Intelligent interpretation and modeling method of velocity semblance based on Bayesian decision theory
WU Guofu1, XIAO Mingtu2, WANG Huazhong1, LING Yue2, ZHAO Yuhe2
1. School of Ocean and Earth Science, Tongji University, Shanghai 200092, China; 2. Research Institute of Exploration and Development-Northwest, PetroChina, Lanzhou, Gansu 730020, China
Abstract:As a strong nonlinear problem,the high precision velocity modeling requires a relatively correct initial velocity model. The initial background velocity sacnning method based on the common middle-point (CMP) gathers is the most robust method. Facing the huge size of CMP gathers,it is necessary to research the intelligent initial background velocity analysis method,and its core is the reasonable velocity semblance interpretation. This can be viewed as a scan for the most reasonable time-velocity(TV) pairs with the smallest value of defined risk decision function in a high-dimensional velocity semblance data based on the prior knowledge of the interpreters and the horizon constraint in the sense of Baye-sian decision. Therefore,this paper proposes a decision framework guided by the logic in manual interaction picking. Firstly,the semblance data and “pseudo stack profile” are generated to further extract the structural information from the profile by calculating the coherence properties. Then,K-means clustering is performed on the semblance panel according to the structural information. For each classification,TV pairs that minimize the cost function constrained by priori information and statistical information from the data space are iteratively searched. Finally,the velocity field is formed by interpolation and smoothing,as the lateral discontinuities are reduced by quality control based on statistics constraints. This method implements the utilization of horizon information into the whole process from clustering to automatic pi-cking,and quantifies the priori knowledge of the interpreter and neighborhood picking results into restrained variables in automatic picking. This can reflect the intelligence of velocity semblance interpretation and shorten the velocity modeling cycle.
马彦彦,李国发,张星宇,等.叠前深度偏移速度建模方法分析[J].石油地球物理勘探,2014,49(4):687-693.MA Yanyan,LI Guofa,ZHANG Xingyu,et al.Strategy of velocity model building in prestack depth migration[J].Oil Geophysical Prospecting,2014,49(4):687-693.
[2]
王华忠,冯波,王雄文,等.地震波反演成像方法与技术核心问题分析[J].石油物探,2015,54(2):115-125,141.WANG Huazhong,FENG Bo,WANG Xiongwen,et al.Analysis of seismic inversion imaging and its technical core issues[J].Geophysical Prospecting for Petroleum,2015,54(2):115-125,141.
[3]
GAROTTA R,MICHON D.Continuous analysis of the velocity function and of the move out corrections[J].Geophysical Prospecting,1967,15(4):584-597.
[4]
TANER M T,KOEHLER F.Velocity spectra-digital computer derivation applications of velocity functions[J].Geophysics,1969,34(6):859-881.
[5]
TOLDI J L.Velocity analysis without picking[J].Geo-physics,1989,54(2):191-199.
[6]
LUMLEY D E.Monte Carlo Automatic Velocity Picks[R].Stanford Exploration Project,1997.
[7]
陈志德,刘桭宽,李成斌.三维叠前深度偏移速度分析及蒙特卡洛自动层速度拾取[J].地球物理学报,2002,45(2):246-254.CHEN Zhide,LIU Zhenkuan,LI Chengbin.3-D pre-stack depth migration velocity analysis and automatic Monte Carlo velocity picking in depth[J].Chinese Journal of Geophysics,2002,45(2):246-254.
[8]
AL-YAHYA K.Velocity analysis by iterative profile migration[J].Geophysics,1989,54(6):718-729
[9]
林年添,刘洪,李建勇.基于Viterbi算法的复杂地质体速度约束化自动拾取[J].地球物理学进展,2004,19(2):311-316.LIN Niantian,LIU Hong,LI Jianyong.Automatic picking velocity by the Viterbi algorithm for the complex geological case[J].Progress in Geophysics,2004,19(2):311-316.
[10]
DECKER L,FOMEL S.A variational method for picking velocity surfaces from semblance scans[C].SEG Technical Program Expanded Abstracts,2020,39:3684-3688.
