Automated oil field operations and log processing

Abstract

Some implementations include a computer-implemented method for determining one or more subsurface properties from one or more graphical oil field logs created during oil field of one or more oil field operation. The computer-implemented method may include graphically analyzing the graphical oil field logs; determining one or more regions of interest in the graphical oil field logs; generating, based on the graphical analysis of the graphical oil field logs, a respective textual description for each respective region of interest in the graphical oil field logs; and determining, by a large language model (LLM), one or more lithologies for each respective region of interest based on the textual description for the respective region of interest.

What is claimed is: 
     
         1 . A computer-implemented method for determining one or more subsurface properties from one or more graphical oil field logs created during one or more oil field operations, the computer-implemented method comprising:
 graphically analyzing each of the graphical oil field logs;   determining at least one respective region of interest for each respective graphical oil field log;   generating, based on the graphical analysis of each of the graphical oil field logs, a respective textual description for each respective region of interest; and   determining, by a large language model (LLM), at least one of the subsurface properties for each respective region of interest based on the respective textual description for the respective region of interest.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the determining at least one of the subsurface properties further comprises:
 determining a respective reference image that best describes each respective textual description;   determining respective annotations that describe each respective reference image;   presenting the reference images and annotations on a media presentation device.   
     
     
         3 . The computer-implemented method of  claim 1  further comprising:
 performing an oil field operation in a wellbore based on at least one of subsurface properties. 
 
     
     
         4 . The computer-implemented method of  claim 1 , wherein the graphical oil field logs include at least one of a gamma ray graph, a neutron-porosity graph, a formation density graph, a sonic graph, a resistivity graph, and a nuclear magnetic resonance graph. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein the graphically analyzing the graphical oil field logs includes:
 loading a respective image of each respective one or more graphical oil field logs;   identifying log traces in each of the respective graphical oil field log; and   identifying curve names, ranges, and indexes in each respective graphical oil field log.   
     
     
         6 . The computer-implemented method of  claim 1 , wherein the graphical oil field logs include images but do not include text encoded data. 
     
     
         7 . The computer-implemented method of  claim 1 , wherein the graphical analysis includes reading respective textual image data in each respective graphical oil field log, and wherein the computer-implemented method further comprises:
 aligning the respective textual image data in each respective graphical oil field log to a portion of a curve of a graph in the respective graphical oil field log.   
     
     
         8 . One or more computer-readable mediums including instructions that, when executed by one or more processors, cause the processors to perform operations to determine one or more subsurface properties from one or more graphical oil field logs created during one or more oil field operations, the instructions comprising:
 instructions to graphically analyze each of the graphical oil field logs;   instructions to determine at least one respective region of interest for each respective graphical oil field log;   instructions to generate, based on the graphical analysis of each of the graphical oil field logs, a respective textual description for each respective region of interest; and   instructions to determine, by a large language model (LLM), at least one of the subsurface properties for each respective region of interest based on the respective textual description for the respective region of interest.   
     
     
         9 . The one or more computer-readable mediums of  claim 8 , wherein the instructions to determine at least one of the subsurface properties further comprise:
 instructions to determine a respective reference image that best describes each respective textual description;   instructions to determine respective annotations that describe each respective reference image;   instructions to present the reference images and annotations on a media presentation device.   
     
     
         10 . The one or more computer-readable mediums of  claim 8  further comprising:
 instructions to perform an oil field operation in a wellbore based on at least one of subsurface properties. 
 
     
     
         11 . The one or more computer-readable mediums of  claim 8 , wherein the graphical oil field logs include at least one of a gamma ray graph, a neutron-porosity graph, a formation density graph, a sonic graph, a resistivity graph, and a nuclear magnetic resonance graph. 
     
     
         12 . The one or more computer-readable mediums of  claim 8 , wherein the graphically instructions to analyze the graphical oil field logs includes:
 instructions to load a respective image of each respective one or more graphical oil field logs;   instructions to identify log traces in each of the respective graphical oil field log; and   instructions to identify curve names, ranges, and indexes in each respective graphical oil field log.   
     
     
         13 . The one or more computer-readable mediums of  claim 8 , wherein the graphical oil field logs include images but do not include text encoded data. 
     
     
         14 . The one or more computer-readable mediums of  claim 8 , wherein the instructions to graphically analyze include instructions to read respective textual image data in each respective graphical oil field log, and wherein the one or more computer-readable mediums further comprise:
 instructions to align the respective textual image data in each respective graphical oil field log to a portion of a curve of a graph in the respective graphical oil field log.   
     
     
         15 . A system comprising:
 one or more processors;   one or more computer-readable mediums including instructions that, when executed by the one or more processors, cause the one or more processors to perform operations to determine one or more subsurface properties from one or more graphical oil field logs created during one or more oil field operations, the instructions including,   instructions to graphically analyze each of the graphical oil field logs;   instructions to determine at least one respective region of interest for each respective graphical oil field log;   instructions to generate, based on the graphical analysis of each of the graphical oil field logs, a respective textual description for each respective region of interest; and   instructions to determine, by a large language model (LLM), at least one of the subsurface properties for each respective region of interest based on the respective textual description for the respective region of interest.   
     
     
         16 . The system of  claim 15 , wherein the instructions to determine at least one of the subsurface properties further comprise:
 instructions to determine a respective reference image that best describes each respective textual description;   instructions to determine respective annotations that describe each respective reference image;   instructions to present the reference images and annotations on a media presentation device.   
     
     
         17 . The system of  claim 15  further comprising:
 instructions to perform an oil field operation in a wellbore based on at least one of subsurface properties. 
 
     
     
         18 . The system of  claim 15 , wherein the graphical oil field logs include at least one of a gamma ray graph, a neutron-porosity graph, a formation density graph, a sonic graph, a resistivity graph, and a nuclear magnetic resonance graph. 
     
     
         19 . The system of  claim 15 , wherein the instructions to graphically analyze the graphical oil field logs includes:
 instructions to load a respective image of each respective one or more graphical oil field logs;   instructions to identify log traces in each of the respective graphical oil field log; and   instructions to identify curve names, ranges, and indexes in each respective graphical oil field log.   
     
     
         20 . The system of  claim 15 , wherein the instructions to graphically analyze include instructions to read respective textual image data in each respective graphical oil field log, and wherein the one or more computer-readable mediums further comprise:
 instructions to align the respective textual image data in each respective graphical oil field log to a portion of a curve of a graph in the respective graphical oil field log.