Research on depth residual method of super-resolution for intelligent seismic wave first arrival pickup
LI Jianping1,2, ZHANG Shuowei1, DING Renwei1,3, MA Xiaomin1, ZHAO Lihong1,3, ZHAO Shuo1
1. College of Earth Sciences and Engineering, Shandong University of Science and Technology, Qingdao, Shandong 266590, China; 2. Shandong Institute of Geophysical & Geochemical Exploration, Jinan, Shandong 221116, China; 3. Qingdao National Laboratory for Marine Science and Technology, Functional Laboratory for Marine Mineral Resources Evaluation and Exploration Technology, Qingdao, Shandong 266237, China
Abstract:In view of the low precision and poor generalization ability in the first arrival pickup of conventional semantic segmentation networks, an intelligent first arrival pickup method for depth residual network of super-reso-lution (SD-Net) based on a U-Net network, residual learning module, and subpixel convolution method is proposed. This method uses a U-shaped network with a jump connection to fuse multi-scale information of seismic data and simplifies the work through end-to-end training. Firstly, the residual learning module is introduced in the downsampling stage of SD-Net to overcome the deep network degradation problem and effectively improve the learning ability of seismic data. Secondly, the subpixel convolution method is used in the upsampling stage to achieve the super-resolution reconstruction of the feature map through convolution and multi-channel pixel recombination, and the positioning of the first arrival is achieved with higher accuracy. In addition, transfer learning is utilized to apply the model to the simulated data with a medium and low signal-to-noise ratio (SNR), and the optimal first arrival pickup model can be obtained by training only a small amount of labeled data. Practical examples show that the training efficiency of the SD-Net is significantly improved compared with that of the U-Net method. The network model has higher accuracy and robustness. The results predicted by the transfer learning model prove that SD-Net has a strong generalization ability. This method is of great significance for realizing efficient and accurate intelligent first arrival pickup in actual production.
曾庆才,曾同生,欧阳永林,等.复杂山地层析反演静校正新方法及应用[J].石油地球物理勘探,2017,52(3):418-425.ZENG Qingcai,ZENG Tongsheng,OUYANG Yonglin,et al.A new tomograhpic inversion for static corrections in complex mountain areas[J].Oil Geophysical Prospecting,2017,52(3):418-425.
[2]
谢春,刘玉柱,董良国,等.基于声波方程的有限频伴随状态法初至波旅行时层析[J].石油地球物理勘探,2015,50(2):274-282.XIE Chun,LIU Yuzhu,DONG Liangguo,et al.First arrival tomography with finite frequency adjoint-state method based on acoustic wave equation[J].Oil Geophysical Prospecting,2015,50(2):274-282.
[3]
王立歆,李海英,李弘,等.复杂地质条件下超深层碳酸盐岩断控缝洞体成像及预测技术[J].石油物探,2022,61(5):865-875.WANG Lixin,LI Haiying,LI Hong,et al.Imaging and prediction technology of fault-karst reservoirs in ultra-dep carbonate rocks under complex geological conditions[J].Geophysical Prospecting for Petroleum,2022,61(5):865-875.
[4]
林彬华,金星,康兰池,等.基于卷积神经网络的地震震级测定研究[J].地球物理学报,2021,64(10):3600-3611.LIN Binhua,JIN Xing,KANG Lanchi,et al.The research of earthquake magnitude determination based on Convolutional Neural Networks[J].Chinese Journal of Geophysics,2021,64(10):3600-3611.
[5]
陈金焕,曹永生,孙成龙,等.基于二分法的地震波初至自动拾取算法[J].地球物理学进展,2015,30(2):688-694.CHEN Jinhuan,CAO Yongsheng,SUN Chenglong,et al.The algorithm for automatic first-breaks picking on seismic traces based on Dichotomy[J].Progress in Geophysics,2015,30(2):688-694.
