地震保幅高低频拓展与多尺度贝叶斯融合反演

Research on high-and low-frequency expansion of seismic amplitude preserving and multi-scale Bayesian fusion inversion

针对L气田复杂水道内薄层和巨厚储层难以有效识别和描述的问题,提出利用有、无衰减两类正演信号和实际地震数据的分频剖面,分析地质体的多尺度地震响应特征,发掘叠后地震弱有效信号潜力。首先采用相对保幅拓频处理分别得到高频和低频地震数据体,然后对高、低频地震数据体逐级进行贝叶斯迭代反演,获得能够有效识别大、中、小尺度地质体的反演波阻抗数据体。研究结果表明:(1)地震数据本身隐含低频和高频有效信号,低频反映地质体整体包络(即大尺度特征),中频反映地质体内部的基本形态(即中尺度特征),高频反映地质体构造细节(即小尺度特征);(2)降频道积分能在相对保幅的范围内,有效增加巨厚储层的可识别性;(3)基于降频和提频的地震数据体约束的多尺度贝叶斯反演,能在有效频带范围内获得体现各个尺度地质体的相对可靠的纵波阻抗反演结果。实际资料应用证明了该方法的有效性。

Both thin and very thick reservoirs in the complex water channels are difficult to distinguish and describe efficiently in Gasfield L.To solve this problem,the frequency-division sections of forward signals with and without attenuation and actual seismic data are used to analyze the multi-scale seismic response features of geological bodies,explore the potential of post-stack seismic signals with weak effectiveness.First,the frequency expansion of relative amplitude preserving was utilized to obtain high-and low-frequency seismic data volumes.Then,the Bayesian iterative inversion was conducted on those data step by step to gain the impedance inversion data that could effectively identify large-,medium-,and small-scale geological bodies.The results are as follows:Low-frequency and high-frequency effective signals are inherently hidden in seismic data,and the low-,medium-,and high-frequency signals can reflect the overall envelope(large scale),the internal structure(medium scale),and the structure details(small scale)of geological bodies respectively.Moreover,frequency-reduction trace integration can effectively increase the identification degree of very thick reservoirs within the scope of relative amplitude preserving.Given the seismic data volume constraint of frequency reduction and increase,the multi-scale Bayesian inversion could deliever reliable P-wave impedance inversion results representing multi-scale geological bodies within effective frequency bands.The practical application has proved the validity of this method.