Abstract:The application of machine learning algorithms in the field of geophysics has been expanded and deepened.In fault recognition on seismic data,the main approach is training a shallow convolutional neural network to achieve fault recognition using actual or synthetical fault samples.Actual fault samples require manual marking,which is very time-consuming.Synthetic fault samples are easy to obtain,but the effect of the trained network model is inadequate when applied to actual seismic data.For this reason,this paper combines a deep residual network with transfer learning to fault recognition.First train synthetical fault samples by constructing a deep residual network with better performance,then use a small number of actual fault samples for transfer learning.This way the generalization ability of the network can be enhanced, and the recognition results can be optimized.After transfer learning,the network can more effectively improve the recognition accuracy of actual faults than ever before.Actual seismic data have proved the feasibility and effectiveness of the method.
Bahorich M S,Farmer S L.3-D seismic discontinuity for faults and stratigraphic features:The coherence cube[C].SEG Technical Program Expanded Abstracts,1995,14:93-96.
[2]
Marfurt K J,Kirlin R L,Farmer S L,et al.3-D seismic attributes using a semblance-based coherency algorithm[J].Geophysics,1998,63(4):1150-1165.
[3]
Gersztenkorn A,Marfurt K J.Eigenstructure-based coherence computations as an aid to 3-D structural and stratigraphic mapping[J].Geophysics,1999,64(5):1468-1479.
[4]
Rande T,Reymond B,Sjulstad H I,et al.New seismic attributes for automated stratigraphic facies boundary detection[C].SEG Technical Program Expanded Abstracts,1999,18:628-631.
[5]
严哲,顾汉明,蔡成国,等.利用方向约束蚁群算法识别断层[J].石油地球物理勘探,2011,46(4):614-620.YAN Zhe,GU Hanming,CAI Chengguo,et al.Fault identification by orientation constraint ant colony algorithm[J].Oil Geophysical Prospecting,2011,46(4):614-620.
[6]
李楠,王龙颖,黄胜兵,等.利用高清蚂蚁体精细解释复杂断裂带[J].石油地球物理勘探,2019,54(1):182-190.LI Nan,WANG Longying,HUANG Shengbing,et al.3D seismic fine structural interpretation in complex fault zones based on the high-definition ant-tracking attribute volume[J].Oil Geophysical Prospecting,2019,54(1):182-190.
[7]
陈雷,肖创柏,禹晶,等.基于相似性传播聚类与主成分分析的断层识别方法[J].石油地球物理勘探,2017,52(4):826-833.CHEN Lei,XIAO Chuangbai,YU Jing,et al.Fault recognition based on affinity propagation clustering and principal component analysis[J].Oil Geophysical Prospecting,2017,52(4):826-833.
李军,张军华,刘杨,等.图像熵各向异性扩散保边滤波方法及在断层识别中的应用[J].石油地球物理勘探,2019,54(2):365-370.LI Jun,ZHANG Junhua,LIU Yang,et al.Anisotropic diffusion edge-preserved filter based on image entropy and application in fault identification[J].Oil Geophy-sical Prospecting,2019,54(2):365-370.
[10]
董守华,石亚丁,汪洋.地震多参数BP人工神经网络自动识别小断层[J].中国矿业大学学报,1997,26(3):16-20.DONG Shouhua,SHI Yading,WANG Yang.Automatic recognition of small fault by BP artificial ner-vous network from multiple seismic parameters[J].Journal of China University of Mining & Technology,1997,26(3):16-20.
[11]
崔若飞.神经网络技术在地震资料构造解释中的应用[J].地球物理学进展,1997,12(4):67-75.CUI Ruofei.Application of structure interpretation with seismic data using artificial network[J].Progress in Geophysics,1997,12(4):67-75.
[12]
Lecun Y,Kavukcuoglu K,Farabet C.Convolutional networks and applications in vision[C].2010 IEEE International Symposium on Circuits and Systems,2010,253-256.
[13]
Huang L,Dong X,Clee T E.A scalable deep learning platform for identifying geologic features from seismic attributes[J].The Leading Edge,2017,36(3):249-256.
[14]
Guitton A.3D Convolutional neural networks for fault interpretation[C].Extended Abstracts of 80th EAGE Conference and Exhibition,2018,1-5.
[15]
Wu X M,Shi Y Z,Fomel S,et al.Convolutional neural networks for fault interpretation in seismic images[C].SEG Technical Program Expanded Abstracts 2018,37:1946-1950.
[16]
Liu Z,Song C,She B,et al.Visual explanations from convolutional neural networks for fault detection[C].SEG Technical Program Expanded Abstracts,2018,37:2226-2230.
Ma Y,Ji X,Nasher M,et al.Automatic fault detection with convolutional neural networks[C].CPS/SEG International Geophysical Conference,Beijing,China,2018,786-790.
[19]
Guo B,Liu L,Luo Y.Automatic seismic fault detection with convolutional neural network[C].CPS/SEG International Geophysical Conference,Beijing,China,2018,1786-1789.
[20]
Wu X M,Liang L M,Shi Y Z,et al.Fault Seg3D:using synthetic datasets to train an end-to-end convolutional neural network for 3D seismic fault segmentation[J].Geophysics,2019,84(3):IM35-IM45.
[21]
He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[C].The IEEE Conference on Computer Vision and Pattern Recognition (CVPR),Las Vegas,USA,2016,770-778.
[22]
Michael N.Neural Networks and Deep Learning[EB/OL].(2015)[2020-6-5].http://neuralnetworksanddeeplearning.com/.
[23]
Pan S J,Yang Q.A survey on transfer learning[J].IEEE Transactions on Knowledge and Data Enginee-ring,2010,22(10):1345-1359.
[24]
庄福振,罗平,何清,等.迁移学习研究进展[J].软件学报,2015,26(1):26-39.ZHUANG Fuzhen,LUO Ping,HE Qing,et al.Survey on transfer learning research[J].Journal of Software,2015,26(1):26-39.
[25]
Krizhevsky A,Sutskever I,Hinton G E.Image net classification with deep convolutional neural networks[C].Advances in Neural Information Processing Systems,2012,25(2):1097-1105.
[26]
刘万军,梁雪剑,曲海成.不同池化模型的卷积神经网络学习性能研究[J].中国图象图形学报,2016,21(9):1178-1190.LIU Wanjun,LIANG Xuejian,QU Haicheng.Lear-ning performance of convolutional neural networks with different pooling models[J].Journal of Image and Graphics,2016,21(9):1178-1190.
[27]
Kingma D,Ba J.Adam:A method for stochastic optimization[C].International Conference for Learning Representations,San Diego,2015.
[28]
Wang J,Jiang T,Cheung J.Transfer Learning Tutorial[EB/OL].(2018)[2020-6-5].https://github.com/jindongwang/transferlearning-tutorial.
[29]
Dai W,Jin O,Xue G,et al.EigenTransfer:a unified framework for transfer learning[C].The 26th Annual International Conference on Machine Learning 2009,193-200.
[30]
Rosenstein M T,Marx Z,Kaelbling L P,et al.To transfer or not to transfer[C].NIPS 2005 Workshop on Transfer Learning.2005,1-4.