混合概率模型驱动的叠前地震反演方法

Prestack seismic inversion driven by mixture probabilistic models

叠前地震反演是获取复杂油气储层弹性参数、岩性及含流体性质的主要途径。常规的叠前地震反演往往将"弹性参数"、"离散岩性"和"流体因子"三者独立预测,通常忽视了储层岩性差异对弹性参数的影响,由此引入的先验信息误差会严重影响弹性参数、离散岩性及流体指示因子预测的精度。为此,考虑待反演模型参数的先验概率服从混合型概率密度分布,基于贝叶斯框架推导了由时域、频域地震、低频整合先验信息及已知模型数据点四类数据集协同约束的后验混合概率分布的显式解,将非线性边界约束算法引入叠前地震弹性参数反演中,缓解了模型反演出现不稳定解的问题;利用序贯模拟算法对后验概率密度函数随机采样,且对不同后验概率分量的模拟结果进行分类,发展了对地层连续"弹性参数"、"离散岩性"及储层"流体因子"的叠前地震同步预测方法。理论测试和实际应用验证了该方法在岩性预测和储层孔隙流体识别中的有效性和实用性。

Prestack seismic inversion is the most important method for quantitatively evaluate the elastic,lithologic and fluid properties of subsurface media.Conventional seismic inversion often seperately predicts the’elastic modulus’,’discrete lithology’and’fluid factor’while ignoring the influence of lithology on model parameters,so that the errors of prior knowledge introduced will seriously affect the accuracy of seismic inversion and lithology prediction.Considering that the prior probability density function(PDF)of model parameters follows the distributon of mixture probabilistic density,this paper derives the explicit solution to the posterior PDF under the constraints of four conditional datasets including time-domain seismic data,frequencydomain seismic data,composite low-frequency prior informaton and known model points on the Bayesian framework.After introducing non-linear boundary constraints into prestack elastic inverson,the solution to model inversion becomes stable.The posterior PDF is randomly sampled by the sequential simulation algorithm,and the simulation results of different posterior probability components are classified,consequently a prestack simultaneous prediction method is established for continuous’elastic parameters’,’discrete lithology’and’fluid factor’.Model and real data have proved the method effectivee and practical.