What question did this study set out to answer?

This research aims to develop a unified machine-learning framework for predicting lithology and formation logs from drilling parameters in high-pressure salt formations.

July 23, 2026Journal of Petroleum Exploration and Production TechnologyOpen Access

Real-time lithology and log prediction from drilling parameters using machine learning for high-pressure salt-bearing formation, Missan oilfields, Iraq

View Full Paper

Ask AI

Bookmark

Authors

HYHayder Yousif XHXuri Huang OAOsama G. Al-Salih

Discussion

Member takes

Overview

Randomized trial predicts lithology and log data from drilling parameters, suggesting enhanced operational efficiency.

Key Points

This research aims to develop a unified machine-learning framework for predicting lithology and formation logs from drilling parameters in high-pressure salt formations.
Utilized a dataset of 30,500 records from four wells in the Buzurgan oilfield.
Employed seven supervised algorithms, including Random Forest and Extreme Gradient Boosting, evaluated with blind-well validation.
Analyzed drilling parameters such as rate of penetration, weight on bit, torque, and flow rate to predict lithology and logs.
Achieved over 97% accuracy in lithology classification and 99% in formation-member identification.
Regressors correlated strongly with wireline measurements (R² ≥ 0.93 for gamma-ray and ≥ 0.91 for sonic travel-time).
Identified torque and weight on bit as the most influential predictors of lithology and log outcomes.

Cite This Study

Yousif et al. (2026) studied this question.

synapsesocial.com/papers/6a61ae6bfaa9903c51169a79 https://doi.org/10.1007/s13202-026-02192-y

View Full Paper

Ask AI

Bookmark

July 23, 2026Journal of Petroleum Exploration and Production TechnologyOpen Access

Real-time lithology and log prediction from drilling parameters using machine learning for high-pressure salt-bearing formation, Missan oilfields, Iraq

View Full Paper

Ask AI

Bookmark

Authors

HYHayder Yousif XHXuri Huang OAOsama G. Al-Salih

Discussion

Member takes

Overview

Randomized trial predicts lithology and log data from drilling parameters, suggesting enhanced operational efficiency.

Key Points

This research aims to develop a unified machine-learning framework for predicting lithology and formation logs from drilling parameters in high-pressure salt formations.
Utilized a dataset of 30,500 records from four wells in the Buzurgan oilfield.
Employed seven supervised algorithms, including Random Forest and Extreme Gradient Boosting, evaluated with blind-well validation.
Analyzed drilling parameters such as rate of penetration, weight on bit, torque, and flow rate to predict lithology and logs.
Achieved over 97% accuracy in lithology classification and 99% in formation-member identification.
Regressors correlated strongly with wireline measurements (R² ≥ 0.93 for gamma-ray and ≥ 0.91 for sonic travel-time).
Identified torque and weight on bit as the most influential predictors of lithology and log outcomes.

Cite This Study

Yousif et al. (2026) studied this question.

synapsesocial.com/papers/6a61ae6bfaa9903c51169a79 https://doi.org/10.1007/s13202-026-02192-y

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark