Geologically-inspired and mutation-aware driven well log density reconstruction method for complex heterogeneous formations
- 1Zhongyuan Oilfield Informatization Management Center Department, Sinopec, Puyang, China
- 2Zhongyuan Oilfield Company, Sinopec, Puyang, China
Abstract
To address the issue of data distortion in traditional well log density reconstruction methods caused by harsh borehole environments in complex heterogeneous formations, and the challenge for general machine learning models to capture high-frequency abrupt change features due to the lack of geophysical constraints, this paper proposes a density curve reconstruction framework integrating geologically-inspired feature engineering and a mutation-aware mechanism. The method first constructs a multi-dimensional enhanced feature space covering sedimentary cycle characteristics and fluid properties through multi-scale geologically-inspired analysis, utilizing robust range normalization to eliminate interference from outliers. Subsequently, a mutation-aware driven algorithm based on the gradient change rate is innovatively designed. By dynamically adjusting loss weights, it resolves the drawback where traditional smoothing algorithms tend to erase formation interface information. Finally, geological prior constraint terms are embedded into the XGBoost architecture to achieve multi-objective optimization that balances data-driven accuracy with consistency in geological laws. Under leave-one-well-out cross-validation over ten wells, the proposed method achieves a mean R² of 0.98, an RMSE of 0.029, and an MAE of 0.022. Experimental results demonstrate that the proposed method not only improves reconstruction accuracy but also significantly enhances the physical consistency of the results. Furthermore, it precisely identifies thin interbedded boundaries, providing highly reliable basic data support for the refined evaluation of oil and gas reservoirs.
Related
- Recent Advances and Future Perspectives of AI-Based Mineral Exploration: A Review of Machine Learning, Deep Learning, and Geologically Informed Approaches
- A Technical Feasibility Assessment Using Reservoir Simulation for CO2 Storage in Sarmatian Formations of the Getic Platform, Romania
- The circulation and water mass (trans)formations in the Arctic Mediterranean Sea and their implications for the deep ocean circulation: a narrative
- From burial to barrier: how burial history controls the hydraulic conductivity in argillaceous formations
- Knifefish-inspired robotic fish enhances locomotion performance by undulatory anal fin propulsion and flexible body
BibTeX
@article{li2026geologicallyinspired,
title = {{Geologically-inspired and mutation-aware driven well log density reconstruction method for complex heterogeneous formations}},
author = {Yang Li and Haiwei Guo and Xianfeng Gong and Ping Liu and Ning Hao and Yuping Meng},
journal = {PLOS One},
year = {2026},
month = oct,
doi = {10.1371/journal.pone.0347378},
url = {https://doi.org/10.1371/journal.pone.0347378},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Geologically-inspired and mutation-aware driven well log density reconstruction method for complex heterogeneous formations
AU - Yang Li
AU - Haiwei Guo
AU - Xianfeng Gong
AU - Ping Liu
AU - Ning Hao
AU - Yuping Meng
PY - 2026
DA - 2026/10/13
JO - PLOS One
DO - 10.1371/journal.pone.0347378
UR - https://doi.org/10.1371/journal.pone.0347378
AB - To address the issue of data distortion in traditional well log density reconstruction methods caused by harsh borehole environments in complex heterogeneous formations, and the challenge for general machine learning models to capture high-frequency abrupt change features due to the lack of geophysical constraints, this paper proposes a density curve reconstruction framework integrating geologically-inspired feature engineering and a mutation-aware mechanism. The method first constructs a multi-dimensional enhanced feature space covering sedimentary cycle characteristics and fluid properties through multi-scale geologically-inspired analysis, utilizing robust range normalization to eliminate interference from outliers. Subsequently, a mutation-aware driven algorithm based on the gradient change rate is innovatively designed. By dynamically adjusting loss weights, it resolves the drawback where traditional smoothing algorithms tend to erase formation interface information. Finally, geological prior constraint terms are embedded into the XGBoost architecture to achieve multi-objective optimization that balances data-driven accuracy with consistency in geological laws. Under leave-one-well-out cross-validation over ten wells, the proposed method achieves a mean R² of 0.98, an RMSE of 0.029, and an MAE of 0.022. Experimental results demonstrate that the proposed method not only improves reconstruction accuracy but also significantly enhances the physical consistency of the results. Furthermore, it precisely identifies thin interbedded boundaries, providing highly reliable basic data support for the refined evaluation of oil and gas reservoirs.
SN - 1932-6203
ER -