Journal
ENERGY REPORTS
Volume 8, Issue -, Pages 11192-11205Publisher
ELSEVIER
DOI: 10.1016/j.egyr.2022.08.229
Keywords
Shale fundamentals; Hydraulic fracturing; Machine learning; Molecular simulation; Numerical modeling
Categories
Funding
- US Department of Energy through the Los Alamos National Laboratory
- National Nuclear Security Administration of the US Department of Energy [89233218CNA000001]
- US Department of Energy's (DOE) Office of Fossil Energy and Carbon Management, National Energy Technology Laboratory [FWP FE -406/408/409]
- Laboratory Directed Research and Development (LDRD) program, Los Alamos National Laboratory (LANL)
Ask authors/readers for more resources
This article summarizes important findings and methods regarding shale reservoirs to improve hydrocarbon extraction efficiency and minimize environmental impact. By integrating fundamental knowledge and machine learning, a pathway to enhance model prediction capabilities is outlined, and science-based workflows and platforms for pressure-drawdown optimization, real-time management, and uncertainty quantification are presented.
Hydrocarbon production from shale reservoirs is inherently inefficient and challenging since these are low permeability plays. In addition, there is a limited understanding of the fundamentals and the controlling mechanisms, further complicating how to optimize these plays. Herein, we summarize our experimental and computational efforts to reveal unconventional shale fundamentals and devise development strategies to enhance extraction efficiency with a minimal environmental footprint. Integrating these fundamentals with machine learning, we outline a pathway to improve the predictive power of our models, which enhances the forecast quality of production, thereby improving the economics of operations in unconventional reservoirs. We will discuss the main processes involving the matrix, hydraulic fractures, enhanced oil recovery, and carbon dioxide sequestration. In addition, we present science-informed workflows and platforms to optimize pressure-drawdown at a site, enable real-time reservoir management, accelerate numerical modeling and quantify uncertainty. We summarize our insights on pressure-drawdown optimization to maximize recovery while considering the lifetime of the well. In addition, we demonstrate our work on the hybridization of physics -based prediction and machine learning, whereby accurate synthetic data (combined with available site data) can enable the application of machine learning methods for rapid forecasting and optimization. Consequently, the workflow and platform are readily extendable to operations at other sites, plays and basins. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available