基于约束最小二乘与信赖域的储层参数反演方法

The petrophysical parameter inversion method based on constrained least squares and trust region approach

基于包体岩石物理模型的储层参数地震反演方法面临数学形式复杂、多解性强、适应性差、涉及迭代运算等问题,本文提出一种基于约束最小二乘与信赖域的储层参数地震反演方法.该方法基于储层参数与弹性参数关联岩石物理模型,使用最小二乘方法构建目标函数和信赖域约束全局寻优求解,有效降低了地震反演多解性,极大提高了收敛速度.特别是通过在最小二乘求解中引入垂向约束,有效提高反演结果的抗噪声能力.经过模型测试和实际资料的应用,验证了方法的可行性和适用性.

In the context of petrophysical parameter inversion, several aspects are concerned as challenges for the application of inclusion rock physics model, including complex mathematical form, potential multiplicity of solutions, poor adaptability and involved iteration calculation. Herein, we demonstrate an efficient petrophysical parameter inversion method based on constrained least- squares and trust region approach. On account of the correlation between elastic parameters and petrophysical parameters, the established rock physics model is significantly beneficial to the confinement of multiplicity of solutions and the promotion of convergence speed, ascribed to the optimal solution obtained from least squares objective function and trust region approach. In particular, inversion results present strong improvement of noise-resistance by adding vertical constraints in least-squares method. Furthermore, the model test and real data are used to verify the excellent feasibility and applicability of the proposed method. Therefore, the proposed petrophysical parameter inversion method paves the way towards the further boost of the application of inclusion rock physics model in the field of petrophysical parameter inversion.