Full-waveform inversion (FWI) of 3D wide-azimuth data for elastic orthorhombic media suffers from parameter trade-offs which cannot be overcome without constraining the model-updating procedure. We present an FWI methodology that incorporates geologic constraints to reduce the inversion nonlinearity and increase the resolution of parameter estimation for orthorhombic models. These constraints are obtained from well logs, which can provide rock-physics relationships for different geologic facies. Because the locations of the available well logs are usually sparse, a supervised machine-learning (ML) algorithm (Support Vector Machine) is employed to account for lateral heterogeneity in building the lithologic constraints. The advantages of the facies-based FWI are demonstrated on the modified SEG-EAGE 3D overthrust model, which is made orthorhombic with the symmetry planes that coincide with the Cartesian coordinate planes. We employ a velocity-based parameterization, whose suitability for FWI was studied using the radiation-pattern analysis. Application of the facies-based constraints substantially increases the resolution of the P- and S-wave vertical velocities ($V_{\mathrm{P}0}$, $V_{\mathrm{S}0}$, and $V_{\mathrm{S}1}$) and, therefore, of the depth scale of the model. Improvements are also observed for the P-wave horizontal and normal-moveout velocities ($V_{\mathrm{P}1}$, $V_{\mathrm{P}2}$, $V_{\mathrm{nmo},1}$, and $V_{\mathrm{nmo},2}$) and the S-wave horizontal velocity $V_{\mathrm{S}2}$. However, the velocity $V_{\mathrm{nmo},3}$ that depends on Tsvankin’s parameter ${\delta }^{(3)}$ defined in the horizontal plane is not well recovered from the surface data. On the whole, the developed algorithm achieves a much higher spatial resolution compared to unconstrained FWI, even in the absence of recorded frequencies below 2 Hz.

中文翻译：

---

通过机器学习应用岩性约束的正交介质的弹性 FWI

弹性正交介质的 3D 宽方位角数据的全波形反演 (FWI) 受到参数权衡的影响，如果不限制模型更新程序就无法克服参数权衡。我们提出了一种结合地质约束的 FWI 方法，以减少反演非线性并提高正交模型参数估计的分辨率。这些约束是从测井中获得的，可以为不同的地质相提供岩石物理关系。由于可用测井的位置通常很少，因此采用监督机器学习 (ML) 算法（支持向量机）来解释构建岩性约束时的横向非均质性。基于相的 FWI 的优势在改进的 SEG-EAGE 3D 逆冲模型上得到证明，它与与笛卡尔坐标平面重合的对称平面正交。我们采用基于速度的参数化，使用辐射模式分析研究了其对 FWI 的适用性。基于相的约束的应用大大提高了 P 波和 S 波垂直速度的分辨率（${伏}_{\mathrm{磷}0}$, ${伏}_{\mathrm{秒}0}$， 和 ${伏}_{\mathrm{秒}1}$)，因此，模型的深度尺度。还观察到 P 波水平和正常时差速度的改进（${伏}_{\mathrm{磷}1}$, ${伏}_{\mathrm{磷}2}$, ${伏}_{\mathrm{纳米},1}$， 和 ${伏}_{\mathrm{纳米},2}$) 和 S 波水平速度 ${伏}_{\mathrm{秒}2}$. 然而，速度${伏}_{\mathrm{纳米},3}$ 这取决于 Tsvankin 的参数 ${\delta }^{(3)}$平面数据中定义的水平面不能很好地恢复。总的来说，与无约束 FWI 相比，开发的算法实现了更高的空间分辨率，即使在没有低于 2 Hz 的记录频率的情况下也是如此。