# US 11,079,581 B2 · Resolution preserving methodology to generate continuous log scale reservoir permeability profile from petrographic thin section images > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,079,581 B2 - Document ID: US11079581B2 - Status: Granted - Kind: B2 - Application number: 16/694,399 - Filed: 2019-11-25 - Published: 2021-05-27 - Granted: 2021-08-03 - Earliest claimed: 2019-11-25 - Assignees: Saudi Arabian Oil Company - Applicants: Saudi Arabian Oil Company - Inventors: Mokhles M Mezghani; Fatai A Anifowose - Web page: https://patentgrep.com/patent/US11079581B2 ## CPC - G01N 15/08: Investigating permeability, pore-volume, or surface area of porous materials - G02B 21/0036: {Scanning details, e.g. scanning stages} - G06T 9/002: {using neural networks} - G06T 9/40: Tree coding, e.g. quadtree, octree - E21B 47/00: Survey of boreholes or wells (monitoring pressure or flow of drilling fluid E21B21/08) - E21B 2200/20: Computer models or simulations, e.g. for reservoirs under production, drill bits - E21B 2200/22: Fuzzy logic, artificial intelligence, neural networks or the like - G01N 33/241: {for hydrocarbon content} - G01N 2015/0846: {by use of radiation, e.g. transmitted or reflected light} - G02B 21/365: {Control or image processing arrangements for digital or video microscopes (G02B21/361, G02B21/362 take precedence)} - G06T 2207/10056: Microscopic image - G06T 2207/20084: Artificial neural networks [ANN] - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) - G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - E21B: EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS ## Abstract Embodiments of the present disclosure aim to provide advanced log scale permeability estimation systems and methods. In an embodiment, a computer system is provided and configured to perform petrographic thin section image permeability analysis and then generate log scale permeability estimations for a well using machine learning methods and techniques. In an embodiment, the advanced log scale permeability estimation systems and methods are configured with a computer system or a micro-computer system, that can be configured with a computer circuit board comprising a processor, memory, networking capability, and software. In another embodiment the log scale permeability estimations for a well are input into a reservoir simulation model to determine hydrocarbon resources and to make portfolio predictions for a well. ## Claims ### Claim 1 An advanced log scale permeability estimation system, comprising: a high-resolution microscope configured to take photographs of a plurality of petrographic thin section samples and create petrographic thin section sample digital image files from the photographs, and a computer system configured with specialized software to perform a first specialized function and a second specialized function: the first specialized function to receive the petrographic thin section sample digital image files from the high-resolution microscope and analyze the petrographic thin section sample digital image files to determine a permeability estimation for each of the petrographic thin section sample digital image files and further configured to receive and store depth information associated with each of the plurality of petrographic thin section samples and the respective permeability estimation into a permeability estimation log; the second specialized function to combine the permeability estimation log with a set of corresponding wireline logs to form a calibration log, the computer system further configured to perform machine learning on a majority portion of the calibration log, generate a calibrated model, validate the calibrated model with a remaining portion of the calibration log, and determine if the calibrated model is within a pre-identified error threshold such that it can be considered a validated model; the computer system further comprising: a computer circuit board, a microprocessor configured on the computer circuit board, the microprocessor configured with input/output channels, memory configured to be in communication with the microprocessor, a data bus extending between the memory and the microprocessor, and a network interface configured to be in communication with the microprocessor, non-volatile memory configured to be in communication with the microprocessor, and a specialized software program stored on the nonvolatile memory that enables the microprocessor to perform each of the first specialized function and the second specialized function. ### Claim 2 (depends on 1) The system of claim 1, wherein the computer system is further configured to perform a third specialized function and the specialized software program stored on the nonvolatile memory is further configured to enable the microprocessor to perform the third specialized function, the third specialized function configured to receive logs from a new or un-cored well and process the logs using the validated model to output a log scale permeability estimation log for the new or un-cored well. ### Claim 3 (depends on 2) The system of claim 2, wherein the computer system is further configured to input the resulting log scale permeability estimation log for the new or un-cored well into a reservoir saturation model. ### Claim 4 (depends on 2) The system of claim 2, wherein the computer system is further configured to input the resulting log scale permeability estimation log for the new or un-cored well into a fluid flow rate model. ### Claim 5 (depends on 1) The system of claim 1, wherein the first specialized function of the computer system is further configured to perform the Lattice-Boltzmann technique to determine a permeability estimation for each of the petrographic thin section sample digital image files. ### Claim 6 (depends on 1) The system of claim 1, wherein the first specialized function of the computer system is further configured to