A Machine-Learning based generalization for an iterative Hybrid Embedded Fracture scheme
Name:
A machine learning.pdf
Size:
26.62Mb
Format:
PDF
Description:
Accepted manuscript
Embargo End Date:
2022-07-26
Type
ArticleKAUST Department
Computational Transport Phenomena LabEarth Science and Engineering Program
Physical Science and Engineering (PSE) Division
KAUST Grant Number
BAS/1/1351-01-01REP/1/2879-01
Date
2020-05-08Online Publication Date
2020-05-08Print Publication Date
2020-11Embargo End Date
2022-07-26Submitted Date
2019-10-16Permanent link to this record
http://hdl.handle.net/10754/664537
Metadata
Show full item recordAbstract
Accurately simulating fractured systems requires treating the fracture's characteristics. Here we describe a novel framework that involves coupling the Hybrid Embedded Fracture (HEF) scheme with Machine Learning. In general, HEF is more accurate than continuum medium schemes and less reliable but more efficient than the Discrete Fracture Networks (DFN) schemes. In our work, the attributes used to estimate the HEF flux exchange parameters are extracted using image processing, Machine-Learning, and Artificial-Intelligence techniques. In addition, we formulate a pure Machine-Learning classifier and Deep-Learning topology design to deal with the extraction of hierarchical fracture features from low-level to high-level based on Neural-Network layers. Computations are visualized using velocity vectors that are controlled by fractures characteristics extracted automatically from the fractured systems images. Their results provide an understanding of the flow behavior and maps of pressure distributions.Citation
Z. Amir, S., Sun, S., & F. Wheeler, M. (2020). A Machine-Learning based generalization for an iterative Hybrid Embedded Fracture scheme. Journal of Petroleum Science and Engineering, 194, 107235. doi:10.1016/j.petrol.2020.107235Sponsors
This project is funded by King Abdullah University of Science and Technology (KAUST), and KAUST (BAS/1/1351-01-01) research fund awarded through the KAUST-KFUPM Initiative (KKI) (REP/1/2879-01-01) Program.Publisher
Elsevier BVAdditional Links
https://linkinghub.elsevier.com/retrieve/pii/S092041052030320Xae974a485f413a2113503eed53cd6c53
10.1016/j.petrol.2020.107235