Saved in:
Bibliographic Details
Main Authors: Akingboye, Adedibu Sunny, Bery, Andy Anderson, Tang, Hui, Ige, Ayokunle Olalekan, Akakuru, Obinna Chigoziem, Bala, Gabriel Abraham, Dick, Mbuotidem David
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.17089
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911166551293952
author Akingboye, Adedibu Sunny
Bery, Andy Anderson
Tang, Hui
Ige, Ayokunle Olalekan
Akakuru, Obinna Chigoziem
Bala, Gabriel Abraham
Dick, Mbuotidem David
author_facet Akingboye, Adedibu Sunny
Bery, Andy Anderson
Tang, Hui
Ige, Ayokunle Olalekan
Akakuru, Obinna Chigoziem
Bala, Gabriel Abraham
Dick, Mbuotidem David
contents Subsurface lithological heterogeneity presents challenges for traditional geophysical methods, particularly in resolving nonlinear electrical resistivity and induced polarization (IP) relationships. This study introduces a data-driven machine learning and deep learning (ML/DL) framework for predicting 2D IP chargeability models from resistivity, depth, and station distance, reducing reliance on field IP surveys. The framework integrates ensemble regressors with a one-dimensional convolutional neural network (1D CNN) enhanced by global average pooling. Among the tested models, CatBoost achieved the highest prediction accuracy (R^2 = 0.942 training, 0.945 testing), closely followed by random forest, while the stacked ML/DL ensemble further improved performance, particularly for complex resistivity-IP behaviors. Overall accuracy ranged from R^2 = 0.882 to 0.947 with RMSE < 0.04. Integration with k-means clustering enhanced lithological discrimination, effectively delineating sandy silt, silty sand, and weathered granite influenced by saturation, clay content, and fracturing. This scalable approach provides a rapid solution for subsurface modeling in exploration, geotechnical, and environmental applications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17089
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Advancing resistivity-chargeability modeling for complex subsurface characterization using machine learning and deep learning
Akingboye, Adedibu Sunny
Bery, Andy Anderson
Tang, Hui
Ige, Ayokunle Olalekan
Akakuru, Obinna Chigoziem
Bala, Gabriel Abraham
Dick, Mbuotidem David
Geophysics
Subsurface lithological heterogeneity presents challenges for traditional geophysical methods, particularly in resolving nonlinear electrical resistivity and induced polarization (IP) relationships. This study introduces a data-driven machine learning and deep learning (ML/DL) framework for predicting 2D IP chargeability models from resistivity, depth, and station distance, reducing reliance on field IP surveys. The framework integrates ensemble regressors with a one-dimensional convolutional neural network (1D CNN) enhanced by global average pooling. Among the tested models, CatBoost achieved the highest prediction accuracy (R^2 = 0.942 training, 0.945 testing), closely followed by random forest, while the stacked ML/DL ensemble further improved performance, particularly for complex resistivity-IP behaviors. Overall accuracy ranged from R^2 = 0.882 to 0.947 with RMSE < 0.04. Integration with k-means clustering enhanced lithological discrimination, effectively delineating sandy silt, silty sand, and weathered granite influenced by saturation, clay content, and fracturing. This scalable approach provides a rapid solution for subsurface modeling in exploration, geotechnical, and environmental applications.
title Advancing resistivity-chargeability modeling for complex subsurface characterization using machine learning and deep learning
topic Geophysics
url https://arxiv.org/abs/2509.17089