Real time formation prediction using machine learning models based on drilling parameters
Multidiszciplináris Tudományok · 13.02.2026 · 16 (1) · 26-35
DOI: 10.35925/j.multi.2026.1.3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Multidiszciplináris Tudományok, online erschienen am 13.02.2026. Verfasst von József Pap und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 1 Literaturangaben.
Abstract (Originalsprache)
Accurate knowledge of formation characteristics is critical during well development, particularly in the drilling phase, as it guides trajectory planning, casing depth selection, and the design of bit, fluid, and cementing programs. Additionally, a precise lithological sequence is essential for determining optimal perforation depths and managing production. Real-time data interpretation is increasingly valuable for enabling faster decisions and reducing operational costs. Traditionally, formation interpretation relies on manual analysis of drilling logs and shaker samples by petrophysicists or geologists. This paper introduces a machine learning-based approach to predict formation types using real-time drilling and MWD parameters, demonstrating the potential to enhance accuracy and decision-making efficiency compared to conventional methods.
Zitieren
APA
Pap, J., Szabó, N. P., Baracza, M. K., & Turzó, Z. T. (2026). Real time formation prediction using machine learning models based on drilling parameters. Multidiszciplináris Tudományok, 16(1), 26-35. https://doi.org/10.35925/j.multi.2026.1.3
Vancouver
Pap J, Szabó NP, Baracza MK, Turzó ZT. Real time formation prediction using machine learning models based on drilling parameters. Multidiszciplináris Tudományok. 2026;16(1):26-35. doi:10.35925/j.multi.2026.1.3
BibTeX
@article{Pap2026,
author = {Pap, József and Szabó, Norbert Péter and Baracza, Mátyás Krisztián and Turzó, Zoltán Tibor},
title = {Real time formation prediction using machine learning models based on drilling parameters},
journal = {Multidiszciplináris Tudományok},
year = {2026},
volume = {16},
number = {1},
pages = {26--35},
doi = {10.35925/j.multi.2026.1.3}
}
EUVIMED