基于机器学习的地层序列模拟
|
摘要
地层结构及其分布的模拟是地质信息化研究与工程规划设计建造的迫切需求。现有的研究方法主要以钻孔数据为基础,选择插值方法进行二维剖面绘制和三维地层建模。插值方法是决定模拟结果准确程度的重要因素,但插值方法的选取受主观因素影响,缺乏科学合理性,难以推广应用。针对这一问题,本文提出一种基于钻孔数据进行机器学习的地层序列模拟方法,即将钻孔地层数据处理为地层类型序列与地层层厚序列,利用循环神经网络与序列-序列架构建立地层序列模拟模型。通过将模拟结果与实际钻孔数据对比分析,发现地层序列模型可以较准确地模拟地表到基岩面之间的地层类型与厚度范围。研究可为地层模拟提供新方法。
The structure and distribution simulation of strata is an urgent demand in geological informatization as well as engineering. Current study methods are mostly based on borehole data,drawing stratigraphic section or building three-dimensional geological model through interpolation. Interpolation is an important factor in accuracy.However,the determination of interpolation method is subjective,lacking of scientific consideration and therefore difficult to apply to other distinct. Therefore,this study proposes a stratigraphic sequence simulation method based on machine learning. The method considers the borehole data as type and thickness sequence,and presents the stratigraphic sequence simulation model based on recurrent neural network and sequence to sequence learning.Comparing the simulation sequence to the actual borehole data,the result indicates that the machine learning-based model are capable of describing the stratigraphic sequence above bedrock using coordinate information. This study provides a new method for stratigraphy study.
The structure and distribution simulation of strata is an urgent demand in geological informatization as well as engineering. Current study methods are mostly based on borehole data,drawing stratigraphic section or building three-dimensional geological model through interpolation. Interpolation is an important factor in accuracy.However,the determination of interpolation method is subjective,lacking of scientific consideration and therefore difficult to apply to other distinct. Therefore,this study proposes a stratigraphic sequence simulation method based on machine learning. The method considers the borehole data as type and thickness sequence,and presents the stratigraphic sequence simulation model based on recurrent neural network and sequence to sequence learning.Comparing the simulation sequence to the actual borehole data,the result indicates that the machine learning-based model are capable of describing the stratigraphic sequence above bedrock using coordinate information. This study provides a new method for stratigraphy study.
引文
Bhattacharya B,Solomatine D P.2006.Machine learning in soil classification[J].Neural Networks,19(2):186-195.
Breiman L.2001.Statistical modeling:The two cultures[J].Statistical Science,16(3):199-215.
Chen G,An K,Li X.2016.Identification and classification of adverse geological body based on convolution neural networks[J].Geological Science and Technology Information,35(1):205-211.
Cheng G J,Guo W H,Fan P Z.2017.Study on rock image classification based on convolution neural network[J].Journal of Xi'an Shiyou University(Natural Science Edition),32(4):116-122.
Cho K,Van Merrienboer B,Gulcehre C,et al.2014.Learning phrase representations using RNN encoder-decoder for statistical machine translation[J].Arcxiv Preprint arxiv:14061078.
Duan T Z,Griffiths C M,Johnsen S O.2001.High-frequency sequence stratigraphy using syntactic methods and clustering applied to the upper limestone coal group of the Kincardine Basin,United Kingdom[J].Mathematical Geology,33(7):825-844.
Duan Y X,Li G T,Sun Q F.2016.Research on convolutional neural network for reservoir parameter prediction[J].Journal on Communications,37(S1):1-9.
Goodfellow I,Bengio Y,Courville A.2016.Deep learning[M].Cambridge:The MIT Press.
Huang H W,Li Q T.2017.Image recognition for water leakage in shield tunnel based on deep learning[J].Chinese Journal of Rock Mechanics and Engineering,36(12):2861-2871.
Huang Z,Zhao K,Xu H,et al.2017.Prediction of surface settlement induced by soft soil excavation based on SA-BP neural networks[J].Journal of Engineering Geology,25(S1):445-451.
Ji B.2017.Synthetic information mineral prediction research of polymetallic deposit in Haobugao distinct,Inner Mongolia[D].Hefei:Hefei University of Technology.
Korup O,Stolle A.2014.Landslide prediction from machine learning[J].Geology Today,30(1):26-33.
Liu X Z.2010.The application of BP neural network in lithology identification in Liaohe depression archaeozoic era inner buried hill[J].Petroleum Geology and Engineering,24(5):40-42,142-143.
