Seismic prediction of fluid and lithofacies distribution is of great interest to reservoir characterization, geologic model building, and flow unit delineation. Inferring fluids and lithofacies from seismic data under the framework of machine learning is commonly subject to issues of limited features, imbalanced data sets, and spatial constraints. As a consequence, an extreme gradient boosting-based workflow, which takes feature engineering, data balancing, and spatial constraints into account, is proposed to predict the fluid and lithofacies distribution by integrating well-log and seismic data. The constructed feature set based on simple mathematical operations and domain knowledge outperforms the benchmark group consisting of conventional elastic attributes of P-impedance and VP/VS ratio. A radial basis function characterizing the weights of training samples according to the distances from the available wells to the target region is developed to impose spatial constraints on the model training process, significantly improving the prediction accuracy and reliability of gas sandstone. The strategy combining the synthetic minority oversampling technique and spatial constraints further increases the F1 score of gas sandstone and also benefits the overall prediction performance of all of the facies. The application of the combined strategy on prestack seismic inversion results generates a more geologically reasonable spatial distribution of fluids, thus verifying the robustness and effectiveness of our workflow.
We consider the problem of fluid identification and fracture detection in unconventional reservoir (tight gas sand and shale gas) characterization. We begin with a simplification of the stiffness parameters and the derivation of a linearized reflection coefficient and azimuthal elastic impedance (EI). The accuracy of the simplification is confirmed in application to gas-bearing fractured rocks with low porosity and small fracture density. We have developed a modified fluid factor that is more sensitive to fluid type and less influenced by porosity. A two-step inversion workflow is evaluated based on the derived linearized reflection coefficient and azimuthal EI, including (1) a damped least-squares inversion for azimuthal EI, constrained by an initial model, and (2) a Bayesian Markov chain Monte Carlo inversion for the modified fluid factor and dry fracture weaknesses. Stability and accuracy are examined with synthetic data, from which we conclude that the modified fluid factor and dry fracture weaknesses can be stably determined in the presence of moderate data error/noise. The stability of our approach is further confirmed on a fractured tight gas sand field data set, within which we observe that geologically reasonable parameters (Lamé constants, the modified fluid factor, and dry fracture weaknesses) are determined. We conclude that our inversion workflow and its underlying assumptions form realistic predictions/discriminations of reservoir fracture and fluid parameters.
Tilted transverse isotropy (TTI) provides a useful model for the elastic response of a medium containing aligned fractures with a symmetry axis oriented obliquely in the vertical and horizontal coordinate directions. Robust methods for determining the TTI properties of a medium from seismic observations to characterize fractures are sought. Azimuthal differencing of seismic amplitude data produces quantities that are particularly sensitive to TTI properties. Based on the linear slip fracture model, we express the TTI stiffness matrix in terms of the normal and tangential fracture weaknesses. Perturbing stiffness parameters to simulate an interface separating an isotropic medium and a TTI medium, we derive a linearized P-to-P reflection coefficient expression in which the influence of tilt angle and fracture weaknesses separately emerge. We formulate a Bayesian inversion approach in which amplitude differences between seismic data along two azimuths, interpreted in terms of the reflection coefficient approximation, are used to determine fracture weaknesses and tilt angle. Tests with simulated data confirm that the unknown parameter vector involving fracture weakness and tilted fracture weaknesses is stably estimated from seismic data containing a moderate degree of additive Gaussian noise. The inversion approach is applied to a field surface seismic data acquired over a fractured reservoir; from it, interpretable tilted fracture weaknesses, consistent with expected reservoir geology, are obtained. We determine that our inversion approach and the established inversion workflow can produce the properties of systems of tilted fractures stably using azimuthal seismic amplitude differences, which may add important information for characterization of fractured reservoirs.
A system of aligned vertical fractures and fine horizontal shale layers combine to form equivalent orthorhombic media. Weak anisotropy parameters and fracture weaknesses play an important role in the description of orthorhombic anisotropy (OA). We propose a novel approach of utilizing seismic reflection amplitudes to estimate weak anisotropy parameters and fracture weaknesses from observed seismic data, based on azimuthal elastic impedance (EI). We first propose perturbation in stiffness matrix in terms of weak anisotropy parameters and fracture weaknesses, and using the perturbation and scattering function, we derive PP-wave reflection coefficient and azimuthal EI for the case of an interface separating two OA media. Then we demonstrate an approach to first use a model constrained damped least-squares algorithm to estimate azimuthal EI from partially incidence-phase-angle-stack seismic reflection data at different azimuths, and then extract weak anisotropy parameters and fracture weaknesses from the estimated azimuthal EI using a Bayesian Markov Chain Monte Carlo inversion method. In addition, a new procedure to construct rock physics effective model is presented to estimate weak anisotropy parameters and fracture weaknesses from well log interpretation results (minerals and their volumes, porosity, saturation, fracture density, etc.). Tests on synthetic and real data indicate that unknown parameters including elastic properties (P- and S-wave impedances and density), weak anisotropy parameters and fracture weaknesses can be estimated stably in the case of seismic data containing a moderate noise, and our approach can make a reasonable estimation of anisotropy in a fractured shale reservoir.