Predicting rate of penetration (ROP) with machine learning models: A physics-validated comparative case study of Gradient Boosting Regressor (GBR), Random Forest (RF), and K-Nearest Neighbours (KNN)
- 1Department of Chemical and Petroleum Engineering, United Arab Emirates University, Al Ain, United Arab Emirates
- 2Hildebrand Austin Department of Petroleum and Geosystems Engineering, The University of Texas at Austin, Austin, Texas, United States of America
- 3Chemical and Process Engineering, Faculty of Engineering, University of Strathclyde Bahrain, Kingdom of Bahrain
Abstract
A successful drilling operation plays a vital role in the profitability of exploration and production of hydrocarbon reserves. However, these operations can come with high drilling rig rental costs. Reliable predictions of Rate of Penetration (ROP) can avoid unnecessary drilling equipment and rig rental expenses. In this study, Gradient Boosting Regressor, Random Forest, and K-Nearest Neighbours were developed to predict rate of penetration based on drilling operational data. The machine learning models were benchmarked with established empirical models, such as the Bingham and Bourgoyne and Young models, which are typically used to predict the rate of penetration. All machine learning models achieved, coefficient of determination (R2) > 0.93 and Average Absolute Percentage Error (AAPE) < 3% on the test dataset. Random Forest under Scenario 1 was identified as the most physically consistent model, attaining strong predictive performance with R2 = 0.9494 & AAPE = 1.96%, satisfying both the Weight on Bit (WOB) flounder point, and rotary speed optimum criteria used within the industry. These results support the practical use of machine learning-based ROP prediction as a reliable tool for real-time optimization of drilling parameters, offering a pathway to reduce non-productive time and rig costs while preserving the physical interpretability that drilling engineers require for field decision making.
Related
- Predicting Blood–Brain Barrier Permeability from Experimental Data: An Interpretable and Externally Validated Machine Learning Framework
- Comparative Analysis of Cohesive Laws for Predicting Stress Fields in Perforated Fiber Metal Laminates
- Cross-and-Capture: A Dual-Ligand PAMAM Nanocarrier for Sequential BBB Penetration and Ischemic Lesion Retention of Breviscapine
- Interfacial Penetration Drives Anomalous Domain Spacing in Strongly Segregated Linear-Bottlebrush Copolymers.
- Shaping Tumor Targeting: How Nanoparticle Morphology Influences Penetration and Accumulation in 3D Breast Cancer Models
BibTeX
@article{magzoub2026predicting,
title = {{Predicting rate of penetration (ROP) with machine learning models: A physics-validated comparative case study of Gradient Boosting Regressor (GBR), Random Forest (RF), and K-Nearest Neighbours (KNN)}},
author = {Musaab Magzoub and Noora Al Mansoori and Mohammed Abdalla Ayoub Mohammed and Almostafa Alhadi and Kaushik Sivaramakrishnan and Munawar Shaik and Abu Bakar Adni},
journal = {PLOS One},
year = {2026},
month = nov,
doi = {10.1371/journal.pone.0360046},
url = {https://doi.org/10.1371/journal.pone.0360046},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Predicting rate of penetration (ROP) with machine learning models: A physics-validated comparative case study of Gradient Boosting Regressor (GBR), Random Forest (RF), and K-Nearest Neighbours (KNN)
AU - Musaab Magzoub
AU - Noora Al Mansoori
AU - Mohammed Abdalla Ayoub Mohammed
AU - Almostafa Alhadi
AU - Kaushik Sivaramakrishnan
AU - Munawar Shaik
AU - Abu Bakar Adni
PY - 2026
DA - 2026/11/06
JO - PLOS One
DO - 10.1371/journal.pone.0360046
UR - https://doi.org/10.1371/journal.pone.0360046
AB - A successful drilling operation plays a vital role in the profitability of exploration and production of hydrocarbon reserves. However, these operations can come with high drilling rig rental costs. Reliable predictions of Rate of Penetration (ROP) can avoid unnecessary drilling equipment and rig rental expenses. In this study, Gradient Boosting Regressor, Random Forest, and K-Nearest Neighbours were developed to predict rate of penetration based on drilling operational data. The machine learning models were benchmarked with established empirical models, such as the Bingham and Bourgoyne and Young models, which are typically used to predict the rate of penetration. All machine learning models achieved, coefficient of determination (R2) > 0.93 and Average Absolute Percentage Error (AAPE) < 3% on the test dataset. Random Forest under Scenario 1 was identified as the most physically consistent model, attaining strong predictive performance with R2 = 0.9494 & AAPE = 1.96%, satisfying both the Weight on Bit (WOB) flounder point, and rotary speed optimum criteria used within the industry. These results support the practical use of machine learning-based ROP prediction as a reliable tool for real-time optimization of drilling parameters, offering a pathway to reduce non-productive time and rig costs while preserving the physical interpretability that drilling engineers require for field decision making.
SN - 1932-6203
ER -