Please enable JavaScript for this site to function properly.
OnePetro
  • Help
  • About us
  • Contact us
Menu
  • Home
  • Journals
  • Conferences
  • Log in / Register

Log in to your subscription

and
Advanced search Show search help
  • Full text
  • Author
  • Company/Institution
  • Publisher
  • Journal
  • Conference
Boolean operators
This OR that
This AND that
This NOT that
Must include "This" and "That"
This That
Must not include "That"
This -That
"This" is optional
This +That
Exact phrase "This That"
"This That"
Grouping
(this AND that) OR (that AND other)
Specifying fields
publisher:"Publisher Name"
author:(Smith OR Jones)

Characterization of Hydraulic Fracture Barriers in Shale Play Through Core-Log Integration: Practical Integration of Machine Learning and Geological Domain Expertise

Authors
Sebastien Perrier (TOTAL) | Arnaud Delpeint (TOTAL)
DOI
https://doi.org/10.2118/197307-MS
Document ID
SPE-197307-MS
Publisher
Society of Petroleum Engineers
Source
Abu Dhabi International Petroleum Exhibition & Conference, 11-14 November, Abu Dhabi, UAE
Publication Date
2019
Document Type
Conference Paper
Language
English
ISBN
978-1-61399-672-0
Copyright
2019. Society of Petroleum Engineers
Keywords
Electrofacies modeling, unconventional, Fracture barrier characterization, SRV optimization, machine learning
Downloads
93 in the last 30 days
93 since 2007
Show more detail
View rights & permissions
SPE Member Price: USD 9.50
SPE Non-Member Price: USD 28.00
Abstract Objectives/scope

Unconventional shale development requires continuous optimization to improve the Stimulated Rock Volume (SRV) created by hydraulic fracturing, which in turn maximizes the hydrocarbon recovery of wells. Whenever shale formations exhibit a geological heterogeneity, the distribution and magnitude of the associated geomechanical heterogeneity can significantly impact fracture propagation and result in fracture barriers or baffles that negatively impact the SRV. It is essential to adapt well targeting, hydraulic fracture design and well spacing to these heterogeneities to optimize the SRV. In this case study, such mechanically heterogeneous beds within the reservoir (resulting from geologic variability) were identified through core analysis and measurements. These heterogeneities did not have a clear interpretable log signature so it was difficult to locate, map, and assess their distribution across the play using well logs prior to applying the methods described in this paper.

Methods/procedure/process

The method discussed in this paper consists of designing a machine learning predictive model that after training on 9 cored wells, was able to predict the distribution and thickness of the geomechanical heterogeneities across the play using roughly 100 vertical wells with triple combo logs.

Beyond the classic methodology of machine learning, today considered a conventional technology, this paper presents the key steps of data processing that significantly improved prediction accuracy, and focuses on explaining why most of those steps are likely to be useful for a variety of analogous geological machine learning workflows. The workflow included: 1- an original transformation of the raw logs into engineered features based on a proper understanding of the impact of the heterogeneities on the behavior of each log; 2- a decomposition of the classification model into multiple stages, to integrate geological expertise and boost some critical algorithmic elements (in particular through class imbalance correction and bias-variance optimization); 3- an advanced management of cross-validation and exploitation of genetic searching, to optimize model robustness with a relatively small input dataset.

Results/observations/conclusions

Excellent prediction accuracy based on cross-validation was confirmed by a remarkable geological/geographical consistency of the results, once prediction results were converted into maps. The continuity of deposits and orientations of the sediment supply were in line with known basin paleogeography.

This paper defines a comprehensive approach of machine learning applied to electrofacies, and beyond the direct results of the study, it highlights how data science methods benefit from in-depth integration of geological interpretation.

As mentioned earlier, this case is also a great demonstration of the capacity of Machine Learning to identify weak signals within the data, in a case where human interpretation is limited.

File Size  839 KBNumber of Pages   10

The models were realized in Python 3, using PyCharm IDE. The key libraries were: PyQt (to create user-friendly interfaces), Matplotlib (for visualization within PyQt), sqlite (database), scikit-learn (classification models).

Hoeink, T., & Zambrano, C. (2017, August 28). Shale Discrimination with Machine Learning Methods. American Rock Mechanics Association. ARMA-2017-0769

Shi, X., Chen, H., Li, R., Yang, X., Liu, H., & Li, T. (2019, April 26). Improving Permeability and Productivity Estimation with Electrofacies Classification and Core Data Collected in Multiple Oilfields. Offshore Technology Conference. doi:10.4043/29214-MS

Maniar, H., Ryali, S., Kulkarni, M. S., & Abubakar, A. (2018, November 30). Machine-learning methods in geoscience. Society of Exploration Geophysicists. SEG-2018-2997218

Other Resources

Looking for more? 

Some of the OnePetro partner societies have developed subject- specific wikis that may help.


 


PetroWiki was initially created from the seven volume  Petroleum Engineering Handbook (PEH) published by the  Society of Petroleum Engineers (SPE).








The SEG Wiki is a useful collection of information for working geophysicists, educators, and students in the field of geophysics. The initial content has been derived from : Robert E. Sheriff's Encyclopedic Dictionary of Applied Geophysics, fourth edition.

  • Home
  • Journals
  • Conferences
  • Copyright © SPE All rights reserved
  • About us
  • Contact us
  • Help
  • Terms of use
  • Publishers
  • Content Coverage
  • Privacy
  Administration log in