基于机器学习的钻孔数据隐式三维地质建模方法
|
摘要
针对基于钻孔数据的传统显式三维地质建模方法存在过程繁琐、模型质量难以保证等缺点,本文提出了一种基于机器学习的隐式三维地质建模方法,将地层三维建模问题转换为地下空间栅格单元的属性分类问题.分别基于支持向量机、BP神经网络等分类算法,实现了钻孔数据的自动三维地质建模.实际建模结果表明,对于有限、稀疏的钻孔数据,支持向量机方法建模准确率较高,建模效率、效果优于显式建模方法.最后通过敏感性分析研究了超参数对建模结果准确率、模型形态的影响,为可控的自动三维地质建模提供了一种新的解决思路.
Considering the complex modeling process and difficulty in guaranteeing the model quality of traditional explicit 3 D modeling methods,an implicit 3 D geological modeling method for borehole data based on machine learning was proposed,which transformed the strata 3 D modeling problem into a process of geological attribute classification of the underground spatial grid units. Based on the classification algorithms of support vector machine and BP neural network,automatic 3 D geological modeling from borehole data was realized. The results demonstrate that for sparse and limited borehole data,support vector machine can generally perform better than explicit methods. Finally,the influence of hyper-parameter on modeling accuracy and model shape is studied through sensitivity analysis,which provides a new solution for controllable 3 D geological modeling.
Considering the complex modeling process and difficulty in guaranteeing the model quality of traditional explicit 3 D modeling methods,an implicit 3 D geological modeling method for borehole data based on machine learning was proposed,which transformed the strata 3 D modeling problem into a process of geological attribute classification of the underground spatial grid units. Based on the classification algorithms of support vector machine and BP neural network,automatic 3 D geological modeling from borehole data was realized. The results demonstrate that for sparse and limited borehole data,support vector machine can generally perform better than explicit methods. Finally,the influence of hyper-parameter on modeling accuracy and model shape is studied through sensitivity analysis,which provides a new solution for controllable 3 D geological modeling.
引文
[1]朱良峰，吴信才，刘修国，等．基于钻孔数据的三维地层模型的构建[J]．地理与地理信息科学，2004,20(3):26-30.(Zhu Liang-feng,Wu Xin-cai,Liu Xiu-guo, et al.Reconstruction of 3D strata model based on borehole data[J]. Geography and Geo-information Science,2004,20(3):26-30.)
[2] Wu L X. Topological relations embodied in a generalized triprism(GTP)model for a 3D geoscience modeling system[J]. Computers&Geosciences,2004,30(4):405-418.
[3]车德福，吴立新，殷作如，等．基于GTP的断层三维交互建模方法[J]．东北大学学报(自然科学版)，2008,29(3):395-398.(Che De-fu,Wu Li-xin,Yin Zuo-ru,et al. On the GTP-based3D interactive modeling method for geological faults[J].Journal of Northeastern University(Natural Science),2008,29(3):395-398.)
[4]郭甲腾，吴立新，杨宜舟，等．岩土工程勘察场地立体空间建模与可视化信息管理[J]．东北大学学报(自然科学版)，2014,35(1):122-125.(Guo Jia-teng,Wu Li-xin,Yang Yi-zhou,et al. Threedimensional modeling and visualization information management of geotechnical engineering investigation sites[J]. Journal of Northeastern University(Natural Science),2014,35(1):122-125.)
[5] Calcagno P,Chilès J P,Courrioux G,et al. Geological modelling from field data and geological know ledge:part I.modelling method coupling 3D potential-field interpolation and geological rules[J]. Physics of the Earth&Planetary Interiors,2011,171(1):147-157.
[6] Caumon G,Gray G,Antoine C,et al. Three-dimensional implicit stratigraphic model building from remote sensing data on tetrahedral meshes:theory and application to a regional model of La Popa Basin,NE M exico[J]. IEEE Transactions on G eoscience&Remote Sensing,2013,51(3):1613-1621.
[7] Hillier M J,Schetselaar E M,Kemp E A D,et al. Threedimensional modelling of geological surfaces using generalized interpolation with radial basis functions[J].Mathematical G eosciences,2014,46(8):931-953.
[8]邢延涛，李利军．三维地质体重构中空间数据插值方法的研究[J]．计算机与数字工程，2006,34(12):45-47.(Xing Yan-tao,Li Li-jun. Research of spatial interpolation methods about the 3D-reconstruction of geological models[J]. Computer&Digital Engineering,2006,34(12):45-47.)
[9] Smirnoff A,Boisvert E,Paradis S J. Support vector machine for 3D modelling from sparse geological information of various origins[J]. Computers&G eosciences,2008,34(2):127-143.
[10] He K,Zhang X,Ren S,et al. Delving deep into rectifiers:surpassing human-level performance on imagenet classification[C]//Proceedings of the IEEE International Conference on Computer Vision. Santiago, 2015:1026-1034.
[11]ítalo G G,Kumaira S,Guadagnin F. A machine learning approach to the potential-field method for implicit modeling of geological structures[J]. Computers&G eosciences,2017,103:173-182.
[12] Abedi M,Norouzi G H,Bahroudi A. Support vector machine for multi-classification of mineral prospectivity areas[J].Computers&G eosciences,2012,46:272-283.
