Review of detection, prediction and treatment of fluid loss events.

Amish, Mohamed; Khodja, Mohamed

Abstract

Lost circulation has the potential to cause formation damage, wellbore instability and a blowout. Many methods have been introduced, but there is no industry-wide solution available to predict lost circulation due to some constraints in the field. It is essential to predict the onset of loss of circulation to mitigate its effects, reduce operational costs and prevent the risk to people and the environment. A wide range of methods, techniques and treatments, including environmentally friendly materials, are reviewed to mitigate the loss of circulation. Conventional and intelligent methods are presented for detecting and predicting lost circulation events. Using oil field data such as fluid parameters, drilling parameters and geological parameters, artificial intelligence can predict fluid losses using supervised machine learning (ML). Several ML models for predicting fluid loss are reviewed in this paper, and other possible applications are discussed. The sample size, field location, input and output features, performance and ML algorithms are extracted. The paper provides an inclusive presentation of the ML workflow for fluid loss prediction and is anticipated to help and support both drilling engineering practitioners and researchers in the resolution of drilling challenges, with recommendations for future development.

Citation

AMISH, M. and KHODJA, M. 2025. Review of detection, prediction and treatment of fluid loss events. Arabian journal of geosciences [online], 18(1), article number 8. Available from: https://doi.org/10.1007/s12517-024-12142-9

• Journal Article Type: Review
• Acceptance Date: Nov 14, 2024
• Online Publication Date: Dec 9, 2024
• Publication Date: Jan 31, 2025
• Deposit Date: Dec 9, 2024
• Publicly Available Date: Dec 9, 2024
• Journal: Arabian journal of geosciences
• Print ISSN: 1866-7511
• Electronic ISSN: 1866-7538
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Volume: 18
• Issue: 1
• Article Number: 8
• DOI: https://doi.org/10.1007/s12517-024-12142-9
• Keywords: Environmental engineering; Pipelines; Wellbores; Oil and gas engineering; Machine learning
• Public URL: https://rgu-repository.worktribe.com/output/2584733