Determining the water saturations in thin-bedded turbidites using wire-line logs is difficult; errors in Sw calculation frequently result in uneconomical completions. Consequently, current Brushy Canyon completion decisions include expensive core information to provide an acceptable indicator of oil saturation in order to compensate for the Sw calculation problem. Completion decisions can be improved and less core data is needed using a new method that correlates wire-line logs with core measured bulk volume oil (FSo).

A neural network was trained and tested using density and neutron porosity plus shallow and deep resistivity logs as input variables. The neural network was trained to predict the FSo product from whole core analysis.

The trained and tested neural network was then used to estimate FSo in 25 additional Brushy Canyon wells that were not used in the training, but had the same four wire-line logs. A FSo cutoff of 22 units was determined and values greater than the cutoff were summed through the perforated interval in each well. The summed bulk volume oil of the 25 wells was plotted versus the first year's total production. The plot suggests that SFSo greater than 20,000 units will usually result in an economical new well or reentry completion.

During the course of optimizing the neural network architecture, valuable insights into network architecture design were gained. For this type of study, less complex architectures produced robust testing results, indicating that the solution, though non-linear, is still reasonably simple.

The method should be useful when evaluating behind-pipe completion opportunities in the Brushy Canyon interval of the Delaware Sands in the Permian Basin. Re-completion costs are lower than new well costs; thus thin zones with high values of FSo are potential targets.


The Delaware Mountain Group in the Delaware basin of New Mexico consists of a thick (4500 ft) sandstone and siltstone interval with 95% of the sandstone medium to fine-grained.1 Porosity and permeability in the productive interval range from 12–25% and 1–5md respectively.1 Typically the clay content is less than 5%.1 Stratigraphic divisions are uncertain,1 but the top of the Lower Brushy Canyon is regionally identified by a kick in the gamma ray and the accompanying resistivity logs. A standard suite of logs includes gamma ray, neutron and density porosity, plus shallow and deep resistivity. Generally the density log produces the best estimate of porosity, but calculating water saturation is problematic.1Others2,3 have reported similar problems in estimating water saturation in thin-bed, low resistivity formations.

Around 1990 improved sidewall coring technology resulted in the recovery of samples for laboratory analyses and the ability to accurately record sample depth. Reference 2 recognized the thin-bed, low resistivity problem and developed a procedure to calibrate the available logs with the new core information. The procedure follows:

"using the full-core analysis to calibrate log calculations, a procedure was developed to identify the zones that are oil-productive. The procedure is based on the premise that zones with residual oil saturation have a high probability of being productive and zones with no residual oil saturation have a low probability of being productive. By calibrating the Micro Lateral Log to calculate a residual oil saturation value for each one-half foot interval from the digitized log, potential pay zones were identified. By applying porosity correction transforms, setting gamma ray and porosity limits, and calibration of resistivity values, a more accurate determination of the productive intervals was made."

Reference 3 recommends accounting for the difference in scale between the point measurements of the core analysis and the lower resolution log measurements by including (adjust log parameters, "m" and "n") the location of each plug in the log interpretation. Both Refs. 2 and 3 are methods of calibrating well-known equations with core information.

This content is only available via PDF.
You can access this article if you purchase or spend a download.