• ISSN 1003-3238
  • CN 11-2368/P

机器学习和向机器学习

E. Z. Naeini K. Prindle 汪忠德 朱晓丹 赵明

引用本文:
Citation:

机器学习和向机器学习

  • 基金项目:

    中国石油化工股份有限公司前瞻性基础研究项目"地球物理前沿技术跟踪研究"和"2018年物探新技术探索研究"(P18077-3)资助

  • 摘要: 机器学习实际上已经存在了几十年或者也可以认为存在了几个世纪。追溯到17世纪,贝叶斯、拉普拉斯关于最小二乘法的推导和马尔可夫链,这些构成了机器学习广泛使用的工具和基础。1950年(艾伦·图灵提议建立一个学习机器)到2000年初(有深度学习的实际应用以及最近的进展,比如2012年的AlexNet),机器学习有了很大的进展。在过去几年中,深度学习在各种应用领域获得巨大的成功,并且随着一些新的应用模式的出现继续开辟新的领域。最近,由于从大数据中提取有经济价值信息的需要、各种类型的神经网络和计算能力获得较大进展,以及易于使用的程序代码的出现,促使机器学习在石油和天然气工业中流行。在本文中,我们将展示机器学习如何帮助地球科学家在更短的时间内完成日常任务。演示地球科学家从机器中学习到的知识,如文档和图像分割、测井相识别、岩石物理测井预测和断层解释,并利用这些技术来检查他们的工作质量,获得细微的洞察力。另一个优点是,这些方法通过提供更精确的训练数据集来优化机器学习工作流程,从而推动模型的持续学习和提高。
  • [1]

    AlBinHassan,N.M.,and K.Marfurt,2003,Fault detection using Hough transforms:73rd Annual International Meeting,SEG,Expanded Abstra-cts,1719-1721,https://doi.org/10.1190/1.1817639.
    [2]

    Bahorich,M.,and S.Farmer,1995,3-D seismic discontinuity for faults and stratigraphic features:The coherence cube:The Leading Edge,14,no.10,1053-1058,https://doi.org/10.1190/1.1437077.
    [3]

    Barnes,A.E.,2006,A filter to improve seismic discontinuity data for fault interpretation:Geophysics,71,no.3,P1-P4,https://doi.org/10.1190/1.2195988.
    [4]

    Bayes,T.,and M.Price,1763,An essay towards solving a problem in the doctrine of chances:Philosophical Transactions,53,370-418,https://doi.org/10.1098/rstl.1763.0053.
    [5]

    Cohen,I.,and R.R.Coifman,2002,Local discon-tinuity measures for 3-d seismic data:Geophysi-cs,67,no.6,1933-1945,https://doi.org/10.1190/1.1527094.
    [6]

    Cortes,C.,and V.Vapnik,1995,Support-vector networks:Machine Learning,20,no.3,273-297,https://doi.org/10.1007/BF00994018.
    [7]

    Crevier,D.,1993,AI:The tumultuous search for artificial intelligence:Basic Books.
    [8]

    Deng,J.,W.Dong,R.Socher,L.J.Li,K.Li,and L.Fei-Fei,2009,ImageNet:A large-scale hierarchical image database:Conference on Computer Vision and Pattern Recognition,IEEE,https://doi.org/10.1109/CVPR.2009.5206848.
    [9]

    Di,H.,and D.Gao,2014,Gray-level transformation and Canny edge detection for 3D seismic discontinuity enhancement:Computers & Geoscien-ces,72,192-200,https://doi.org/10.1016/j.cageo.2014.07.011.
    [10]

    Di,H.,and D.Gao,2016,Seismic attribute-aided fault detection in petroleum industry:A review,in D.Martin,ed.,Fault detection:Methods,applica-tions and technology:Nova Science Publishers,53-80.
    [11]

    Di,H.,and D.Gao,2017,3D seismic flexure analysis for subsurface fault detection and fracture chara-cterization:Pure and Applied Geophysics,174,no.3,747-761,https://doi.org/10.1007/s00024-016-1406-9.
    [12]

    Fukushima,K.,1980,Neocognitron:A self-organi-zing neural network model for a mechanism of pattern recognition unaffected by shift in position:Biological Cybernetics,36,no.4,193-202,https://doi.org/10.1007/BF00344251.
    [13]

    Gersztenkorn,A.,and K.J.Marfurt,1999,Eigenstructure-based coherence computations as an aid to 3-d structural and stratigraphic mapping:Geophysics,64,no.5,1468-1479,https://doi.org/10.1190/1.1444651.
    [14]