[11]
SMITH K.Machine learning assisted velocity auto-picking[J].SEG Technical Program Expanded Abstracts,2017,36:5686-5690
[12]
CHEN Y Q.Automatic semblance picking by a bottom-up clustering method[C].SEG 2018 Workshop:SEG Maximizing Asset Value Through Artificial Intelligence and Machine Learning,2018,44-48.
[13]
WAHEED U B,AL-ZAHRANI S,HANAFY S M.Machine learning algorithms for automatic velocity picking:K-means vs DBSCAN[C].SEG Technical Program Expanded Abstracts,2019,38:5110-5114.
[14]
王迪,袁三一,袁焕,等.基于自适应阈值约束的无监督聚类智能速度拾取[J].地球物理学报,2021,64(3):1048-1060.WANG Di,YUAN Sanyi,YUAN Huan,et al.Intelligent velocity picking based on unsupervised clustering with the adaptive threshold constraint[J].Chinese Journal of Geophysics,2021,64(3):1048-1060.
[15]
HUANG J,CAO J,CHEN G,et al.Automate seismic velocity model building through machine learning[C].SEG Technical Program Expanded Abstracts,2020,39:1556-1560
[16]
MA Y,JI X,FEI T,et al.Automatic velocity picking with convolutional neural networks[J].SEG Technical Program Expanded Abstracts,2018,37:2066-2070.
[17]
WANG W,YANG F,MA J.Velocity model building with a modified fully convolutional network[C].SEG Technical Program Expanded Abstracts,2018,37:2086-2090.
[18]
DUQUE L,GUTIÉRREZ G,ARIAS C,et al.Automated velocity estimation by deep learning based seismic-to-velocity mapping[J].Extended Abstracts of 81st EAGE Conference & Exhibition,2019,1-5.
[19]
张兵.基于卷积神经网络和叠加速度谱的地震层速度自动建模方法[J].石油物探,2021,60(3):366-375.ZHANG Bing.Automatic seismic interval velocity building based on convolutional neural network and velocity spectrum[J].Geophysical Prospecting for Petroleum,2021,60(3):366-375.
[20]
韩明亮,邹志辉,马锐.利用反射地震资料和多尺度训练集的深度学习速度建模[J].石油地球物理勘探,2021,56(5):935-946.HAN Mingliang,ZOU Zhihui,MA Rui.Deep lear-ning-driven velocity modeling based on seismic reflection data and multi-scale training sets[J].Oil Geophysical Prospecting,2021,56(5):935-946.
[21]
宋磊,印兴耀,宗兆云,等.基于先验约束的深度学习地震波阻抗反演方法[J].石油地球物理勘探,2021,56(4):716-727.SONG Lei,YIN Xingyao,ZONG Zhaoyun,et al.Deep learning seismic impedance inversion based on prior constraints[J].Oil Geophysical Prospecting,2021,56(4):716-727.
[22]
张子良,李振春,张凯,等.地质模型约束的全波形速度建模反演及在复杂断块区的应用[J].石油地球物理勘探,2020,55(3):599-606.ZHANG Ziliang,LI Zhenchun,ZHANG Kai,et al.Research of geological model-constrained FWI and application in complex fault-block zones[J].Oil Geophysical Prospecting,2020,55(3):599-606.
[23]
苑书金.地震相干体技术的研究综述[J].勘探地球物理进展,2007,30(1):7-15.YUAN Shujin.A review of seismic coherence techniques[J].Progress in Exploration Geophysics,2007,30(1):7-15.
[24]
陈双全,季敏.地震数据结构张量相干计算方法[J].石油物探,2012,51(3):233-238.CHEN Shuangquan,JI Min.Structure tensor cohe-rence computation method of seismic data[J].Geophysical Prospecting for Petroleum,2012,51(3):233-238.
[25]
LANDA E,THORE P,SORIN V,et al.Interpretation of velocity estimates from coherency inversion[J].Geophysics,1991,56(9):1377-1383.
[26]
David COVA,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.