EUVIMEDEUVIMED entdecken
Crossref

A REVIEW OF MODERN TECHNIQUES FOR LOST CIRCULATION FORECASTING IN DRILLING OPERATIONS

Nigar Hajibayova Nigar Hajibayova, Samed Rzazade Samed Rzazade

ETM Equipment Technologies Materials · 20.05.2026 · 361

DOI: 10.36962/etm36052026-40 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ETM Equipment Technologies Materials, online erschienen am 20.05.2026. Verfasst von Nigar Hajibayova Nigar Hajibayova und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lost circulation remains one of the most operationally disruptive and economically costly challenges in drilling engineering, affecting up to 25% of all drilled wells worldwide. This review examines the evolution and current state of computational and artificial intelligence (AI) methods applied to the prediction, detection, and real-time monitoring of lost circulation events. Drawing on a systematic analysis of peer-reviewed literature published between 2017 and 2026, the paper evaluates classical machine learning (ML) algorithms, deep learning architectures, hybrid physics-data-driven models, and emerging explainability frameworks. Key methods reviewed include Random Forest, Support Vector Machines, K-Nearest Neighbors, Mixture Density Networks, Convolutional and Long Short-Term Memory neural networks, time-series autoencoders, Shapelet Transformation, LightGBM, Gaussian Process Regression, and Particle Swarm Optimization-enhanced Backpropagation networks. Critical challenges — including class imbalance in drilling datasets, integration of geological uncertainty, and deployment in real-time field environments — are identified and discussed. The review concludes with recommendations for advancing explainable, probabilistic, and self-adaptive AI models that bridge the gap between laboratory performance and operational reliability in complex subsurface conditions. Keywords: lost circulation, machine learning, deep learning, drilling operations, predictive modeling, explainable AI, real-time monitoring.

Zitieren

APA

Hajibayova, N. H. N., & Rzazade, S. R. S. (2026). A REVIEW OF MODERN TECHNIQUES FOR LOST CIRCULATION FORECASTING IN DRILLING OPERATIONS. ETM Equipment Technologies Materials, 361. https://doi.org/10.36962/etm36052026-40

Vancouver

Hajibayova NHN, Rzazade SRS. A REVIEW OF MODERN TECHNIQUES FOR LOST CIRCULATION FORECASTING IN DRILLING OPERATIONS. ETM Equipment Technologies Materials. 2026:361. doi:10.36962/etm36052026-40

BibTeX
@article{Hajibayova2026,
  author = {Hajibayova, Nigar Hajibayova Nigar and Rzazade, Samed Rzazade Samed},
  title = {A REVIEW OF MODERN TECHNIQUES FOR LOST CIRCULATION FORECASTING IN DRILLING OPERATIONS},
  journal = {ETM Equipment Technologies Materials},
  year = {2026},
  pages = {361},
  doi = {10.36962/etm36052026-40}
}
Kostenlos starten →