[6]
王议迎,丁仁伟,李建平,等.联合改进STA/LTA与MLoG算子的微震P波到时自动拾取方法[J/OL].山东科技大学学报(自然科学版),2021,40(6):1-10.WANG Yiying,DING Renwei,LI Jianping,et al.Automatic pickup of microseismic P-wave arrival based on improved STA/LTA and MLoG operators[J/OL].Journal of Shandong University of Science and Technology (Na-tural Science),2021,40(6):1-10.
[7]
江国明,张贵宾,徐峣.远震相对走时数据快速计算方法及应用[J].地球物理学报,2012,55(12):4097-4105.JIANG Guoming,ZHANG Guibin,XU Yao.A fast method for calculating relative residuals of teleseismic data and its application[J].Chinese Journal of Geophysics,2012,55(12):4097-4105.
[8]
刘腾蛟,高阳,储仿东,等.最小二乘曲线拟合的微地震初至优化拾取方法及应用[J].石油地球物理勘探,2018,53(S2):124-129.LIU Tengjiao,GAO Yang,CHU Fangdong,et al.Microseismic first arrival picking based on least square curve fitting[J].Oil Geophysical Prospecting,2018,53(S2):124-129.
[9]
李辉峰,邹强,金文昱.基于边缘检测的初至波自动拾取方法[J].石油地球物理勘探,2006(2):150-155.LI Huifeng,ZOU Qiang,JIN Wenyu.Method of automatic first breaks pick-up based on edge detection[J].Oil Geophysical Prospecting,2006(2):150-155.
[10]
牛沛琛,张建中.基于数字图像处理的地震波初至时间检测[J].计算机与现代化,2007(4):27-30.NIU Peichen,ZHANG Jianzhong.First Arrival Pic-king Based on Image Processing Methods[J].Compu-ter and Modernization,2007(4):27-30.
[11]
宋建国,李赋真,徐维秀,等.改进的神经网络级联相关算法及其在初至拾取中的应用[J].石油地球物理勘探,2018,53(1):8-16.SONG Jianguo,LI Fuzhen,XU Weixiu,et al.An improved neural-network cascade-correlation algorithm and its application in seismic first break picking[J].Oil Geophysical Prospecting,2018,53(1):8-16.
[12]
曹晓莉,刘斌,王淑荣,等.综合动量法和可变学习速度的BP神经网络地震初至拾取[J].石油地球物理勘探,2020,55(1):71-79.CAO Xiaoli,LIU Bin,WANG Shurong,et al.Seismic first-break picking based on BP neural network integrated with momentum method and adaptive learning rate method[J].Oil Geophysical Prospecting,2020,55(1):71-79.
[13]
COVA D,刘洋,丁成震,等.人工智能和视速度约束的地震波初至拾取方法[J].石油地球物理勘探,2021,56(3):419-435.COVA D,LIU Yang,DING Chengzhen,et al.First break picking method based on artificial intelligence and apparent velocity constraint[J].Oil Geophysical Prospecting,2021,56(3):419-435.
[14]
杨晶,丁仁伟,林年添,等.基于深度学习的地震断层智能识别研究进展[J].地球物理学进展,2022,37(1):298-311.YANG Jing,DING Renwei,LIN Niantian,et al.Research progress of intelligent identification of seismic faults based on deep learning[J].Progress in Geophysics,2022,37(1):298-311.
[15]
张岩,李新月,王斌,等.基于深度学习的鲁棒地震数据去噪[J].石油地球物理勘探,2022,57(1):12-25.ZHANG Yan,LI Xinyue,WANG Bin,et al.Robust seismic data denoising based on deep learning[J].Oil Geophysical Prospecting,2022,57(1):12-25.
[16]
李祺鑫,罗亚能,马晓强,等.基于深度嵌入网络的地震相聚类技术[J].石油地球物理勘探,2022,57(2):261-267.LI Qixin,LUO Yaneng,MA Xiaoqiang,et al.Seismic facies clustering technology based on deep embedding network[J].Oil Geophysical Prospecting,2022,57(2):261-267.