Que J S,Yan H X,Wang H B,et al.2016.Prediction of the landslide displacement based on the wavelet theory and BP neural network[J].Journal of Engineering Geology,24(S1):630-635.
Rodriguez-Galiano V,Sanchez-Castillo M,Chica-Olmo M,et al.2015.Machine learning predictive models for mineral prospectivity:An evaluation ofneural networks,random forest,regression trees and support vector machines[J].Ore Geology Reviews,71:804-818.
Sha A M,Tong Z,Gao J.2018.Recognition and measurement of pavement disasters based on convolutional neural networks[J].China Journal of Highway and Transport,31(1):1-10.
Song R B,Jiang N,Yin B,et al.2017.Method of automatically modeling complex geological bodies with arcgis model builder[J].Journal of Engineering Geology,25(2):393-401.
Song R B,Qin X Q,Tao Y Q,et al.2018.A semi-automatic method for3D modeling and visualizing complex geological bodies[J].Bulletin of Engineering Geology and the Environment,1-13.
Sutskever I,Vinyals O,Le Q V.2014.Sequence to sequence learning with neural networks[C]//Advances in neural information processing systems:3104-3112.
Wang R Y,Wang Q,Zhang Y,et al.2013.Time series-dynamic neural network forecast on dredger fill settlement[J].Journal of Engineering Geology,21(3):351-356.
Wang X,Li Y,Chen T J,et al.2017.Quantitative thickness prediction of tectonically deformed coal using Extreme Learning Machine and Principal Component Analysis:a case study[J].Computers&Geosciences,101:38-47.
Watson C,Richardson J,Wood B,et al.2015.Improving geological and process model integration through TIN to 3D grid conversion[J].Computers&Geosciences,82(C):45-54.
Wen J W,Chen C,Chen B Y,et al.2013.Visualization model of the stratum three-dimensional structure based on GMS and the prediction of the neural network[J].Science&Technology Review,31(15):44-51.
Xie M L,Zhao J J,Qu S J,et al.2016.Prediction of rock strength considering multi-factors interaction[J].Journal of Engineering Geology,24(S1):868-873.
Yang G,Qiao S J,Chen P F,et al.2015.Rock and soil classification using PLS-DA and SVM combined with a laser-induced breakdown spectroscopy Library[J].Plasma Science and Technology,17(8):656.
Yang G,Qiao S J,Chen P F,et al.2015.Rock and soil classification using PLS-DA and SVM combined with a laser-induced breakdown spectroscopy Library[J].Plasma Science and Technology,17(8):656.
Zhang R C,Li H,Wu M F,et al.2015.An automatic unified modeling method of geological object and engineering object based on triprism(TP)[J].Journal of Central South University,22(4):1419-1426.
Zhang T.2016.The relationships between rock elements and the igneous rocks,the lithological discrimination and mineral identification of sedimentary rocks:a study based on the Artificial Neural Networks[D].Xi‘an:Northwest University.
Zhang Y,Su G,Yan L.2011.Gaussian Process machine learning model for forecasting of karstic collapse[C]//International Conference on Applied Informatics and Communication.Springer Berlin Heidelberg:365-372.
Zhou C Y,Dong L G.2006.Block theory for the structure of 3Dstratum[J].Chinese Journal of Geotechnical Engineering,28(9):1081-1084.
Zhou C Y,Kong L H,Liu Z,et al.2017.A meshless method for 3Dgeological modeling:China CN107481320A[P].2017-12-15.
陈冠宇,安凯,李向.2016.基于卷积神经网络的不良地质体识别与分类[J].地质科技情报,35(1):205-211.
程国建,郭文惠,范鹏召.2017.基于卷积神经网络的岩石图像分类[J].西安石油大学学报(自然科学版),32(4):116-122.
段友祥,李根田,孙歧峰.2016.卷积神经网络在储层预测中的应用研究[J].通信学报,37(增刊1):1-9.
黄宏伟,李庆桐.2017.基于深度学习的盾构隧道渗漏水病害图像识别[J].岩石力学与工程学报,36(12):2861-2871.
黄震,赵奎,许宏伟,等.2017.基于SA-BP神经网络的软土基坑开挖地表沉降预测[J].工程地质学报,25(S1):445-451.
季斌.2017.内蒙古浩布高地区多金属矿综合信息找矿预测研究[D].合肥:合肥工业大学.
解明礼,赵建军,瞿生军,等.2016.考虑多因素交互作用的岩石强度预测[J].工程地质学报,24(S1):868-873.