    Goodfellow,I.J.,J.Pouget-Abadie,M.Mirza,B.Xu,D.Warde-Farley,S.Ozair,A.Courville,and Y.Bengio,2014,Generative adversarial networks:Proceedings of the 27th International Conference on Neural Information Processing Systems,2,2672-2680.
    [15]

    Greenspan,H.,B.van Ginneken,and R.M.Summers,2016,Guest editorial deep learning in medical imaging:Overview and future promise of an exciting new technique:Transactions on Medical Imaging,IEEE,35,no.5,1153-1159,https://doi.org/10.1109/TMI.2016.2553401.
    [16]

    Hale,D.,2013,Methods to compute fault images,extract fault surfaces,and estimate fault throws from 3D seismic images:Geophysics,78,no.2,O33-O43,https://doi.org/10.1190/geo2012-0331.1.
    [17]

    Ho,T.K.,1995,Random decision forests:Pro-ceedings of the 3rd International Conference on Document Analysis and Recognition,IEEE,278-282 https://doi.org/10.1109/ICDAR.1995.598994.
    [18]

    Hochreiter,S.,and J.Schmidhuber,1997,Long short-term memory:Neural Computation,9,no.8,1735-1780,https://doi.org/10.1162/neco.1997.9.8.1735.
    [19]

    Hopfield,J.J.,1982,Neural networks and physical systems with emergent collective computational abilities:Proceedings of the National Academy of Sciences of the United States of America,79,no.8,2554-2558,https://doi.org/10.1073/pnas.79.8.2554.
    [20]

    Infante-Paez,L.,L.F.Cardona,B.McCullough,and R.Slatt,2017,Seismic analysis of paleotopography and stratigraphic controls on total organic carbon:Rich sweet spot distribution in the Wood-ford Shale,Oklahoma,USA:Interpretation,5,no.1,T33-T47,https://doi.org/10.1190/INT-2015-0151.1.
    [21]

    Jones,K.S.,1973,Index term weighting:Information Storage and Retrieval,9,no.11,619-633,https://doi.org/10.1016/0020-0271(73)90043-0.
    [22]

    Krizhevsky,A.,I.Sutskever,and G.E.Hinton,2012,ImageNet classification with deep convolutional neural networks:Proceedings of the 25th International Conference on Neural Information Processing Systems,1097-1105.
    [23]

    Laplace,P.,1812,Théorie analytique des proba-bilités:Courcier.
    [24]

    Legendre,A.M.,1805,Nouvelles méthodes pour la détermination des orbites des comètes:Firmin Didot.
    [25]

    Linnainmaa,S.,1970,The representation of the cumulative rounding error of an algorithm as a Taylor expansion of the local rounding errors:M.S.thesis,University of Helsinki.
    [26]

    Luo,Y.,W.Higgs,and W.Kowalik,1996,Edge detection and stratigraphic analysis using 3D seismic data:66th Annual International Meeting,SEG,Expanded Abstracts,324-327,https://doi.org/10.1190/1.1826632.
    [27]

    Marfurt,K.J.,R.L.Kirlin,S.L.Farmer,and M.S.Bahorich,1998,3-D seismic attributes using a semblance-based coherency algorithm:Geophy-sics,63,no.4,1150-1165,https://doi.org/10.1190/1.1444415.
    [28]

    Markov,A.A.,1906,Extension of the law of large numbers to dependent quantities[in Russian]:Izvestiya Fiziko-Matematicheskikh Obschestva Kazan University,15,135-156.
    [29]

    McCarthy,J.,and E.Feigenbaum,1990,Arthur Sa-muel:Pioneer in machine learning:AI Magazi-ne,11,no.3,10-11.
    [30]

    Nunn,J.A.,2012,Burial and thermal history of the Haynesville Shale:Implications for overpres-sure,gas generation,and natural hydrofracture:GCAGS,1,81-96.
    [31]

    Pedersen,S.I.,T.Randen,L.Sonneland,and Ø.Steen,2002,Automatic fault extraction using artificial ants:72nd Annual International Meeting,SEG,Expanded Abstracts,512-515.
    [32]

    Qi,X.,and K.Marfurt,2017,Volumetric aberrancy to map subtle faults and flexures:87th Annual International Meeting,SEG,Expanded Abstrac-ts,3443-3447,https://doi.org/10.1190/segam2017-17632807.1.
    [33]

