Board 90: Core Feature Extraction with Computer Vision

Salvador A. Vargas; Daniel Torres; Alberto Cureg Cruz

Download Paper | Permalink

Conference: 2023 ASEE Annual Conference & Exposition
Location: Baltimore , Maryland
Publication Date: June 25, 2023
Start Date: June 25, 2023
End Date: June 28, 2023
Conference Session: Energy Conversion, Conservation and Nuclear Engineering Division (ECCNE) Poster Session
Tagged Divisions: Energy Conversion and Conservation and Nuclear Engineering Division (ECCNE)
Tagged Topic: Diversity
Page Count: 18
DOI: 10.18260/1-2--42993
Permanent URL: https://strategy.asee.org/42993
Download Count: 124

Request a correction

Paper Authors

biography

Salvador A. Vargas California State University, Bakersfield

visit author page

I received a bachelors of science in geological sciences from California State University Bakersfield (CSUB) the year of 2018. In 2020 I received a masters of science in geological sciences from CSUB with an emphasis in petroleum geology, and am currently pursuing a third degree in computer science. I am interested in research that helps the energy industry through the involvement of artificial intelligence.

visit author page

biography

Daniel Torres California State University, Bakersfield

visit author page

I am completing my bachelors in computer science at CSU, Bakersfield. My primary interest is in Artificial Intelligence. I am currently conducting research in Computer Vision. Particularly, using AI in order extract valuable data from Core slabs in order to improve the energy industry. In the future, I would love to pursue a Masters degree in the field of Artificial Intelligence and apply my knowledge to solve problems around the world.

visit author page

biography

Alberto Cureg Cruz California State University, Bakersfield

visit author page

Dr. Cruz is an Assistant Professor of Computer Science, Principal Investigator of the Computer Perception Laboratory (COMPLAB), and board member of the Center for Environmental Studies (CES) at the California State University, Bakersfield (CSUB). He recei

visit author page

Download Paper | Permalink

Abstract

In the oil and gas industry, exploration is largely dependent on the study of the subsurface hundreds or thousands of feet below. Most of the data used for this purpose is collected using borehole logging tools. Although sophisticated, these tools are limited as to how precisely they can measure the subsurface in terms of vertical resolution. There is one method of studying the subsurface that provides unlimited vertical resolution – core samples. Although core samples provide scientists the opportunity to generate a full, continuous data set, lab analysis work is normally done at one-foot intervals, as anything more would be prohibitively expensive. This means at best, a representative data set is generated. However, if the subsurface is not homogeneous, it is difficult to generate a representative data set with lab analysis done at one-foot intervals. This is a void that artificial intelligence can fill. More specifically, a properly trained neural network can analyze high-resolution core images continuously from top to bottom and generate a continuous analysis. It is also important to note that geologic interpretation tied to core analysis can introduce human error and subjectivity. Here too, a properly trained neural network can generate results with extreme levels of accuracy and precision. One core analysis expert believes that core analysis done manually is flawed about 70% of the time. This flawed analysis can result from lack of experience and or a lack of knowledge of the geologic formation. We are not the first to attempt to analyze core samples with vision algorithms. A group of Stanford researchers used micro-computed tomography (micro-CT) and Scanning Electron Microscopy (SEM) images of core samples to characterize the porous media. While promising, SEM and micro-CT imaging is expensive, and more importantly it is not a standard practice in the oil and gas industry to collect these types of images, making these images rare. One other work applied convolutional neural networks to a GIS based regional saturation system, but our work is significantly different. It is well known that training a neural network requires abundant data, thankfully with the method of core analysis we are proposing that will not be a problem. Through industrial partnerships we’ve obtained hundreds to thousands of core images sufficient to train a neural network, as well as core interpretations tied to those images coming from a core analysis expert with over 40 years of experience. We are the first to propose automatic hydrocarbon saturation as well as lithology prediction from core slab images. We propose the use of convolutional neural networks to analyze core samples at a single site. We plan to conduct experiments using a variety of neural networks to determine the best practices, and explore how such a service can be offered to the industry via the software-as-a-service paradigm. In the past, automated analysis through core slab images has not been possible simply because images of the required resolution were not common, but that has changed. If implemented successfully, this proposed method could become the new standard for core evaluation.

Citation
Format

Vargas, S. A., & Torres, D., & Cruz, A. C. (2023, June), Board 90: Core Feature Extraction with Computer Vision Paper presented at 2023 ASEE Annual Conference & Exposition, Baltimore , Maryland. 10.18260/1-2--42993

TY - CPAPER
AB - In the oil and gas industry, exploration is largely dependent on the study of the subsurface hundreds or thousands of feet below. Most of the data used for this purpose is collected using borehole logging tools. Although sophisticated, these tools are limited as to how precisely they can measure the subsurface in terms of vertical resolution. There is one method of studying the subsurface that provides unlimited vertical resolution – core samples. Although core samples provide scientists the opportunity to generate a full, continuous data set, lab analysis work is normally done at one-foot intervals, as anything more would be prohibitively expensive. This means at best, a representative data set is generated. However, if the subsurface is not homogeneous, it is difficult to generate a representative data set with lab analysis done at one-foot intervals. This is a void that artificial intelligence can fill. More specifically, a properly trained neural network can analyze high-resolution core images continuously from top to bottom and generate a continuous analysis. It is also important to note that geologic interpretation tied to core analysis can introduce human error and subjectivity. Here too, a properly trained neural network can generate results with extreme levels of accuracy and precision. One core analysis expert believes that core analysis done manually is flawed about 70% of the time. This flawed analysis can result from lack of experience and or a lack of knowledge of the geologic formation. We are not the first to attempt to analyze core samples with vision algorithms. A group of Stanford researchers used micro-computed tomography (micro-CT) and Scanning Electron Microscopy (SEM) images of core samples to characterize the porous media. While promising, SEM and micro-CT imaging is expensive, and more importantly it is not a standard practice in the oil and gas industry to collect these types of images, making these images rare. One other work applied convolutional neural networks to a GIS based regional saturation system, but our work is significantly different. It is well known that training a neural network requires abundant data, thankfully with the method of core analysis we are proposing that will not be a problem. Through industrial partnerships we’ve obtained hundreds to thousands of core images sufficient to train a neural network, as well as core interpretations tied to those images coming from a core analysis expert with over 40 years of experience. We are the first to propose automatic hydrocarbon saturation as well as lithology prediction from core slab images. We propose the use of convolutional neural networks to analyze core samples at a single site. We plan to conduct experiments using a variety of neural networks to determine the best practices, and explore how such a service can be offered to the industry via the software-as-a-service paradigm. In the past, automated analysis through core slab images has not been possible simply because images of the required resolution were not common, but that has changed. If implemented successfully, this proposed method could become the new standard for core evaluation.

AU - Salvador A. Vargas
AU - Daniel Torres
AU - Alberto Cureg Cruz
CY - Baltimore , Maryland
DA - 2023/06/25
PB - ASEE Conferences
TI - Board 90: Core Feature Extraction with Computer Vision
UR - https://strategy.asee.org/42993
DO - 10.18260/1-2--42993
ER -