刘兴周.2010.BP神经网络在辽河坳陷太古宇潜山内幕岩性识别中的应用[J].石油地质与工程,24(5):40-42,142-143.
阙金声,燕慧晓,王洪播,等.2016.基于小波理论与人工神经网络的滑坡变形预测[J].工程地质学报,24(S1):630-635.
沙爱民,童峥,高杰.2018.基于卷积神经网络的路表病害识别与测量[J].中国公路学报,31(1):1-10.
宋仁波,江南,殷彪,等.2017.基于Arc GIS Model Builder的复杂地质体自动建模方法[J].工程地质学报,25(2):393-401.
王蕊颖,王清,张颖,等.2013.基于时间序列-动态神经网络吹填土沉降预测研究[J].工程地质学报,21(3):351-356.
温继伟,陈晨,陈宝义,等.2013.基于GMS的地层三维结构可视化模型及神经网络预测[J].科技导报,31(15):44-51.
张涛.2016.用人工神经网络研究元素与岩浆岩、沉积岩岩性及沉积岩矿物的关系[D].西安:西北大学.
周翠英,董立国.2006.三维地层构造的块体理论方法[J].岩土工程学报,28(9):1081-1084.
Breiman L.2001.Statistical modeling:The two cultures[J].Statistical Science,16(3):199-215.
Chen G,An K,Li X.2016.Identification and classification of adverse geological body based on convolution neural networks[J].Geological Science and Technology Information,35(1):205-211.
Cheng G J,Guo W H,Fan P Z.2017.Study on rock image classification based on convolution neural network[J].Journal of Xi'an Shiyou University(Natural Science Edition),32(4):116-122.
Cho K,Van Merrienboer B,Gulcehre C,et al.2014.Learning phrase representations using RNN encoder-decoder for statistical machine translation[J].Arcxiv Preprint arxiv:14061078.
Duan T Z,Griffiths C M,Johnsen S O.2001.High-frequency sequence stratigraphy using syntactic methods and clustering applied to the upper limestone coal group of the Kincardine Basin,United Kingdom[J].Mathematical Geology,33(7):825-844.
Duan Y X,Li G T,Sun Q F.2016.Research on convolutional neural network for reservoir parameter prediction[J].Journal on Communications,37(S1):1-9.
Goodfellow I,Bengio Y,Courville A.2016.Deep learning[M].Cambridge:The MIT Press.
Huang H W,Li Q T.2017.Image recognition for water leakage in shield tunnel based on deep learning[J].Chinese Journal of Rock Mechanics and Engineering,36(12):2861-2871.
Huang Z,Zhao K,Xu H,et al.2017.Prediction of surface settlement induced by soft soil excavation based on SA-BP neural networks[J].Journal of Engineering Geology,25(S1):445-451.
Ji B.2017.Synthetic information mineral prediction research of polymetallic deposit in Haobugao distinct,Inner Mongolia[D].Hefei:Hefei University of Technology.
Korup O,Stolle A.2014.Landslide prediction from machine learning[J].Geology Today,30(1):26-33.
Liu X Z.2010.The application of BP neural network in lithology identification in Liaohe depression archaeozoic era inner buried hill[J].Petroleum Geology and Engineering,24(5):40-42,142-143.
Que J S,Yan H X,Wang H B,et al.2016.Prediction of the landslide displacement based on the wavelet theory and BP neural network[J].Journal of Engineering Geology,24(S1):630-635.
Rodriguez-Galiano V,Sanchez-Castillo M,Chica-Olmo M,et al.2015.Machine learning predictive models for mineral prospectivity:An evaluation ofneural networks,random forest,regression trees and support vector machines[J].Ore Geology Reviews,71:804-818.
Sha A M,Tong Z,Gao J.2018.Recognition and measurement of pavement disasters based on convolutional neural networks[J].China Journal of Highway and Transport,31(1):1-10.
Song R B,Jiang N,Yin B,et al.2017.Method of automatically modeling complex geological bodies with arcgis model builder[J].Journal of Engineering Geology,25(2):393-401.
Song R B,Qin X Q,Tao Y Q,et al.2018.A semi-automatic method for3D modeling and visualizing complex geological bodies[J].Bulletin of Engineering Geology and the Environment,1-13.
Sutskever I,Vinyals O,Le Q V.2014.Sequence to sequence learning with neural networks[C]//Advances in neural information processing systems:3104-3112.
