Data-driven prediction of rate of penetration (ROP) in drilling operations using advanced machine learning models
Predicting the rate of penetration (ROP) is critical for optimizing drilling performance, yet it remains a complex task due to the interplay of multiple geological and operational parameters. This study comprehensively evaluates machine learning models, utilizing a real-time, high-resolution dataset from drilling operations in southeast Iraq. Among the models tested, the Random Forest algorithm demonstrated outstanding performance, achieving an R2 of 0.955, a Mean Squared Error (MSE) of 0.119, and an Average Absolute Relative Error (AARE%) of 7.683, highlighting its reliability and robustness in predicting ROP. Sensitivity analysis and SHAP (Shapley Additive Explanations) also identified fracture pressure, kinematic viscosity, and rotary speed (RPM) as the most influential parameters affecting ROP. While alternative methods like Decision Tree and AdaBoost showed signs of overfitting, the results emphasize the Random Forest model’s superiority in balancing accuracy and generalizability. This research underscores the potential of advanced machine learning techniques in enhancing drilling performance, offering significant implications for real-world applications.
Authors
- Mohammad Mahtab Alam (ORCID: https://orcid.org/0000-0003-3966-6988)
- G. L. Huang (ORCID: https://orcid.org/0000-0003-2147-6406)
- A. Karthikeyan (ORCID: https://orcid.org/0000-0002-8435-7642)
- Thiagarajan Ramachandran (ORCID: https://orcid.org/0009-0000-9259-7243)
- Shaymaa Mohammed Abdulameer
- Mahmood Jasem Jawad (ORCID: https://orcid.org/0000-0001-6542-7230)
- Sarah Kanaan Hamzah
- Hiba Mushtaq
- Deepak Gupta (ORCID: https://orcid.org/0000-0002-8542-4480)
- H. Abbasi (ORCID: https://orcid.org/0000-0003-4812-8487)
- Mariem Alwan
- Dhirendra Nath Thatoi (ORCID: https://orcid.org/0000-0002-2633-4805)
- Pinank Patel
- Aman Shankhyan
- Zahraa Saad Abdulali
Institutions
- Jain University (IN)
- University of Mosul (IQ)
- University of Babylon (IQ)
- Siksha O Anusandhan University (IN)
- Ahl Al Bayt University (IQ)
- National University of Science and Technology (ZW)
- Herat University (AF)
- Marwadi University (IN)
- Yan'an University (CN)
- University of Kerbala (IQ)
- Sathyabama Institute of Science and Technology (IN)
- Al-Farahidi University
- Graphic Era University (IN)
- Chitkara University (IN)
- King Khalid University (SA)
Publication Details
- Journal
- Journal of Petroleum Exploration and Production Technology
- Published
- 2025-06-19
- DOI
- https://doi.org/10.1007/s13202-025-02018-3
- Citations
- 2
- Primary Topic
- Drilling and Well Engineering
- Type
- article
- Field-Weighted Citation Impact
- 2.29
Funders
- King Khalid University