Leveraging boosting machine learning for drilling rate of penetration (ROP) prediction based on drilling and petrophysical parameters

Drilling optimization requires accurate drill bit rate-of-penetration (ROP) predictions. ROP decreases drilling time and costs and increases rig productivity. This study employs random forest (RF), gradient boosting modeling (GBM), extreme gradient boosting (XGBoost), and adaptive boosting (Adaboost...

Full description

Saved in:
Bibliographic Details
Main Authors: Raed H. Allawi, Watheq J. Al-Mudhafar, Mohammed A. Abbas, David A. Wood
Format: Article
Language:English
Published: KeAi Communications Co. Ltd. 2025-06-01
Series:Artificial Intelligence in Geosciences
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666544125000176
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850164064004603904
author Raed H. Allawi
Watheq J. Al-Mudhafar
Mohammed A. Abbas
David A. Wood
author_facet Raed H. Allawi
Watheq J. Al-Mudhafar
Mohammed A. Abbas
David A. Wood
author_sort Raed H. Allawi
collection DOAJ
description Drilling optimization requires accurate drill bit rate-of-penetration (ROP) predictions. ROP decreases drilling time and costs and increases rig productivity. This study employs random forest (RF), gradient boosting modeling (GBM), extreme gradient boosting (XGBoost), and adaptive boosting (Adaboost) models to generate ROP predictions. The models use well data from a 3200-m segment across the stratigraphic column (Dibdibba to Zubair formations) of the large West Qurna oil field in Southern Iraq, penetrating 19 formations and four oil reservoirs. The reservoir sections are between 40 and 440 m thick and consist of both carbonate and clastic lithologies. The ROP predictive models were developed using 14 operational parameters: TVD, weight on bit (WOB), torque, effective circulating density (ECD), drilling rotation per minute (RPM), flow rate, standpipe pressure (SPP), bit size, total RPM, D exponent, gamma ray (GR), density, neutron, caliper, and discrete lithology distribution. Training and validation of the ROP models involves data compiled from three development wells. Applying Random subsampling, the compiled dataset was split into 85 % for training and 15 % for validation and testing. The test subgroup's measured and predicted ROP mismatch was assessed using root mean square error (RMSE) and coefficient of correlation (R2). The RF, GBM, and XGBoost models provide ROP predictions versus depth with low errors. Models with cross-validation that integrate data from three wells deliver more accurate ROP predictions than datasets from single well. The input variables' influences on ROP optimization identify the optimal value ranges for 14 operating parameters that help to increase drilling speed and reduce cost.
format Article
id doaj-art-c50ae7354d474d8188b69caa7f338eaf
institution OA Journals
issn 2666-5441
language English
publishDate 2025-06-01
publisher KeAi Communications Co. Ltd.
record_format Article
series Artificial Intelligence in Geosciences
spelling doaj-art-c50ae7354d474d8188b69caa7f338eaf2025-08-20T02:22:05ZengKeAi Communications Co. Ltd.Artificial Intelligence in Geosciences2666-54412025-06-016110012110.1016/j.aiig.2025.100121Leveraging boosting machine learning for drilling rate of penetration (ROP) prediction based on drilling and petrophysical parametersRaed H. Allawi0Watheq J. Al-Mudhafar1Mohammed A. Abbas2David A. Wood3Thi-Qar Oil Company, Thi-Qar, Iraq; Petroleum Engineering College, Al-Ayen University, Thi-Qar, IraqBasrah Oil Company, Basrah, Iraq; Corresponding author.Basrah Oil Company, Basrah, IraqDWA Energy Limited, Lincoln, UKDrilling optimization requires accurate drill bit rate-of-penetration (ROP) predictions. ROP decreases drilling time and costs and increases rig productivity. This study employs random forest (RF), gradient boosting modeling (GBM), extreme gradient boosting (XGBoost), and adaptive boosting (Adaboost) models to generate ROP predictions. The models use well data from a 3200-m segment across the stratigraphic column (Dibdibba to Zubair formations) of the large West Qurna oil field in Southern Iraq, penetrating 19 formations and four oil reservoirs. The reservoir sections are between 40 and 440 m thick and consist of both carbonate and clastic lithologies. The ROP predictive models were developed using 14 operational parameters: TVD, weight on bit (WOB), torque, effective circulating density (ECD), drilling rotation per minute (RPM), flow rate, standpipe pressure (SPP), bit size, total RPM, D exponent, gamma ray (GR), density, neutron, caliper, and discrete lithology distribution. Training and validation of the ROP models involves data compiled from three development wells. Applying Random subsampling, the compiled dataset was split into 85 % for training and 15 % for validation and testing. The test subgroup's measured and predicted ROP mismatch was assessed using root mean square error (RMSE) and coefficient of correlation (R2). The RF, GBM, and XGBoost models provide ROP predictions versus depth with low errors. Models with cross-validation that integrate data from three wells deliver more accurate ROP predictions than datasets from single well. The input variables' influences on ROP optimization identify the optimal value ranges for 14 operating parameters that help to increase drilling speed and reduce cost.http://www.sciencedirect.com/science/article/pii/S2666544125000176Drilling rate of penetrationEnsemble machine learningPredictive modelsDrilling optimizationDrilling/petrophysical inputs
spellingShingle Raed H. Allawi
Watheq J. Al-Mudhafar
Mohammed A. Abbas
David A. Wood
Leveraging boosting machine learning for drilling rate of penetration (ROP) prediction based on drilling and petrophysical parameters
Artificial Intelligence in Geosciences
Drilling rate of penetration
Ensemble machine learning
Predictive models
Drilling optimization
Drilling/petrophysical inputs
title Leveraging boosting machine learning for drilling rate of penetration (ROP) prediction based on drilling and petrophysical parameters
title_full Leveraging boosting machine learning for drilling rate of penetration (ROP) prediction based on drilling and petrophysical parameters
title_fullStr Leveraging boosting machine learning for drilling rate of penetration (ROP) prediction based on drilling and petrophysical parameters
title_full_unstemmed Leveraging boosting machine learning for drilling rate of penetration (ROP) prediction based on drilling and petrophysical parameters
title_short Leveraging boosting machine learning for drilling rate of penetration (ROP) prediction based on drilling and petrophysical parameters
title_sort leveraging boosting machine learning for drilling rate of penetration rop prediction based on drilling and petrophysical parameters
topic Drilling rate of penetration
Ensemble machine learning
Predictive models
Drilling optimization
Drilling/petrophysical inputs
url http://www.sciencedirect.com/science/article/pii/S2666544125000176
work_keys_str_mv AT raedhallawi leveragingboostingmachinelearningfordrillingrateofpenetrationroppredictionbasedondrillingandpetrophysicalparameters
AT watheqjalmudhafar leveragingboostingmachinelearningfordrillingrateofpenetrationroppredictionbasedondrillingandpetrophysicalparameters
AT mohammedaabbas leveragingboostingmachinelearningfordrillingrateofpenetrationroppredictionbasedondrillingandpetrophysicalparameters
AT davidawood leveragingboostingmachinelearningfordrillingrateofpenetrationroppredictionbasedondrillingandpetrophysicalparameters