Wang R Y,Wang Q,Zhang Y,et al.2013.Time series-dynamic neural network forecast on dredger fill settlement[J].Journal of Engineering Geology,21(3):351-356.
Wang X,Li Y,Chen T J,et al.2017.Quantitative thickness prediction of tectonically deformed coal using Extreme Learning Machine and Principal Component Analysis:a case study[J].Computers&Geosciences,101:38-47.
Watson C,Richardson J,Wood B,et al.2015.Improving geological and process model integration through TIN to 3D grid conversion[J].Computers&Geosciences,82(C):45-54.
Wen J W,Chen C,Chen B Y,et al.2013.Visualization model of the stratum three-dimensional structure based on GMS and the prediction of the neural network[J].Science&Technology Review,31(15):44-51.
Xie M L,Zhao J J,Qu S J,et al.2016.Prediction of rock strength considering multi-factors interaction[J].Journal of Engineering Geology,24(S1):868-873.
Yang G,Qiao S J,Chen P F,et al.2015.Rock and soil classification using PLS-DA and SVM combined with a laser-induced breakdown spectroscopy Library[J].Plasma Science and Technology,17(8):656.
Yang G,Qiao S J,Chen P F,et al.2015.Rock and soil classification using PLS-DA and SVM combined with a laser-induced breakdown spectroscopy Library[J].Plasma Science and Technology,17(8):656.
Zhang R C,Li H,Wu M F,et al.2015.An automatic unified modeling method of geological object and engineering object based on triprism(TP)[J].Journal of Central South University,22(4):1419-1426.
Zhang T.2016.The relationships between rock elements and the igneous rocks,the lithological discrimination and mineral identification of sedimentary rocks:a study based on the Artificial Neural Networks[D].Xi‘an:Northwest University.
Zhang Y,Su G,Yan L.2011.Gaussian Process machine learning model for forecasting of karstic collapse[C]//International Conference on Applied Informatics and Communication.Springer Berlin Heidelberg:365-372.
Zhou C Y,Dong L G.2006.Block theory for the structure of 3Dstratum[J].Chinese Journal of Geotechnical Engineering,28(9):1081-1084.
Zhou C Y,Kong L H,Liu Z,et al.2017.A meshless method for 3Dgeological modeling:China CN107481320A[P].2017-12-15.
陈冠宇,安凯,李向.2016.基于卷积神经网络的不良地质体识别与分类[J].地质科技情报,35(1):205-211.
程国建,郭文惠,范鹏召.2017.基于卷积神经网络的岩石图像分类[J].西安石油大学学报(自然科学版),32(4):116-122.
段友祥,李根田,孙歧峰.2016.卷积神经网络在储层预测中的应用研究[J].通信学报,37(增刊1):1-9.
黄宏伟,李庆桐.2017.基于深度学习的盾构隧道渗漏水病害图像识别[J].岩石力学与工程学报,36(12):2861-2871.
黄震,赵奎,许宏伟,等.2017.基于SA-BP神经网络的软土基坑开挖地表沉降预测[J].工程地质学报,25(S1):445-451.
季斌.2017.内蒙古浩布高地区多金属矿综合信息找矿预测研究[D].合肥:合肥工业大学.
解明礼,赵建军,瞿生军,等.2016.考虑多因素交互作用的岩石强度预测[J].工程地质学报,24(S1):868-873.
刘兴周.2010.BP神经网络在辽河坳陷太古宇潜山内幕岩性识别中的应用[J].石油地质与工程,24(5):40-42,142-143.
阙金声,燕慧晓,王洪播,等.2016.基于小波理论与人工神经网络的滑坡变形预测[J].工程地质学报,24(S1):630-635.
沙爱民,童峥,高杰.2018.基于卷积神经网络的路表病害识别与测量[J].中国公路学报,31(1):1-10.
宋仁波,江南,殷彪,等.2017.基于Arc GIS Model Builder的复杂地质体自动建模方法[J].工程地质学报,25(2):393-401.
王蕊颖,王清,张颖,等.2013.基于时间序列-动态神经网络吹填土沉降预测研究[J].工程地质学报,21(3):351-356.
温继伟,陈晨,陈宝义,等.2013.基于GMS的地层三维结构可视化模型及神经网络预测[J].科技导报,31(15):44-51.
张涛.2016.用人工神经网络研究元素与岩浆岩、沉积岩岩性及沉积岩矿物的关系[D].西安:西北大学.
周翠英,董立国.2006.三维地层构造的块体理论方法[J].岩土工程学报,28(9):1081-1084.
© 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 |