Seismic inversion is an important processing step for characterizing reservoirs with properties predicted away from well controls. A new approach to inversion and reservoir modeling is based on a nonlinear multitrace seismic inversion algorithm. Neural-network solutions for the inversion problem exist, whereby a multiattribute analysis increases output reliability. A more robust 3D working method is proposed that uses a simple nonlinear operator. The method is fast, user friendly, and cost effective. Initial input is formed by poststack seismic data and relevant well logs (e.g., acoustic impedance). The latter serve as a training and control point set to calculate optimized weights in the neural-network scheme. The nonlinear output operator trans-forms the seismic data into the desired log-response equivalent. Crucial is finding a real regional minimum for the difference between the computed synthetic and the recorded seismic traces at the target location. Intelligent data decimation eliminates the number of unknown coefficients in the operator computation. Moreover, it speeds up the true 3D minicube processing. Genetic inversion can be applied to properties other than acoustic impedance. However, these attributes should have a meaningful physical relationship to the seismic data, e.g., porosity, density, and saturation. Geologic modeling constitutes the last step of the inversion workflow. The geologic model is populated stochastically with relevant reservoir properties. The capabilities of the genetic inversion were tested on a semicontrolled seismic example and a real case study across the Shtokman gas field, Russia.

No abstract

Multivariate predictive analysis is a widely used tool in the petroleum industry in situations in which the deterministic nature of the relationship between a variable that requires prediction and a variable that is used for the purposes of such prediction is unknown or very complex. For example, to perform a sweet-spot analysis, it is necessary to predict potential oil and gas production rates on a map, using various geologic and geophysical attribute maps (porosity, density, seismic attributes, gravity, magnetic, etc.) and the initial oil and gas production rates of several control or training wells located in the area of interest. We have developed a new technology that allows for building a stable nonlinear predictive operator by using the combination of a neural network, a genetic algorithm, and a controlled gradient method. The main idea behind the proposed technology is to combine stochastic and deterministic approaches during the construction of the predictive operator at the training stage. The proposed technology avoids many disadvantages of the genetic algorithm and gradients methods, such as a high level of dependency on the initial values; the phenomenon of over-fitting (overtraining), which results in creation of an operator with unstable predictability; and a low speed of decreasing error during iteration, and, as a result, a low level of prediction quality. However, the above-mentioned combination uses the advantages of both methods and allows for finding a solution significantly closer to a global minimum for the objective function, compared to simple gradient methods, such as back propagation. The combination of these methods together with Tikhonov regularization allows for building stable predictions in spatial or/and time coordinates.

A target-oriented, predrill, pore-pressure prediction method using seismically estimated acoustic impedance is applied to recently acquired and processed dual-coil data in the Green Canyon and Walker Ridge areas of the Gulf of Mexico. Three deepwater subsalt wells are used in the study. One was used as a calibration well, and the other two were used as blind wells for comparing prediction results with the measured pore-pressure and mud-weight data. All three wells are in the Green Canyon area, penetrating thick salt bodies. A new seismic-inversion method is used for inversion of seismic impedance. The pore-pressure method uses a direct transform of the inverse of acoustic impedance, with two adjustable parameters. The optimization of the parameters is done through an iterative process to match the pore-pressure gradient obtained from the well acoustic impedance with those of pore-pressure measurements and mud weights within a tolerable range of those data for the calibration well. The optimized parameters are then used to transform the seismic acoustic-impedance volume to pore-pressure gradient volume. The predicted pore pressure at the blind wells from the well impedance and seismic impedance match reasonably with well data.

No abstract