Data-driven prediction of rate of penetration (ROP) in drilling operations using advanced machine learning models.
Saved in:
| Title: | Data-driven prediction of rate of penetration (ROP) in drilling operations using advanced machine learning models. |
|---|---|
| Authors: | Huang, Guoli1 (AUTHOR) hgl2011@yau.edu.cn, Hamzah, Sarah Kanaan2 (AUTHOR) sarah.kanaan@alnoor.edu.iq, Patel, Pinank3 (AUTHOR) pinank.patel@marwadieducation.edu.in, Ramachandran, T.4 (AUTHOR) t.ramachandran@jainuniversity.ac.in, Shankhyan, Aman5 (AUTHOR) aman_shankhyan@outlook.com, Karthikeyan, A.6 (AUTHOR) akarthikeyan.auto@sathyabama.ac.in, Thatoi, Dhirendra Nath7 (AUTHOR) dhirendrathatoi@soa.ac.in, Gupta, Deepak8,9 (AUTHOR) deepakgupta@gehu.ac.in, AbdulAmeer, S.10,11 (AUTHOR) sabah.abdulameer@uobabylon.edu.iq, Alwan, Mariem12 (AUTHOR) mariamkh681@gmail.com, Abdulali, Zahraa Saad13 (AUTHOR) zahraa.s.abdulali@nust.edu.iq, Jawad, Mahmood Jasem14 (AUTHOR) mahmood@g.alzahu.edu.iq, Mushtaq, Hiba15 (AUTHOR) hiba.mushtaq.ahmed@gau.edu.iq, Alam, Mohammad Mahtab16 (AUTHOR) mmalam@kku.edu.sa, Abbasi, Hojjat17 (AUTHOR) hojjatabbasimeybodi@gmail.com |
| Source: | Journal of Petroleum Exploration & Production Technology. Jul2025, Vol. 15 Issue 7, p1-22. 22p. |
| Abstract: | 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. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
Be the first to leave a comment!