[17]
唐杰,韩盛元,刘英昌,等.基于去噪卷积神经网络的面波噪声压制方法[J].石油物探,2022,61(2):245-252.TANG Jie,HAN Shengyuan,LIU Yingchang,et al.Seismic surface wave atenuation based on denoising convolutional neural networks[J].Geophysical Prospecting for Petroleum,2022,2022,61(2):245-252.
[18]
LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015,3431-3440.
[19]
BADRINARAYANAN V, KENDALL A, CIPOLLA R.Segnet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE transactions on pattern analysis and machine intelligence,2017,39(12):2481-2495.
[20]
RONNEBERGER O,FISCHER P, BROX T.U-net:Convolutional networks for biomedical image segmentation[C].International Conference on Medical image computing and computer-assisted intervention.Springer,Cham,2015,234-241.
[21]
赵明,陈石,房立华,等.基于U形卷积神经网络的震相识别与到时拾取方法研究[J].地球物理学报,2019,62(8):3034-3042.ZHAO Ming,CHEN Shi,FANG Lihua,et al.Earthquake phase arrival auto-picking based on U-shaped convolutional neural network[J].Chinese Journal of Geophysics,2019,62(8):3034-3042.
[22]
张逸伦,喻志超,胡天跃,等.基于U-Net的井中多道联合微地震震相识别和初至拾取方法[J].地球物理学报,2021,64(6):2073-2085.ZHANG Yilun,YU Zhichao,HU Tianyue,et al.Multi-trace joint downhole microseismic phase detection and arrival picking method based on U-Net[J].Chinese Journal of Geophysics,2021,64(6):2073-2085.
[23]
刘佳楠,武杰.基于全卷积神经网络的地震初至波拾取[J].信息技术与网络安全,2018,37(11):58-63.LIU Jia'nan,WU Jie.Seismic first arrival picking based on fully convolutional networks[J].Information Technology and Network Security,2018,37(11):58-63.
[24]
陈德武,杨午阳,魏新建,等.基于混合网络U-SegNet的地震初至自动拾取[J].石油地球物理勘探,2020,55(6):1188-1201.CHEN Dewu,YANG Wuyang,WEI Xinjian,et al.Automatic picking of seismic first arrivals based on hybrid network U-SegNet[J].Oil Geophysical Prospecting,2020,55(6):1188-1201.
[25]
潘英杰,许银坡,倪宇东,等.一种基于地震图像深度语义分割的初至拾取方法[J].地球物理学进展,2022,37(3):1122-1131.PAN Yingjie,XU Yinpo,NI Yudong,et al. 2022.First break picking method based on deep learning semantic segmentation of seismic image[J]. Progress in Geophysics (in Chinese),37(3):1122-1131.
[26]
王维波,官强,高明,等.利用残差网络和地震发射层析成像的微地震事件检测[J].石油地球物理勘探,2022,57(2):251-260.WANG Weibo,GUAN Qiang,GAO Ming,et al.Detection of microseismic events based on residual network and seismic emision tomography[J].Oil Geophysical Prospecting,2022,57(2):251-260.
[27]
SZEGEDY C, LIU W, JIA Y,et al.Going deeper with convolutions[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015,1-9.
[28]
SIMONYAN K, ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv preprint arXiv:1409.1556,2014.
[29]
HE K,JIAN S.Convolutional neural networks at constrained time cost[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015,5353-5360.
[30]
HE K,ZHANG X, REN S,et al.Deep residual lear-ning for image recognition[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Re-cognition,2016,770-778.
[31]
SHI W, CABALLERO J,F HUSZ?R,et al.Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016,1874-1883.
[32]
OFFE S,SZEGEDY C.Batch normalization:Accelerating deep network training by reducing internal covariate shift[C].International conference on machine learning,PMLR,2015,448-456.