Estimating permeability values from well logs using a depth blended model

11966,828

16/787245

February 11, 2020

Permeability values are estimated based on well logs using regression algorithms, such as gradient boosting and random forest. The training data is selected from well logs for which core-analysis-based permeability values are available. The estimated permeability values are used to plan hydrocarbon production. The well logs used to build the depth blended model may include total porosity, gamma ray, volume of calcite, density, resistivity, and neutron logs. Selecting the training data may include grouping the well logs according to regions expected to have similar characteristics, choosing a subset of the well logs corresponding to wells expected to provide stable models according to pre-determined criteria, and/or identifying training zones on the chosen well logs according to one or more rules. Validation and consistency checks may also be performed.

CGG SERVICES SAS (Massy, FR); KUWAIT GULF OIL COMPANY (Ahmadi, SA)

CGG SERVICES SAS (Massy, FR), KUWAIT GULF OIL COMPANY (Ahmadi, KW)

1. A method for estimating permeability values based on well logs, the method comprising: selecting training data and test data from well logs for which core-analysis-based permeability values are available; training two regression algorithms using the training data to generate a depth blended model for estimating permeability values, the core-analysis-based permeability values being used for calibrating the depth blended model which outputs first values obtained via a first regression algorithm among the two regression algorithms when the first values are positive, and outputs second permeability values obtained via a second regression algorithm among the two regression algorithms otherwise; selectively adjusting algorithm parameters of the two regression algorithms depending on an overall consistency check of the first values and the second values obtained for the test data; and applying the depth blended model to the well logs for which respective core-analysis-based permeability values are not available to estimate model-based permeability values, wherein the model-based permeability values are used to plan hydrocarbon production.

2. The method of claim 1 , wherein the well logs used to build the depth blended model include total porosity, gamma ray, resistivity, volume of calcite, density, and neutron logs.

3. The method of claim 1 , wherein the selecting includes grouping the well logs according to regions expected to have similar characteristics.

4. The method of claim 1 , wherein the selecting includes choosing a subset of the well logs corresponding to wells expected to provide stable models according to pre-determined criteria.

5. The method of claim 4 , wherein the selecting further includes identifying training zones on the chosen well logs according to one or more rules.

6. The method of claim 1 , wherein the selecting includes pre-processing the training data by scaling and/or interpolating.

7. The method of claim 1 , wherein the primary regression algorithm is a gradient boosting, and the secondary regression algorithm is a random forest algorithm.

8. The method of claim 1 , wherein the overall consistency check includes at least one of: comparing permeability values obtained using the depth blended model with the core-analysis-based permeability values, or comparing the first values with the second values.

9. The method of claim 1 , further comprising: performing well-by-well quality checks for the model-estimated permeability values.

10. A permeability estimating apparatus, comprising: a processor configured to select training data and test data from well logs for which core-analysis-based permeability values are available, to train two regression algorithms to generate a depth blended model for estimating permeability values, based on well logs included the training data with their corresponding core-analysis-based permeability values being used for calibrating the depth blended model, the depth blended model outputting first values obtained by applying a first regression algorithm among the two regression algorithms when the first values are positive, and outputting second permeability values obtained by applying a second regression algorithm among the two regression algorithms otherwise, selectively adjusting algorithm parameters of the two regression algorithms depending on an overall consistency check of the first values and the second values obtained for the test data; and to apply the depth blended model to the well logs for which respective core-analysis-based permeability values are not available for obtaining model-estimated permeability values; and a communication interface connected to the processor and configured to exchange data with other devices and/or enable interaction with a user, wherein the model-estimated permeability values are used to plan hydrocarbon production, and the depth blended model selectively outputs values obtained via at least two of the regression algorithms.

11. The permeability estimating apparatus of claim 10 , wherein the well logs used to build the depth blended model include total porosity, gamma ray, volume of calcite, density, and neutron logs.

12. The permeability estimating apparatus of claim 10 , wherein when selecting the training data, the processor groups the well logs according to regions expected to have similar characteristics.

13. The permeability estimating apparatus of claim 10 , wherein, when selecting the training data, the processor chooses a subset of the well logs corresponding to wells expected to provide stable models according to pre-determined criteria.

14. The permeability estimating apparatus of claim 13 , wherein, when selecting the training data, the processor identifies training zones on the chosen well logs according to one or more rules.

15. The permeability estimating apparatus of claim 10 , wherein the processor is further configured to perform pre-processing of the training data by scaling and/or interpolating.

16. The permeability estimating apparatus of claim 10 , wherein the primary regression algorithm is a gradient boosting, and the second regression algorithm is a random forest algorithm.

17. The permeability estimating apparatus of claim 10 , wherein the processor is further configured to perform the overall consistency check including at least one comparing permeability values obtained using the depth blended model with the core-analysis-based permeability values, or comparing first values with second values.

18. The permeability estimating apparatus of claim 10 , wherein the processor is further configured to perform well-by-well consistency checks for the model-estimated permeability values.

19. The method of claim 1 , wherein the core-analysis-based permeability values are obtained by analyzing well rock samples outside the well, the well rock samples being sampled at substantially larger intervals than intervals between measurements of the well logs.

20. The permeability estimating apparatus of claim 10 , wherein the core-analysis-based permeability values are obtained by analyzing well rock samples outside the well, the well rock samples being sampled at substantially larger intervals than intervals between measurements of the well logs.

5251286 October 1993 Wiener et al.
6714871 March 2004 Xu et al.
8510242 August 2013 Al-Fattah
9229127 January 2016 Leseur
9501716 November 2016 Fleishman et al.
20130282286 October 2013 Thorne
20170017896 January 2017 Hamann
20170364795 December 2017 Anderson et al.
20190257977 August 2019 Skalinski
20190331813 October 2019 Zhang
WO-2018125760 July 2018

Petro Wiki, “Types of logs”, captured Dec. 2, 2013 (Year: 2013). cited by examiner
Ahmed Elsherif et al., “Facies Analysis and Permeability Estimation in Late Cretaceous Giant Carbonate Reservoir using LWD Technology: A Case Study in Sabriyah Field, North Kuwait,” AAPG Search and Discovery Article #41842, 2016, 22 pages. cited by applicant

edspgr.11966828