skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Quantifying Topological Uncertainty in Fractured Systems using Graph Theory and Machine Learning

Abstract

Fractured systems are ubiquitous in natural and engineered applications as diverse as hydraulic fracturing, underground nuclear test detection, corrosive damage in materials and brittle failure of metals and ceramics. Microstructural information (fracture size, orientation, etc.) plays a key role in governing the dominant physics for these systems but can only be known statistically. Current models either ignore or idealize microscale information at these larger scales because we lack a framework that efficiently utilizes it in its entirety to predict macroscale behavior in brittle materials. Here, we propose a method that integrates computational physics, machine learning and graph theory to make a paradigm shift from computationally intensive high-fidelity models to coarse-scale graphs without loss of critical structural information. We exploit the underlying discrete structure of fracture networks in systems considering flow through fractures and fracture propagation. We demonstrate that compact graph representations require significantly fewer degrees of freedom (dof) to capture micro-fracture information and further accelerate these models with Machine Learning. Our method has been shown to improve accuracy of predictions with up to four orders of magnitude speedup.

Authors:
; ; ; ORCiD logo; ; ; ORCiD logo; ; ;
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE Laboratory Directed Research and Development (LDRD) Program
OSTI Identifier:
1462126
Alternate Identifier(s):
OSTI ID: 1467273
Report Number(s):
LA-UR-17-29575
Journal ID: ISSN 2045-2322; 11665; PII: 30117
Grant/Contract Number:  
AC52-06NA25396; 20170103DR; 20150693ECR
Resource Type:
Published Article
Journal Name:
Scientific Reports
Additional Journal Information:
Journal Name: Scientific Reports Journal Volume: 8 Journal Issue: 1; Journal ID: ISSN 2045-2322
Publisher:
Nature Publishing Group
Country of Publication:
United Kingdom
Language:
English
Subject:
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSICS; 58 GEOSCIENCES; 97 MATHEMATICS AND COMPUTING

Citation Formats

Srinivasan, Gowri, Hyman, Jeffrey D., Osthus, David A., Moore, Bryan A., O’Malley, Daniel, Karra, Satish, Rougier, Esteban, Hagberg, Aric A., Hunter, Abigail, and Viswanathan, Hari S. Quantifying Topological Uncertainty in Fractured Systems using Graph Theory and Machine Learning. United Kingdom: N. p., 2018. Web. doi:10.1038/s41598-018-30117-1.
Srinivasan, Gowri, Hyman, Jeffrey D., Osthus, David A., Moore, Bryan A., O’Malley, Daniel, Karra, Satish, Rougier, Esteban, Hagberg, Aric A., Hunter, Abigail, & Viswanathan, Hari S. Quantifying Topological Uncertainty in Fractured Systems using Graph Theory and Machine Learning. United Kingdom. doi:https://doi.org/10.1038/s41598-018-30117-1
Srinivasan, Gowri, Hyman, Jeffrey D., Osthus, David A., Moore, Bryan A., O’Malley, Daniel, Karra, Satish, Rougier, Esteban, Hagberg, Aric A., Hunter, Abigail, and Viswanathan, Hari S. Fri . "Quantifying Topological Uncertainty in Fractured Systems using Graph Theory and Machine Learning". United Kingdom. doi:https://doi.org/10.1038/s41598-018-30117-1.
@article{osti_1462126,
title = {Quantifying Topological Uncertainty in Fractured Systems using Graph Theory and Machine Learning},
author = {Srinivasan, Gowri and Hyman, Jeffrey D. and Osthus, David A. and Moore, Bryan A. and O’Malley, Daniel and Karra, Satish and Rougier, Esteban and Hagberg, Aric A. and Hunter, Abigail and Viswanathan, Hari S.},
abstractNote = {Fractured systems are ubiquitous in natural and engineered applications as diverse as hydraulic fracturing, underground nuclear test detection, corrosive damage in materials and brittle failure of metals and ceramics. Microstructural information (fracture size, orientation, etc.) plays a key role in governing the dominant physics for these systems but can only be known statistically. Current models either ignore or idealize microscale information at these larger scales because we lack a framework that efficiently utilizes it in its entirety to predict macroscale behavior in brittle materials. Here, we propose a method that integrates computational physics, machine learning and graph theory to make a paradigm shift from computationally intensive high-fidelity models to coarse-scale graphs without loss of critical structural information. We exploit the underlying discrete structure of fracture networks in systems considering flow through fractures and fracture propagation. We demonstrate that compact graph representations require significantly fewer degrees of freedom (dof) to capture micro-fracture information and further accelerate these models with Machine Learning. Our method has been shown to improve accuracy of predictions with up to four orders of magnitude speedup.},
doi = {10.1038/s41598-018-30117-1},
journal = {Scientific Reports},
number = 1,
volume = 8,
place = {United Kingdom},
year = {2018},
month = {8}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
DOI: https://doi.org/10.1038/s41598-018-30117-1

Citation Metrics:
Cited by: 4 works
Citation information provided by
Web of Science

Figures / Tables:

Figure 1 Figure 1: A modest sized fracture network with 459 fractures. (a) The original Discrete Fracture Network (DFN) model; (b) the 2-core representation of the DFN and (c) the graph corresponding to the shortest path between inflow and outflow boundaries. Insets show the DFN models corresponding to the reduced graph representations.

