012,47(2):282-285.
[16]
殷文,李援,郭加树等.基于改进蚁群追踪策略的地震层位自动识别方法.石油地球物理勘探,2017,52(3):553-561.Yin Wen,Li Yuan,Guo Jiashu et al.Seismic horizon automatic identification based on ant colony tracking strategy.OGP,2017,52(3):553-561.
[17]
王艳伟,夏克文,牛文佳等.基于低秩矩阵恢复的去噪方法在石油测井中的应用.石油物探,2017,56(5):644-650.Wang Yanwei,Xia Kewen,Niu Wenjia et al.A denoising method by low-rank matrix recovery and its application in oil well logging.GPP,2017,56(5):644-650.
[18]
Fung G,Mangasarian O L.Proximal support vector machine classifiers.Proceedings of the 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,ACM,2001.
[19]
Zhao T,Jayaram V,Marfurt K J et al.Lithofacies classification in Barnett Shale using proximal support vector machines.SEG Technical Program Expanded Abstracts,2014,33:1491-1495
[20]
Zhang B,Zhao T,Jin X et al.Brittleness evaluation of resource plays by integrating petrophysical and seismic data analysis.Interpretation,2015,3(2):T81-T92.
[21]
刘佳乐,文晓涛,张瑞等.辽宁化工,2016(4):449-453.Liu Jiale,Wen Xiaotao,Zhang Rui et al.A fluid identification method based on proximal support vector machine.Liaoning Chemical Industry,2016(4):449-453.
[22]
Hsu C W,Lin C J.A comparison of methods for multi-class support vector machines.IEEE Transactions on Neural Networks,2002,13(2):415-425.
[23]
程学云.PSVM多类分类及其应用.信息技术,2009,33(4):12-14.Cheng Xueyun.Multi-category proximal support vector machine and its applications.Information Techno-logy,2009,33(4):12-14.