EUVIMEDEUVIMED entdecken
Crossref

Leveraging Data-driven Approach for Sand Production Prediction and Management in Oil and Gas Wells

Awwal Oladipupo, Isaac Johnson, Opeyemi Adebayo, Theophilus Fashanu, Kingsley Abhulimen

Petroleum Science and Engineering · 05.08.2025 · 9 (2) · 67-83

DOI: 10.11648/j.pse.20250902.13 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Petroleum Science and Engineering, online erschienen am 05.08.2025. Verfasst von Awwal Oladipupo und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sand production poses a major challenge in wells completed within sandstone reservoirs, despite their inherent benefits. It could lead to erosion of surface and subsurface equipment, well plugging from sand grain deposition and accumulation, and potential collapse of sections in horizontal wells, resulting in non-productive time, costly cleanup, and remedial or work-over operations. Various researchers have proposed strategies and models to tackle sand production and its associated problems. While these models have successfully predicted the onset of sand production, cavity stability, and rock collapse, they often struggle to accurately forecast the sand production rate due to the complexity of influencing parameters and the difficulty in fully capturing all reservoir and wellbore processes. Early prediction of sand production before drilling and field development is critical for selecting appropriate equipment and mitigation strategies. A thorough evaluation of sanding potential based on key reservoir and wellbore properties is essential to inform field development plans. In this study, a ν-support vector classification (ν-SVC) model was used to classify sanding potential, achieving 100% accuracy on the training set and 87% on the test set. For wells identified as having sanding potential, the sand occurrence was predicted using critical drawdown pressure estimated by a Random Forest model, also with 97.65% training and 88.89% test accuracy. The expected volume of sand produced over time was then predicted using an AdaBoost regression model with 99.51% training and 79.07% test accuracy. Together, these models form a predictive pipeline for proactive sand control and management. Their effectiveness was validated using publicly available field data, demonstrating strong predictive capability for real-world applications. The results indicate that these machine learning models can support completion engineers in designing timely and effective sand management strategies, minimizing production losses and operational risks.

Zitieren

APA

Oladipupo, A., Johnson, I., Adebayo, O., Fashanu, T., & Abhulimen, K. (2025). Leveraging Data-driven Approach for Sand Production Prediction and Management in Oil and Gas Wells. Petroleum Science and Engineering, 9(2), 67-83. https://doi.org/10.11648/j.pse.20250902.13

Vancouver

Oladipupo A, Johnson I, Adebayo O, Fashanu T, Abhulimen K. Leveraging Data-driven Approach for Sand Production Prediction and Management in Oil and Gas Wells. Petroleum Science and Engineering. 2025;9(2):67-83. doi:10.11648/j.pse.20250902.13

BibTeX
@article{Oladipupo2025,
  author = {Oladipupo, Awwal and Johnson, Isaac and Adebayo, Opeyemi and Fashanu, Theophilus and Abhulimen, Kingsley},
  title = {Leveraging Data-driven Approach for Sand Production Prediction and Management in Oil and Gas Wells},
  journal = {Petroleum Science and Engineering},
  year = {2025},
  volume = {9},
  number = {2},
  pages = {67--83},
  doi = {10.11648/j.pse.20250902.13}
}
Kostenlos starten →