Skip to main content
Home
Membership
Log on
Cart
Toggle search
Search
Toggle navigation
Search
Society of Petrophysicists and Well Log Analysts
About
Toggle
Vision
SPWLA History
Presidents and Awards
Symposium Locations and Conferences
Board of Directors
Policies
Events
Toggle
Event List
Event Calendar
Annual Symposium
Event Roster
Publications
Toggle
SPWLA Today Newsletter
Petrophysics Journal
Publication Guidelines
Digital Papers
Publications Advertisement
Petrophysicists Covers
Resources
Toggle
Careers/Education
Job Opportunities
Frank S. Millard Training Center
Webinars/Videos
Petrophysics Skill Set Guidelines (PSSG)
SPWLA Nuggets of Wisdom
SPWLA The More You Know
YP Resources
Mnemonics
API Standards
Petrophysical Software Directory
Member Directory
Downloads
Glossary
Annual Symposium
Toggle
2024 Annual Symposium
Symposium Author Instructions
International Student Paper Contest
Chapters/SIGs
Toggle
Chapters
SIGs
Resources for Chapter Officers
Chapters at Large
Student Chapters
Distinguished Speaker Program
Foundation
Toggle
Make a Donation
Foundation Board Members
Foundation Overview
Scholarship and Grant Program
Store
Toggle
Digital Papers
Books, CDs and more
Additional Membership Dues
Make A Donation
All
Volunteer Opportunities
Synthetic Sonic Log Generation With Machine Learning: A Cont
Compressional and shear sonic traveltime logs (DTC and DTS, respectively) are crucial for subsurface characterization and seismic-well tie. However, these two logs are often missing or incomplete in many oil and gas wells. Therefore, many petrophysical and geophysical workflows include sonic log synthetization or pseudo-log generation based on multivariate regression or rock physics relations. Started on March 1, 2020, and concluded on May 7, 2020, the SPWLA PDDA SIG hosted a contest aiming to predict the DTC and DTS logs from seven “easy-to-acquire” conventional logs using machine-learning methods (GitHub, 2020). In the contest, a total number of 20,525 data points with half-foot resolution from three wells was collected to train regression models using machine-learning techniques. Each data point had seven features, consisting of the conventional “easy-to-acquire” logs: caliper, neutron porosity, gamma ray (GR), deep resistivity, medium resistivity, photoelectric factor, and bulk density, respectively, as well as two sonic logs (DTC and DTS) as the target. The separate data set of 11,089 samples from a fourth well was then used as the blind test data set. The prediction performance of the model was evaluated using root mean square error (RMSE) as the metric, {FULL EQUATION IN PAPER}
In the benchmark model, (Yu et al., 2020), we used a Random Forest regressor and conducted minimal preprocessing to the training data set; an RMSE score of 17.93 was achieved on the test data set. The top five models from the contest, on average, beat the performance of our benchmark model by 27% in the RMSE score. In the paper, we will review these five solutions, including preprocess techniques and different machine-learning models, including neural network, long short-term memory (LSTM), and ensemble trees. We found that data cleaning and clustering were critical for improving the performance in all models.
Standard price:
10.00
Discounted price:
1.00
Your price:
10.00
You could save:
90.0%
Quantity:
Quantity is required.
Quantity must be a positive whole number.
Author(s):
Yanxiang Yu, Chicheng Xu, Siddharth Misra, Weichang Li, Michael Ashby, Wen Pan, Tianqi Deng, Honggeu
Company(s):
SPWLA PPDA SIG
Year:
2021
{1}
##LOC[OK]##
{1}
##LOC[OK]##
##LOC[Cancel]##
{1}
##LOC[OK]##
##LOC[Cancel]##