Case Study: Using AI&ML to Generate Well Logs in Santa-Fe Field, Kansas

Mehrdad Zamirian; Shahab D. Mohaghegh

Download Paper | Permalink

Conference: 2023 ASEE North Central Section Conference
Location: Morgantown, West Virginia
Publication Date: March 24, 2023
Start Date: March 24, 2023
End Date: March 25, 2023
Page Count: 39
DOI: 10.18260/1-2--44900
Permanent URL: https://peer.asee.org/44900
Download Count: 141

Shahab D. Mohaghegh, a pioneer in the application of Artificial Intelligence and Machine Learning in the Exploration and Production industry, is a Professor of Petroleum and Natural Gas Engineering at West Virginia University and the president and CEO of Intelligent Solutions, Inc. (ISI). He is the director of WVU-LEADS (Laboratory for Engineering Application of Data Science).
Including more than 30 years of research and development in the petroleum engineering application of Artificial Intelligence and Machine Learning, he has authored four books (Shale Analytics, Data-Driven Reservoir Modeling, Application of Data-Driven Analytics for the Geological Storage of CO2, Smart Proxy Modeling), more than 230 technical papers and carried out more than 60 projects for independents, NOCs and IOCs. He is an SPE Distinguished Lecturer (2007 and 2020) and has been featured four times as a Distinguished Author in SPE’s Journal of Petroleum Technology (JPT 2000 and 2005). He is the founder of SPE’s Technical Section dedicated to AI and machine learning (Petroleum Data-Driven Analytics, 2011). He has been honored by the U.S. Secretary of Energy for his AI-based technical contribution in the aftermath of the Deepwater Horizon (Macondo) incident in the Gulf of Mexico (2011) and was a member of the U.S. Secretary of Energy’s Technical Advisory Committee on Unconventional Resources in two administrations (2008-2014). He represented the United States in the International Standard Organization (ISO) on Carbon Capture and Storage technical committee (2014-2016).

visit author page

Download Paper | Permalink

Abstract

Well logs are one of the most crucial field measurements in formation evaluation and reservoir characterization. They have been utilized for almost a century since 1926 when Schlumberger brothers invented the electric logs. During the decades, well logging tools and interpretation techniques have gone under many advancements and developments adding to its value as a critical field measurement. However, there are several thousand cases in which due to issues such as technical problems of the tools, operational state of the well, age of the well, time sensitivity, and economical reasons few or many of the logs are not measured. In addition to missing logs, there are many cases that logs are measured but have a bad quality and are not reliable. Nowadays, Artificial Intelligence and Machine Learning (AI&ML) techniques can be used to provide the missing data and/or identify bad quality ones. There are several studies in the literature that have used multiple available logs and trained different AI&ML models like Artificial Neural networks (ANN), Decision Tree, Random Forests, XGBoost to predict a single missed well log i.e., Sonic, Neutron Porosity, Density. In other words, multiple available logs were used as input to predict a single output log for a well. However, in reality thousands of cases can be found where a well misses multiple logs or have the minimum available logs. This study will address this issue. In this case study which is used on Santa Fe field data located in Kansas, a sequence of nine ANNs were trained, Calibrated, validated, and tested (blind validation) to generate synthetic logs step-by-step only based on GR (Gamma Ray) and caliper logs. This study consists of ten wells where nine of them were used for training, calibration, validation, and one well has been used for blind validation of the ANNs performance. The blind validation well is a well that was never used in any of ANNs training, calibration, and validation and is assumed not to exist. The order of nine ANNs sequence is to predict Neutron Porosity, Sonic Travel Time, Density, Photoelectric, and Array Resistivities (R10, R20, R30, R60, R90), respectively. The order of ANNs sequence is determined based on logs’ “Key Performance Index (KPI)”, a technique based on Fuzzy Set Theory. In all nine ANNs prediction of the blind validation well, only GR and Caliper measurements are used, and any other logs that are used as an input are generated synthetically by the previous ANNs. The results successfully show that all missed logs can be generated with high accuracy based on minimum available logs like GR and Caliper.

Citation
Format

Zamirian, M., & Mohaghegh, S. D. (2023, March), Case Study: Using AI&ML to Generate Well Logs in Santa-Fe Field, Kansas Paper presented at 2023 ASEE North Central Section Conference, Morgantown, West Virginia. 10.18260/1-2--44900

TY - CPAPER
AB - Well logs are one of the most crucial field measurements in formation evaluation and reservoir characterization. They have been utilized for almost a century since 1926 when Schlumberger brothers invented the electric logs. During the decades, well logging tools and interpretation techniques have gone under many advancements and developments adding to its value as a critical field measurement. However, there are several thousand cases in which due to issues such as technical problems of the tools, operational state of the well, age of the well, time sensitivity, and economical reasons few or many of the logs are not measured. In addition to missing logs, there are many cases that logs are measured but have a bad quality and are not reliable. Nowadays, Artificial Intelligence and Machine Learning (AI&amp;amp;ML) techniques can be used to provide the missing data and/or identify bad quality ones.
There are several studies in the literature that have used multiple available logs and trained different AI&amp;amp;ML models like Artificial Neural networks (ANN), Decision Tree, Random Forests, XGBoost to predict a single missed well log i.e., Sonic, Neutron Porosity, Density. In other words, multiple available logs were used as input to predict a single output log for a well. However, in reality thousands of cases can be found where a well misses multiple logs or have the minimum available logs. This study will address this issue.
In this case study which is used on Santa Fe field data located in Kansas, a sequence of nine ANNs were trained, Calibrated, validated, and tested (blind validation) to generate synthetic logs step-by-step only based on GR (Gamma Ray) and caliper logs. This study consists of ten wells where nine of them were used for training, calibration, validation, and one well has been used for blind validation of the ANNs performance. The blind validation well is a well that was never used in any of ANNs training, calibration, and validation and is assumed not to exist. The order of nine ANNs sequence is to predict Neutron Porosity, Sonic Travel Time, Density, Photoelectric, and Array Resistivities (R10, R20, R30, R60, R90), respectively. The order of ANNs sequence is determined based on logs’ “Key Performance Index (KPI)”, a technique based on Fuzzy Set Theory. In all nine ANNs prediction of the blind validation well, only GR and Caliper measurements are used, and any other logs that are used as an input are generated synthetically by the previous ANNs. The results successfully show that all missed logs can be generated with high accuracy based on minimum available logs like GR and Caliper.

AU - Mehrdad Zamirian
AU - Shahab D. Mohaghegh
CY - Morgantown, West Virginia
DA - 2023/03/24
PB - ASEE Conferences
TI - Case Study: Using AI&ML to Generate Well Logs in Santa-Fe Field, Kansas
UR - https://peer.asee.org/44900
DO - 10.18260/1-2--44900
ER -

Case Study: Using AI&ML to Generate Well Logs in Santa-Fe Field, Kansas

Paper Authors

Mehrdad Zamirian West Virginia University

Shahab D. Mohaghegh West Virginia University

Abstract

Citation

APA

APA - LaTeX bibitem

MLA

MLA - LaTeX bibitem

Bibtex

EndNote - RIS