Improving subsurface characterization in tropical granitic terrains using machine learning and deep learning-enhanced resistivity–chargeability modeling
10 affiliations
- 1Earth System Processes and Hazard Modeling Center, Geophysics Programme, School of Physics, Universiti Sains Malaysia, 11800 USM, Penang, Malaysia
- 2Faculty of Environmental & Urban Change, York University, 4700 Keele Street, Toronto, ON, M3J 1P3, Canada
- 3Geophysics Programme, School of Physics, Universiti Sains Malaysia, 11800 USM, Penang, Malaysia
- 4Helmholtz Centre Potsdam – GFZ German Research Centre for Geosciences, 14473, TelegrafenbergPotsdam, Brandenburg, Germany
- 5Department of Computer Science, University of Fredericton, Fredericton, NB, E3B 6Z6, Canada
- 6Department of Chemical and Environmental Engineering, University of Cincinnati, Cincinnati, OH, USA
- 7Department of Geology, Federal University of Technology, Owerri, 1526, Imo, Nigeria
- 8Department of Mathematical and Physical Sciences, Miami University, Oxford, OH, USA
- 9Department of Physics, Federal University Gashua, Nguru Road, Gashua, Yobe, Nigeria
- 10Akwa Ibom State Polytechnic, 1200 Ikot Osurua, Ikot Ekpene, Akwa Ibom, Nigeria
Abstract
Accurately characterizing subsurface lithological heterogeneity in tropical granitic terrains remains challenging because conventional electrical resistivity tomography (ERT) and induced polarization (IP) inversions often smooth abrupt boundaries, obscure weathered interfaces, and underrepresent clay–moisture contrasts. This study develops an integrated geophysical framework for approximating inversion-derived chargeability patterns using depth-referenced ERT–IP collocation, conservative outlier filtering, and stratified sampling to construct a robust dataset representative of residual soils, weathered and fractured granite, and moisture-bearing weak zones. Machine learning and deep learning (ML/DL) methods were applied to capture nonlinear resistivity–IP relationships governing lithological transitions. CatBoost achieved the strongest standalone performance (R 2 = 0.942 train; 0.945 test), marginally surpassing random forest, while the stacked ensemble achieved the highest predictive performance (test R 2 = 0.947). The one-dimensional convolutional neural network with global average pooling performed comparably to the artificial neural network while effectively representing depth-dependent resistivity–IP relationships. All ML/DL models yielded RMSE ≈ 0.76–1.09 msec (< 10%), confirming high predictive fidelity. ML/DL-derived and CatBoost-regressed 2D chargeability models reproduced inversion-defined structures and preserved the spatial expression of clay-rich horizons, fracture-controlled weak zones, and lithological interfaces. The results are relevant to geoengineering assessments, where relatively competent bedrock generally occurs below ~ 30–33 m and may provide favorable conditions for deep foundation development, subject to geotechnical verification. They also provide useful insights for hydrogeological evaluations by identifying weathered/fractured zones extending to ~ 41 m that may represent favorable groundwater targets. K-means clustering analysis (KMCA) further supported lithological discrimination by grouping materials into coherent residual-soil-to-weathered-granite domains. The integrated inversion–ML/DL–KMCA workflow provides a cost-effective and geologically consistent framework for approximating inversion-derived chargeability patterns and supporting subsurface characterization in complex crystalline terrains.
Related
- Integrating high-resolution magnetic surveys and metaheuristic optimization for quantitative characterization of subsurface magnetic sources in a municipal landfill
- Activated Carbon from Tropical Almond Shell ( Terminalia catappa L. ): Synthesis, Characterization, Application, and Regeneration for Chromium (VI) Adsorption
- Geochemical evaluation of subsurface hydrogen-brine-mineral interactions and hydrogen loss
- Damage Assessment of Supporting Pillars in an Underground Cave Using Joint Inversion of Electrical Resistivity and P-wave Velocity, Burgundy (France)
- Sidewall-Based Three-Dimensional DC Resistivity Imaging for Identifying Potentially Water-Bearing Zones Around an Operational Railway Tunnel
BibTeX
@article{akingboye2026improving,
title = {{Improving subsurface characterization in tropical granitic terrains using machine learning and deep learning-enhanced resistivity–chargeability modeling}},
author = {Adedibu Sunny Akingboye and Andy Anderson Bery and Hui Tang and Ayokunle Olalekan Ige and Obinna Chigoziem Akakuru and G.A. Bala and Mbuotidem David Dick},
journal = {Scientific Reports},
year = {2026},
month = aug,
doi = {10.1038/s41598-026-62674-1},
url = {https://doi.org/10.1038/s41598-026-62674-1},
note = {CC BY},
}
RIS
TY - JOUR
TI - Improving subsurface characterization in tropical granitic terrains using machine learning and deep learning-enhanced resistivity–chargeability modeling
AU - Adedibu Sunny Akingboye
AU - Andy Anderson Bery
AU - Hui Tang
AU - Ayokunle Olalekan Ige
AU - Obinna Chigoziem Akakuru
AU - G.A. Bala
AU - Mbuotidem David Dick
PY - 2026
DA - 2026/08/17
JO - Scientific Reports
DO - 10.1038/s41598-026-62674-1
UR - https://doi.org/10.1038/s41598-026-62674-1
AB - Accurately characterizing subsurface lithological heterogeneity in tropical granitic terrains remains challenging because conventional electrical resistivity tomography (ERT) and induced polarization (IP) inversions often smooth abrupt boundaries, obscure weathered interfaces, and underrepresent clay–moisture contrasts. This study develops an integrated geophysical framework for approximating inversion-derived chargeability patterns using depth-referenced ERT–IP collocation, conservative outlier filtering, and stratified sampling to construct a robust dataset representative of residual soils, weathered and fractured granite, and moisture-bearing weak zones. Machine learning and deep learning (ML/DL) methods were applied to capture nonlinear resistivity–IP relationships governing lithological transitions. CatBoost achieved the strongest standalone performance (R 2 = 0.942 train; 0.945 test), marginally surpassing random forest, while the stacked ensemble achieved the highest predictive performance (test R 2 = 0.947). The one-dimensional convolutional neural network with global average pooling performed comparably to the artificial neural network while effectively representing depth-dependent resistivity–IP relationships. All ML/DL models yielded RMSE ≈ 0.76–1.09 msec (< 10%), confirming high predictive fidelity. ML/DL-derived and CatBoost-regressed 2D chargeability models reproduced inversion-defined structures and preserved the spatial expression of clay-rich horizons, fracture-controlled weak zones, and lithological interfaces. The results are relevant to geoengineering assessments, where relatively competent bedrock generally occurs below ~ 30–33 m and may provide favorable conditions for deep foundation development, subject to geotechnical verification. They also provide useful insights for hydrogeological evaluations by identifying weathered/fractured zones extending to ~ 41 m that may represent favorable groundwater targets. K-means clustering analysis (KMCA) further supported lithological discrimination by grouping materials into coherent residual-soil-to-weathered-granite domains. The integrated inversion–ML/DL–KMCA workflow provides a cost-effective and geologically consistent framework for approximating inversion-derived chargeability patterns and supporting subsurface characterization in complex crystalline terrains.
SN - 2045-2322
ER -