Abstract:The seismic data reconstruction technology is mainly employed to address the problems such as missing seismic traces or insufficient spatial sampling. As a seismic data reconstruction method,support vector regression does not make full use of the physical information of seismic data. Thus,this paper introduces Gabor transform which can extract texture features with different scales and directions. The purpose is to fully mine the physical information of seismic data and reconstruct missing seismic data based on the algorithm framework of support vector regression. Firstly, the texture features are extracted by the Gabor filters,and a new feature vector database can be built by combining with the original data features. Then,a regression model is learned by the support vector regression algorithm to reconstruct the missing seismic data. A large number of reconstruction examples from synthetic and actual seismic data show that texture features extracted by Gabor transform can effectively improve the reconstruction accuracy of support vector regression algorithms and realize higher signal-to-noise ratios.
FOMEL S.Seismic reflection data interpolation with differential offset and shot continuation[J].Geophy-sics,2003,68(2):733-744.
[2]
VAN GROENESTIJN G J A,VERSCHUUR D J.Estimation of primaries and near-offset reconstruction by sparse inversion:Marine data applications[J].Geophysics, 2009,74(6):R119-R128.
[3]
KAPLAN S T,NAGHIZADEH M,SACCHI M D.Two dimensional shot-profile migration data reconstruction[C].SEG Technical Program Expanded Abstracts,2010,29:3645-3649.
[4]
李欣,杨婷,孙文博,等.一种基于光滑 L1 范数的地震数据插值方法[J].石油地球物理勘探,2018,53(2):251-256.LI Xin,YANG Ting,SUN Wenbo,et al.A gradient projection method for smooth L1 norm regularization based seismic data sparse interpolation[J].Oil Geophysical Prospecting,2018,53(2):251-256.
[5]
HUANG W,WU R S,WANG R.Damped dreamlet representation for exploration seismic data interpolation and denoising[J].IEEE Transactions on Geo-science and Remote Sensing,2018,56(6):3159-3172.
[6]
MOUSAVI S M,LANGSTON C A.Automatic noise-removal/signal-removal based on general cross-validation thresholding in synchrosqueezed domain and its application on earthquake data[J].Geophysics,2017,82(4):V211-V227.
[7]
PORSANI M J.Seismic trace interpolation in the f-x domain using half-step prediction filters[C].SEG Technical Program Expanded Abstracts,1997,16: 1985-1988.
[8]
NAGHIZADEH M,SACCHI M D.Multistep auto-regressive reconstruction of seismic records[J].Geophysics,2007,72(6):V111-V118.
[9]
GAO J,SACCHI M D,CHEN X.A fast reduced-rank interpolation method for prestack seismic volumes that depend on four spatial dimensions[J].Geophy-sics,2013, 78(1):V21-V30.
[10]
MA J.Three-dimensional irregular seismic data reconstruction via low-rank matrix completion[J].Geophysics,2013,78(5):V181-V192.
[11]
JIA Y,YU S,LIU L,et al.A fast rank-reduction algorithm for three-dimensional seismic data interpolation[J].Journal of Applied Geophysics,2016,132:137-145.
[12]
陈杰,牛聪,李勇,等.基于数据驱动紧框架理论的三维地震数据去噪与重建[J].石油地球物理勘探,2020,55(4):725-732.CHEN Jie,NIU Cong,LI Yong,et al.Denoising and reconstruction of 3D seismic data on a data-driven tight frame[J].Oil Geophysical Prospecting,2020,55(4):725-732.
[13]
CHEN Y,MA J,FOMEL S.Double-sparsity dictionary for seismic noise attenuation[J].Geophysics,2016,81(2):V103-V116.
[14]
JIA Y,YU S,MA J.Intelligent interpolation by Monte Carlo machine learning[J].Geophysics,2018,83(2):V83-V97.
[15]
张岩,李杰,王斌,等.基于联合小波域深度学习的地震数据规则化方法[J].石油地球物理勘探,2022,57(4):777-788.ZHANG Yan,LI Jie,WANG Bin,et al.Seismic data regularization based on deep learning combining wavelet domain[J].Oil Geophysical Prospecting,2022,57(4):777-788.
[16]
孟宏宇,杨华臣,张建中.无监督残差网络的地震数据重构方法[J].石油地球物理勘探,2022,57(4):789-799.MENG Hongyu,YANG Huachen,ZHANG Jianzhong.Seismic data reconstruction method based on unsupervised residual network[J].Oil Geophysical Prospecting,2022,57(4):789-799.
[17]
CHAI X,TANG G,WANG S,et al.Deep learning for irregularly and regularly missing data reconstruction[J].Scientific Reports,2020,10(1):3302.
[18]
MARGRAVE G F,LAMOUREUX M P,HENLEY D C.Gabor deconvolution:Estimating reflectivity by nonstationary deconvolution of seismic data[J].Geophysics,2011,76(3):W15-W30.
[19]
SACCHI M D,KAPLAN S,NAGHIZADEH M.FX Gabor seismic data reconstruction[C].Extended Abstracts of 71st EAGE Conference & Exhibition,2009,cp-127-00434.
[20]
KUMAR R,SUMATHI P,KUMAR A.De-noising of seismic signal based on Gabor transform[C].2013 International Conference on Advances in Computing,Communications and Informatics (ICACCI),IEEE,2013,1997-2001.
[21]
GAO J,WANG L,ZHAO W,et al.Enhancing resolution of nonstationary seismic data by molecular-Gabor transform[J].Geophysics,2013,78(1):V31-V41.
[22]
LIU J,WU Y,HAN D,et al.Time-frequency decomposition based on Ricker wavelet[C].SEG Technical Program Expanded Abstracts,2004,23:1937-1940.
[23]
JIA Y,GAO M,GU J.Self-learning regression interpolation based on Ricker kernel function for seismic data[J].Exploration Geophysics,2022,53(3):289-299.
[24]
JIA Y,MA J.What can machine learning do for seismic data processing? An interpolation application[J].Geophysics,2017,82(3):V163-V177.