[13] Edwards J,Lallier F, Caumon G, et al. Uncertainty management in stratigraphic well correlation and stratigraphic architectures:a training-based method[J]. Computers&G eosciences,2017,111(2):1-17.
[14] Cracknell M J,Reading A M. Geological mapping using remote sensing data:a comparison of five machine learning algorithms,their response to variations in the spatial distribution of training data and the use of explicit spatial information[J]. Computers&G eosciences,2014,63(1):22-33.
[15]谷琼．面向非均衡数据集的机器学习及在地学数据处理中的应用[D]．武汉:中国地质大学，2009.(Gu Qiong. Research of machine learning on imbalanced data sets and its application in geoscienes data processing[D].Wuhan:China University of Geosciences,2009.)
[16] Pedregosa F,Gramfort A,Michel V,et al. Scikit-learn:machine learning in Python[J]. Journal of Machine Learning Research,2011,12(10):2825-2830.
[17] Chaudhuri A,De K,Chatterjee D. A comparative study of kernels for the multi-class support vector machine[C]//International Conference on Natural Computation. Jinan,2008:3-7.
[2] Wu L X. Topological relations embodied in a generalized triprism(GTP)model for a 3D geoscience modeling system[J]. Computers&Geosciences,2004,30(4):405-418.
[3]车德福，吴立新，殷作如，等．基于GTP的断层三维交互建模方法[J]．东北大学学报(自然科学版)，2008,29(3):395-398.(Che De-fu,Wu Li-xin,Yin Zuo-ru,et al. On the GTP-based3D interactive modeling method for geological faults[J].Journal of Northeastern University(Natural Science),2008,29(3):395-398.)
[4]郭甲腾，吴立新，杨宜舟，等．岩土工程勘察场地立体空间建模与可视化信息管理[J]．东北大学学报(自然科学版)，2014,35(1):122-125.(Guo Jia-teng,Wu Li-xin,Yang Yi-zhou,et al. Threedimensional modeling and visualization information management of geotechnical engineering investigation sites[J]. Journal of Northeastern University(Natural Science),2014,35(1):122-125.)
[5] Calcagno P,Chilès J P,Courrioux G,et al. Geological modelling from field data and geological know ledge:part I.modelling method coupling 3D potential-field interpolation and geological rules[J]. Physics of the Earth&Planetary Interiors,2011,171(1):147-157.
[6] Caumon G,Gray G,Antoine C,et al. Three-dimensional implicit stratigraphic model building from remote sensing data on tetrahedral meshes:theory and application to a regional model of La Popa Basin,NE M exico[J]. IEEE Transactions on G eoscience&Remote Sensing,2013,51(3):1613-1621.
[7] Hillier M J,Schetselaar E M,Kemp E A D,et al. Threedimensional modelling of geological surfaces using generalized interpolation with radial basis functions[J].Mathematical G eosciences,2014,46(8):931-953.
[8]邢延涛，李利军．三维地质体重构中空间数据插值方法的研究[J]．计算机与数字工程，2006,34(12):45-47.(Xing Yan-tao,Li Li-jun. Research of spatial interpolation methods about the 3D-reconstruction of geological models[J]. Computer&Digital Engineering,2006,34(12):45-47.)
[9] Smirnoff A,Boisvert E,Paradis S J. Support vector machine for 3D modelling from sparse geological information of various origins[J]. Computers&G eosciences,2008,34(2):127-143.
[10] He K,Zhang X,Ren S,et al. Delving deep into rectifiers:surpassing human-level performance on imagenet classification[C]//Proceedings of the IEEE International Conference on Computer Vision. Santiago, 2015:1026-1034.
[11]ítalo G G,Kumaira S,Guadagnin F. A machine learning approach to the potential-field method for implicit modeling of geological structures[J]. Computers&G eosciences,2017,103:173-182.
[12] Abedi M,Norouzi G H,Bahroudi A. Support vector machine for multi-classification of mineral prospectivity areas[J].Computers&G eosciences,2012,46:272-283.
[13] Edwards J,Lallier F, Caumon G, et al. Uncertainty management in stratigraphic well correlation and stratigraphic architectures:a training-based method[J]. Computers&G eosciences,2017,111(2):1-17.
[14] Cracknell M J,Reading A M. Geological mapping using remote sensing data:a comparison of five machine learning algorithms,their response to variations in the spatial distribution of training data and the use of explicit spatial information[J]. Computers&G eosciences,2014,63(1):22-33.
[15]谷琼．面向非均衡数据集的机器学习及在地学数据处理中的应用[D]．武汉:中国地质大学，2009.(Gu Qiong. Research of machine learning on imbalanced data sets and its application in geoscienes data processing[D].Wuhan:China University of Geosciences,2009.)
[16] Pedregosa F,Gramfort A,Michel V,et al. Scikit-learn:machine learning in Python[J]. Journal of Machine Learning Research,2011,12(10):2825-2830.
[17] Chaudhuri A,De K,Chatterjee D. A comparative study of kernels for the multi-class support vector machine[C]//International Conference on Natural Computation. Jinan,2008:3-7.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |