本文针对深度域地震资料反演问题提出了神经网络数据驱动岩性参数反演方法。
In view of the issue of seismic data inversion in depth domain, the paper presented the method for inversion of lithologic parameters driven by neural network.
通过对广义线性算法的基础理论研究,分析这种算法在深度域岩性参数反演过程中的稳定性和可靠性。
The reliability and the stability of lithology parameter inversion method in depth domain is analysed by the studies of basic theory in generalized linear.
即从测井数据出发,在地震资料的控制下,通过逐次迭代,精确地反演岩性及厚层参数,有效地解决了反演的多解性问题。
Guided by seismic data, we use logging data to invert lithological parameters and bed thickness exactly by successive iteration, hence solving the problem of multi solution in inversion.
所以利用曲线拟合方法很容易实现全部地震岩性参数的反演,并可提取零偏移距剖面。
Consequently, with the use of curve fitting method, the inversion of all seismic lithologic parameters can be easy achieved, and zero-offset section can be obtained.
从而双参数反演方法可为地震勘探提供更多的岩性参数。
The inversion method can offer rich lithology parameters for seismic exploration.
该方法利用动校正后的CMP及CCP全部角道集,建立多波多参数联合反演方程,进而求解出目的层段的岩性参数。
The method utilizes all the CMP and CCP angle gathers after NMO to build multi-wave & multi-parameter joint inversion equation and calculate the lithologic parameters of interval.
该方法利用动校正后的CMP及CCP全部角道集,建立多波多参数联合反演方程,进而求解出目的层段的岩性参数。
The method utilizes all the CMP and CCP angle gathers after NMO to build multi-wave & multi-parameter joint inversion equation and calculate the lithologic parameters of interval.
应用推荐