    Roberts,A.,2001,Curvature attributes and their application to 3D interpreted horizons:First Brea-k,19,no.2,85-100,https://doi.org/10.1046/j.0263-5046.2001.00142.x.
    [34]

    Rosenblatt,F.,1958,The perceptron:A probabilistic model for information storage and organization in the brain:Psychological Review,65,no.6,386-408,https://doi.org/10.1037/h0042519.
    [35]

    Rumelhart,D.,G.Hinton,and R.Williams,1986,Learning representations by back-propagating errors:Nature,323,533-536,https://doi.org/10.1038/323533a0.
    [36]

    Tingdahl,K.M.,and M.De Rooij,2005,Semi-automatic detection of faults in 3D seismic data:Geophysical Prospecting,53,no.4,533-542,https://doi.org/10.1111/j.1365-2478.2005.00489.x.
    [37]

    Tovaglieri,F.,and A.George,2012,Sedimentology and image-log analysis of the Jurassic Deltaic Plover Formation,Browse Basin,Australian North West Shelf:Presented at Annual Convention and Exhibition,AAPG.
    [38]

    Turing,A.,1950,Computing machinery and intelligence:Mind,59,433-460.
    [39]

    Wang,S.,S.Yuan,B.Yan,Y.He,and W.Sun,2016,Directional complex-valued coherence attributes for discontinuous edge detection:Journal of Applied Geophysics,129,1-7,https://doi.org/10.1016/j.jappgeo.2016.03.016.
    [40]

    Wang,Z.,Z.Long,G.AlRegib,A.Asjad,and M.A.Deriche,2014,Automatic fault tracking across seismic volumes via tracking vectors:International Conference on Image Processing,IEEE,5851-5855.
    [41]

