A dynamic all parameters adaptive BP neural networks model and its application on oil reservoir prediction

Petrophysical data prediction from seismic attributes using committee fuzzy inference system

Estimation of Reservoir Porosity and Water Saturation Based on Seismic Attributes Using Support Vector Regression Approach

Today, the major challenge in reservoir characterization is integrating data coming from different sources in varying scales, in order to obtain an accurate and high-resolution reservoir model. The role of seismic data in this integration is often limited to providing a structural model for the reservoir. Its relatively low resolution usually limits its further use. However, its areal coverage and availability suggest that it has the potential of providing valuable data for more detailed reservoir characterization studies through the process of seismic inversion. In this paper, a novel intelligent seismic inversion methodology is presented to achieve a desirable correlation between relatively low-frequency seismic signals, and the much higher frequency wireline-log data. Vertical seismic profile (VSP) is used as an intermediate step between the well logs and the surface seismic. A synthetic seismic model is developed by using real data and seismic interpretation. In the example presented here, the model represents the Atoka and Morrow formations, and the overlying Pennsylvanian sequence of the Buffalo Valley Field in New Mexico. Generalized regression neural network (GRNN) is used to build two independent correlation models between; 1) Surface seismic and VSP, 2) VSP and well logs. After generating virtual VSP’s from the surface seismic, well logs are predicted by using the correlation between VSP and well logs. The values of the density log, which is a surrogate for reservoir porosity, are predicted for each seismic trace through the seismic line with a classification approach having a correlation coefficient of 0.81. The same methodology is then applied to real data taken from the Buffalo Valley Field, to predict interwell gamma ray and neutron porosity logs through the seismic line of interest. The same procedure can be applied to a complete 3D seismic block to obtain 3D distributions of reservoir properties with less uncertainty than the geostatistical estimation methods. The intelligent seismic inversion method should help to increase the success of

/pdf/reservoir-characterization-using-intelligent-seismic-kck2e5xlff.pdf

Reservoir Characterization Using Intelligent Seismic Inversion

To remove some of the ambiguities in a heterogeneous oil reservoir, a three dimensional model of the reservoir would be constructed by application of newly introduced methods. The aim of this study is to define an accurate and efficient model of a complex reservoir in southwest of Iran and accurately derive the geological and geometrical properties of the reservoir for well location proposal. Seismic data in addition to well logs were used for that purpose. A corner point grid was used in this study, and a generic global scale-up method was combined with previous result for reservoir simulation. The final model pointed out the heterogeneous characterization of the reservoir and proved the advantage of combining these methods in constructing accurate and efficient reservoir models. According to these models, it is concluded that the reservoir has different productive zones in different members that was not cleared in the previous models.

3D static reservoir modeling by geostatistical techniques used for reservoir characterization and data integration

Well data gives precise information on reservoir properties at specific field locations with high vertical resolution. 3D seismic surveys cover large areas of the field but reservoir properties are not directly observable due to poor vertical resolution. For this paper, a new methodology has been developed and tested for relating reservoir properties at the well-bore to sets of seismic attributes, in order to predict reservoir properties in two zones of the Nash Draw field in SE New Mexico. Over 350 seismic attributes can be used in regression analyses of reservoir properties. Since using all attributes is computationally unfeasible and labor intensive, fuzzy logic is used to select the most statistically significant attributes for developing regression equations for individual reservoir properties. Non-linear regressions were used, as individual attributes lead low correlation coefficients when cross-plotted with reservoir properties, and neural network architectures were developed to relate the selected attributes to each property. In each case the output data used for training was a reservoir property, porosity (Φ), water saturation( Sw), or net pay, from 19 wells in the field. Each property was estimated using a neural network trained to CC=0.8 or higher using the highest ranking seismic attributes as inputs. The validity of the solutions were tested by removing three wells from the training data, re-computing the weights, and predicting the three absent points. These tests were applied three times for each reservoir property, with different points removed. Each network accurately predicted these nine test points and the solutions are considered robust. Φ, Sw, and net pay maps were generated using the regression relationships and the seismic attributes at each seismic bin location. Pore volume (Φh) and hydrocarbon pore volume (hΦSo) maps were derived from those reservoir property maps. These new techniques maximize both the well control and seismic data and generated useful maps for targeted drilling programs in the field.

Using Artificial Intelligence to Corellate Multiple Seismic Attributes to Reservoir Properties

Time-to-Depth Conversion of Nash Draw "L" Seismic Horizon using Seismic Attributes and Neural Networks

Well logs and cores are used to define formation thickness, porosity, and water saturation. These data are required to design well completions and to prepare workover and reservoir management plans. The presence of shale (clay) in the pay zone complicates log interpretation. This paper presents a methodology utilizing a neural network to reconcile the differences between density log effective porosity and plug core total porosity values in a shaly, laminated Cretaceous sandstone. Core plug measurements are typically taken in the better pay intervals and generally do not include the shale laminations evident in core photographs. Log measurements do include the heterogeneity that is evident in core photographs, but the log measurements represent an average of a 6-to-36-in. section that does not reflect the small scale variability. A multivariable correlating technique was used to associate gamma ray, density, and shallow and deep resistivity logs with core plug porosity measurements. Core water saturation values were used to tune a shaly sand water saturation model. The S W model was used to choose between plug core porosity, density log porosity, or neural network porosity as the preferred measurement to use with induction log resistivity to estimate water saturation. The porosity and water saturation values were then used to construct bulk volume oil and bulk volume water logs that were combined to identify productive zones. A case history format is used to explain the approach developed to correlate the four dependent variables measured by the logs with the core porosity and water saturation measurements. The subject field is an 80-well Gallup pool located on the southwest flank of the San Juan Basin of northwest New Mexico. The high clay content of the Muddy Formation in the Powder River Basin is known for contributing to errors in water saturation estimates. If modern logs capable of resolving thin beds are not available, this methodology can be applied to the Muddy, the Gallup and other Cretaceous reservoirs in the Rockies that contain thin shale laminations.

S. Wo

Papers

Using Artificial Intelligence to Corellate Multiple Seismic Attributes to Reservoir Properties

Time-to-Depth Conversion of Nash Draw "L" Seismic Horizon using Seismic Attributes and Neural Networks

Integrating Core Porosity and Sw Measurements with Log Values

Predicting Core Porosity using Wire-Line Logs at Dagger Draw Field, SE New Mexico