Petrophysical methods are widely used to study physical and chemical properties of rocks and fluids. Due to the complexity of the lithological makeup of different rock types, quantitative analysis of mineral composition is a challenging task. In this study, we describe the use of a hybrid machine learning (ML) model to estimate mineral compositions by combining a convolutional neural network (CNN) and XGBoost algorithm. The selected inputs are preprocessed into a square matrix of format and passed to the convolutional layers of the feature learning section, and the XGBoost is utilized to solve the regression problem. The conventional and geochemical logs from the Horn River Basin, in western Canada, are selected for the model training and validation. Monte Carlo dropout (MCD) is added to model training to decrease the sensitivity and increase repeatability of model prediction. The comparison of metrics and correlation coefficients shows that the hybrid ML is slightly better than U-net CNN and XGBoost individually, which demonstrates the reliability and effectiveness of the proposed algorithm. The presented method could be applied to other exploration settings such as geothermal, unconformity uranium or sediment-hosted mineral deposits.
Skip Nav Destination
SEG/AAPG International Meeting for Applied Geoscience & Energy
August 26–29, 2024
Houston, Texas
A hybrid machine learning model for improving regression of mineral composition estimation using well logging data
Xiaojun Liu;
Xiaojun Liu
Geological Survey of Canada - Natural Resources Canada
Search for other works by this author on:
Kezhen Hu;
Kezhen Hu
Geological Survey of Canada - Natural Resources Canada
Search for other works by this author on:
Stephen E. Grasby;
Stephen E. Grasby
Geological Survey of Canada - Natural Resources Canada
Search for other works by this author on:
Benjamin Lee
Benjamin Lee
Geological Survey of Canada - Natural Resources Canada
Search for other works by this author on:
Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, Houston, Texas, August 2024.
Paper Number:
SEG-2024-4089738
Published:
August 26 2024
Citation
Liu, Xiaojun, Hu, Kezhen, Grasby, Stephen E., and Benjamin Lee. "A hybrid machine learning model for improving regression of mineral composition estimation using well logging data." Paper presented at the SEG/AAPG International Meeting for Applied Geoscience & Energy, Houston, Texas, August 2024. doi: https://doi.org/10.1190/image2024-4089738.1
Download citation file:
Sign in
Don't already have an account? Register
Personal Account
You could not be signed in. Please check your username and password and try again.
Captcha Validation Error. Please try again.
Pay-Per-View Access
$9.00
Advertisement
7
Views
Advertisement
Suggested Reading
Advertisement