perform the modified Kozeny technique to determine a permeability estimation for each of the petrographic thin section sample digital image files. ### Claim 7 (depends on 1) The system of claim 1, wherein the first specialized function of the computer system is further configured to perform the Darcy flow model technique to determine a permeability estimation for each of the petrographic thin section sample digital image files. ### Claim 8 (depends on 1) The system of claim 1, wherein the second specialized function of the computer system is further configured to perform the artificial neural network machine learning technique. ### Claim 9 (depends on 1) The system of claim 1, wherein the second specialized function of the computer system is further configured to perform the support vector machine, radial basis function, fuzzy logic, decision tree, or other similar machine learning techniques. ### Claim 10 (depends on 1) The system of claim 1, wherein the first specialized function is further configured to sort and store the permeability estimation log by depth. ### Claim 11 A method of generating advanced log scale permeability estimations for a well, comprising the following steps: deploying an log scale permeability estimation system, comprising: a high-resolution microscope configured to take photographs of a plurality of petrographic thin section samples and create petrographic thin section sample digital image files from the photographs, and a computer system configured with specialized software to perform a first specialized function and a second specialized function: the first specialized function to receive the petrographic thin section sample digital image files from the high-resolution microscope and analyze the petrographic thin section sample digital image files to determine a permeability estimation for each of the petrographic thin section sample digital image files and further configured to receive and store depth information associated with each of the plurality of petrographic thin section samples and the respective permeability estimation into a permeability estimation log; the second specialized function to combine the permeability estimation log with a set of corresponding wireline logs to form a calibration log, the computer system further configured to perform machine learning on a majority portion of the calibration log, generate a calibrated model, validate the calibrated model with a remaining portion of the calibration log, and determine if the calibrated model is within a pre-identified error threshold such that it can be considered a validated model; the computer system further comprising: a computer circuit board, a microprocessor configured on the computer circuit board, the microprocessor configured with input/output channels, memory configured to be in communication with the microprocessor, a data bus extending between the memory and the microprocessor, and a network interface configured to be in communication with the microprocessor, non-volatile memory configured to be in communication with the microprocessor, and a specialized software program stored on the nonvolatile memory that enables the microprocessor to perform each of the first specialized function and the second specialized function; the method further comprising the step of: performing processing steps, by the computer, system, to perform each of the first specialized function and the second specialized function. ### Claim 12 (depends on 11) The method of claim 11, wherein the computer method is further configured to perform a third specialized function and the specialized software program stored on the nonvolatile memory is further configured to enable the microprocessor to perform the third specialized function, the third specialized function configured to receive logs from a new or un-cored well and process the logs using the validated model to output a log scale permeability estimation log for the new or un-cored well. ### Claim 13 (depends on 12) The method of claim 12, wherein the computer system is further configured to input the resulting log scale permeability estimation log for the new or un-cored well into a reservoir saturation model. ### Claim 14 (depends on 12) The method of claim 12, wherein the computer system is further configured to input the resulting log scale permeability estimation log for the new or un-cored well into a fluid flow rate model. ### Claim 15 (depends on 11) The method of claim 11, wherein the first specialized function of the computer system is further configured to perform the Lattice-Boltzmann technique to determine a permeability estimation for each of the petrographic thin section sample digital image files. ### Claim 16 (depends on 11) The method of claim 11, wherein the first specialized function of the computer system is further configured to perform the modified Kozeny technique to determine a permeability estimation for each of the petrographic thin section sample digital image files. ### Claim 17 (depends on 11) The method of claim 11, wherein the first specialized function of the computer system is further configured to perform the Darcy flow model technique to determine a permeability estimation for each of the petrographic thin section sample digital image files. ### Claim 18 (depends on 11) The method of claim 11, wherein the second specialized function of the computer system is further configured to perform the artificial neural network machine learning technique. ### Claim 19 (depends on 11) The method of claim 11, wherein the second specialized function of the computer system is further configured to perform the support vector machine, radial basis function, fuzzy logic, decision tree, or other similar machine learning techniques. ### Claim 20 (depends on 11) The method of claim 11, wherein the first specialized function is further configured to sort and store the permeability estimation log by depth.