paper-with-me

홈 › Papers

Deep learning for prediction of complex geology ahead of drilling

2021-04-06 · Kristian Fossum, Sergey Alyaev, Jan Tveranger, Ahmed Elsheikh

During a geosteering operation the well path is intentionally adjusted in response to the new data acquired while drilling. To achieve consistent high-quality decisions, especially when drilling in complex environments, decision support systems can help cope with high volumes of data and interpretation complexities. They can assimilate the real-time measurements into a probabilistic earth model and use the updated model for decision recommendations. Recently, machine learning (ML) techniques have enabled a wide range of methods that redistribute computational cost from on-line to off-line calculations. In this paper, we introduce two ML techniques into the geosteering decision support framework. Firstly, a complex earth model representation is generated using a Generative Adversarial Network (GAN). Secondly, a commercial extra-deep electromagnetic simulator is represented using a Forward Deep Neural Network (FDNN). The numerical experiments demonstrate that the combination of the GAN and the FDNN in an ensemble randomized maximum likelihood data assimilation scheme provides real-time estimates of complex geological uncertainty. This yields reduction of geological uncertainty ahead of the drill-bit from the measurements gathered behind and around the well bore.

📄 PDF Abstract BibTeX arXiv:2104.02550

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningGenerative Adversarial Network

Similar Papers 제목 키워드 기반

DISTINGUISH Workflow: A New Paradigm of Dynamic Well Placement Using Generative Machine Learning

2025-03-11 · Sergey Alyaev, Kristian Fossum, Hibat Errahmen Djecta, Jan Tveranger 외

The real-time process of directional changes while drilling, known as geosteering, is crucial for hydrocarbon extraction and emerging directional drilling applications such as geothermal energy, civil infrastructure, and…

Probabilistic forecasting for geosteering in fluvial successions using a generative adversarial network

2022-07-04 · Sergey Alyaev, Jan Tveranger, Kristian Fossum, Ahmed H. Elsheikh

Quantitative workflows utilizing real-time data to constrain ahead-of-bit uncertainty have the potential to improve geosteering significantly. Fast updates based on real-time data are essential when drilling in complex r…

Generative Adversarial Network

Representation Learning in Geology and GilBERT

2019-09-14 · NeurIPS Workshop Document_Intelligen 2019 12 · Zikri Bayraktar, Hedi Driss, Marie Lefranc

Geology lays at the foundation of the oil and gas industry and a good understanding of geology in each newly drilled well can make or break an exploration project with a price tag in the millions of dollars. Over the pa…

Language ModelingLanguage ModellingRepresentation LearningTAG

A Machine Learning Approach for Material Type Logging and Chemical Assaying from Autonomous Measure-While-Drilling (MWD) Data

2022-02-07 · Rami N Khushaba, Arman Melkumyan, Andrew J Hill

Understanding the structure and mineralogical composition of a region is an essential step in mining, both during exploration (before mining) and in the mining process. During exploration, sparse but high-quality data ar…

Explainable Probabilistic Machine Learning for Predicting Drilling Fluid Loss of Circulation in Marun Oil Field

2025-11-10 · Seshu Kumar Damarla, Xiuli Zhu arxiv

Lost circulation remains a major and costly challenge in drilling operations, often resulting in wellbore instability, stuck pipe, and extended non-productive time. Accurate prediction of fluid loss is therefore essentia…