    Watkins,C.J.,1989,Learning from delayed rewards:Ph.D.thesis,University of Cambridge.
  • [1] Z. F. LiM. -A. MeierE. HaukssonZ. W. ZhanJ. Andrews王林张红才 . 机器学习应用于地震预警中的地震波判别研究. 世界地震译丛, 2019, 50(5): 401-410. doi: 10.16738/j.cnki.issn.1003-3238.201905001
    [2] Y. K. Chen李帛珊唐丽华孙燕萍吕春来 . 通过无监督机器学习自动拾取微震事件. 世界地震译丛, 2019, 50(5): 411-432. doi: 10.16738/j.cnki.issn.1003-3238.201905002
    [3] Y. YamamotoK. ObanaT. TakahashiA. NakanishiS. KodairaY. Kaneda陈萍韩同城吕春来 . 南海海槽西部俯冲带日向滩地区俯冲九州-帕劳洋脊的成像. 世界地震译丛, 2014, 45(1-2): 78-93.
    [4] Peter Folger侯炳正赵仲和 . 地震:灾害风险、检测、预警和研究. 世界地震译丛, 2015, 46(5-6): 413-431. doi: 10.16738/j.cnki.issn.1003-3238.2015Z1003
    [5] T. EgbelakinS. WilkinsonJ. InghamM. ASCER. PotangaroaM. Sajoudi杨磊王宾 . 提高建筑抗震能力的激励措施和因素. 世界地震译丛, 2019, 50(2): 168-189. doi: 10.16738/j.cnki.issn.1003-3238.201902004
    [6] Masaki KanaoVladimir D. SuvorovShigeru TodaSeiji Tsuboi刘伟吕春来 . 北极地区的地震活动、结构和构造. 世界地震译丛, 2016, 47(1): 1-21. doi: 10.16738/j.cnki.issn.1003-3238.201601001
    [7] J. GombergS. PrejeanN. Ruppert邓津吕春来许忠淮 . 余滑、颤动和迪纳利断层地震. 世界地震译丛, 2013, 44(3): 17-24.
    [8] A. BaltayS. IdeG. PrietoG. Beroza袁志祥吕春来 . 地震应力降和视应力的可变性. 世界地震译丛, 2013, 44(3): 25-31.
    [9] V. Vavryčuk高熹微宋程万永革吕春来 . 根据震源机制迭代联合反演应力和断层取向. 世界地震译丛, 2014, 45(4): 21-33.
    [10] Y. G. WanZ. -K. ShenR. BürgmannJ. B. SunM. Wang靳志同万永革 . 根据GPS和InSAR测量推断2008年MW7.9汶川地震的断层形状和破裂分布. 世界地震译丛, 2018, 49(3): 195-221. doi: 10.16738/j.cnkii.ssn.1003-3238.201803002
    [11] 黄有志姚华建吴大铭梁文宗黄柏寿林正洪温国梁李万金吕春来 . 根据环境地震噪声和远震瑞雷波分析得到的台湾海峡地壳和上地幔S波速度结构. 世界地震译丛, 2014, 45(4): 46-65.
    [12] I. KurzonF. L. VernonA. RosenbergerY. Ben-Zion刘长生李万金赵谊吴何珍 . 利用奇异值分解方法实时自动检测P波和S波. 世界地震译丛, 2017, 48(4): 291-307. doi: 10.16738/j.cnki.issn.1003-3238.201704002
    [13] César R. RaneroMarta Pérez-Gussinyé刘见宝吕春来 . 相继断层作用解释共轭边缘的非对称性和伸展差异. 世界地震译丛, 2017, 48(1): 62-73. doi: 10.16738/j.cnki.issn.1003-3238.201701005
    [14] U. S. Geological Survey邹立晔梁姗姗杜广宝赵博张雪梅苗春兰万事成齐刚徐志国刘杰王春华黄媛 . 美国国家现代地震监测系统(ANSS)——现状、发展机遇和战略规划(2017~2027). 世界地震译丛, 2018, 49(5): 397-423. doi: 10.16738/j.cnkii.ssn.1003-3238.201805001
    [15] E. M. ThompsonD. J. WaldC. B. Worden杨国栋高曙德金严 . 带有地质和地形约束的加利福尼亚州VS30图. 世界地震译丛, 2016, 47(2): 147-159. doi: 10.16738/j.cnki.issn.1003-3238.201602005
    [16] Jeanne L. Hardebeck靳志同万永革李一琼 . 俯冲带的应力方向和俯冲带大型逆断层的强度. 世界地震译丛, 2016, 47(3): 255-260. doi: 10.16738/j.cnki.issn.1003-3238.201603007
    [17] Haruo SatoMichael C. FehlerTakuto Maeda朱维吴何珍 . 《非均匀地球中的地震波传播和散射:第二版》引言. 世界地震译丛, 2016, 47(4): 269-281. doi: 10.16738/j.cnki.issn.1003-3238.201604001
    [18] Huan-Huan BIANYu-Duo WANG孙宏志卢山赵龙梅许卫卫吕春来 . 微震信号无线数据采集和远程传输接口的设计. 世界地震译丛, 2015, 46(1): 58-65.
    [19] A. McPhersonL. Hall谭颖吕春来 . 澳大利亚地震危险性和灾害风险评估中的场地分类. 世界地震译丛, 2013, 44(3): 32-52.
    [20] O. S. Boyd李晶吕春来 . 包括前震和余震的不含时间的地震危险性概率分析. 世界地震译丛, 2013, 44(4): 37-47.
  • 加载中
计量
  • 文章访问数:  74
  • HTML全文浏览量:  24
  • PDF下载量:  6
  • 被引次数: 0
出版历程

机器学习和向机器学习

基金项目:  中国石油化工股份有限公司前瞻性基础研究项目"地球物理前沿技术跟踪研究"和"2018年物探新技术探索研究"(P18077-3)资助

摘要: 机器学习实际上已经存在了几十年或者也可以认为存在了几个世纪。追溯到17世纪,贝叶斯、拉普拉斯关于最小二乘法的推导和马尔可夫链,这些构成了机器学习广泛使用的工具和基础。1950年(艾伦·图灵提议建立一个学习机器)到2000年初(有深度学习的实际应用以及最近的进展,比如2012年的AlexNet),机器学习有了很大的进展。在过去几年中,深度学习在各种应用领域获得巨大的成功,并且随着一些新的应用模式的出现继续开辟新的领域。最近,由于从大数据中提取有经济价值信息的需要、各种类型的神经网络和计算能力获得较大进展,以及易于使用的程序代码的出现,促使机器学习在石油和天然气工业中流行。在本文中,我们将展示机器学习如何帮助地球科学家在更短的时间内完成日常任务。演示地球科学家从机器中学习到的知识,如文档和图像分割、测井相识别、岩石物理测井预测和断层解释,并利用这些技术来检查他们的工作质量,获得细微的洞察力。另一个优点是,这些方法通过提供更精确的训练数据集来优化机器学习工作流程,从而推动模型的持续学习和提高。

English Abstract

参考文献 (41)

目录

    /

    返回文章
    返回