Save / Share:

Works referenced in this record:

Network structure and minimum degree
journal, September 1983


Effective permeability of fractured porous media with power-law distribution of fracture sizes
journal, September 2007


Curve Fitting and Optimal Design for Prediction
journal, September 1978


Computer Model Calibration Using High-Dimensional Output
journal, June 2008

  • Higdon, Dave; Gattiker, James; Williams, Brian
  • Journal of the American Statistical Association, Vol. 103, Issue 482
  • DOI: 10.1198/016214507000000888

Machine learning for graph-based representations of three-dimensional discrete fracture networks
journal, January 2018

  • Valera, Manuel; Guo, Zhengyang; Kelly, Priscilla
  • Computational Geosciences, Vol. 22, Issue 3
  • DOI: 10.1007/s10596-018-9720-1

Bayesian calibration of computer models
journal, August 2001

  • Kennedy, Marc C.; O'Hagan, Anthony
  • Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 63, Issue 3
  • DOI: 10.1111/1467-9868.00294

A quasi steady state method for solving transient Darcy flow in complex 3D fractured networks
journal, January 2012


Learning on Graphs for Predictions of Fracture Propagation, Flow and Transport
conference, May 2017

  • Djidjev, Hristo; O'Malley, Daniel; Viswanathan, Hari
  • 2017 IEEE International Parallel and Distributed Processing Symposium: Workshops (IPDPSW), 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)
  • DOI: 10.1109/IPDPSW.2017.11

Evaluating the effect of internal aperture variability on transport in kilometer scale discrete fracture networks
journal, August 2016


Predictions of first passage times in sparse discrete fracture networks using graph-based reductions
journal, July 2017


Shale gas and non-aqueous fracturing fluids: Opportunities and challenges for supercritical CO2
journal, June 2015


dfnWorks: A discrete fracture network framework for modeling subsurface flow and transport
journal, November 2015


Trends, prospects and challenges in quantifying flow and transport through fractured rocks
journal, February 2005


Trace gas emissions on geological faults as indicators of underground nuclear testing
journal, August 1996

  • Carrigan, C. R.; Heinle, R. A.; Hudson, G. B.
  • Nature, Vol. 382, Issue 6591
  • DOI: 10.1038/382528a0

Conforming Delaunay Triangulation of Stochastically Generated Three Dimensional Discrete Fracture Networks: A Feature Rejection Algorithm for Meshing Strategy
journal, January 2014

  • Hyman, Jeffrey D.; Gable, Carl W.; Painter, Scott L.
  • SIAM Journal on Scientific Computing, Vol. 36, Issue 4
  • DOI: 10.1137/130942541

Design and Analysis of Computer Experiments
journal, November 1989

  • Sacks, Jerome; Welch, William J.; Mitchell, Toby J.
  • Statistical Science, Vol. 4, Issue 4
  • DOI: 10.1214/ss/1177012413

Scaling of fracture systems in geological media
journal, August 2001

  • Bonnet, E.; Bour, O.; Odling, N. E.
  • Reviews of Geophysics, Vol. 39, Issue 3
  • DOI: 10.1029/1999RG000074

Ranking in interconnected multilayer networks reveals versatile nodes
journal, April 2015

  • De Domenico, Manlio; Solé-Ribalta, Albert; Omodei, Elisa
  • Nature Communications, Vol. 6, Issue 1
  • DOI: 10.1038/ncomms7868

Approaching a universal scaling relationship between fracture stiffness and fluid flow
journal, February 2016

  • Pyrak-Nolte, Laura J.; Nolte, David D.
  • Nature Communications, Vol. 7, Issue 1
  • DOI: 10.1038/ncomms10663

Where Does Water Go During Hydraulic Fracturing?: D. O'Malley et al. Groundwater xx, no. x: xx-xx
journal, October 2015

  • O'Malley, D.; Karra, S.; Currier, R. P.
  • Groundwater, Vol. 54, Issue 4
  • DOI: 10.1111/gwat.12380

Modeling flow and transport in fracture networks using graphs
journal, March 2018


    Works referencing / citing this record:

    Robust system size reduction of discrete fracture networks: a multi-fidelity method that preserves transport characteristics
    journal, September 2018

    • Srinivasan, Shriram; Hyman, Jeffrey; Karra, Satish
    • Computational Geosciences, Vol. 22, Issue 6
    • DOI: 10.1007/s10596-018-9770-4

    Model reduction for fractured porous media: a machine learning approach for identifying main flow pathways
    journal, March 2019

    • Srinivasan, Shriram; Karra, Satish; Hyman, Jeffrey
    • Computational Geosciences, Vol. 23, Issue 3
    • DOI: 10.1007/s10596-019-9811-7

    Emergence of Stable Laws for First Passage Times in Three-Dimensional Random Fracture Networks
    journal, December 2019


      Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.