Machine learning for graph-based representations of three-dimensional discrete fracture networks
Abstract
Structural and topological information play a key role in modeling flow and transport through fractured rock in the subsurface. Discrete fracture network (DFN) computational suites such as dfnWorks (Hyman et al. Comput. Geosci. 84, 10–19 2015) are designed to simulate flow and transport in such porous media. Flow and transport calculations reveal that a small backbone of fractures exists, where most flow and transport occurs. Restricting the flowing fracture network to this backbone provides a significant reduction in the network’s effective size. However, the particle-tracking simulations needed to determine this reduction are computationally intensive. Such methods may be impractical for large systems or for robust uncertainty quantification of fracture networks, where thousands of forward simulations are needed to bound system behavior. In this paper, we develop an alternative network reduction approach to characterizing transport in DFNs, by combining graph theoretical and machine learning methods. We consider a graph representation where nodes signify fractures and edges denote their intersections. Using random forest and support vector machines, we rapidly identify a subnetwork that captures the flow patterns of the full DFN, based primarily on node centrality features in the graph. Our supervised learning techniques train on particle-tracking backbone paths found by dfnWorks,more »
- Authors:
-
- San Diego State Univ., San Diego, CA (United States). Computational Science Research Center; Claremont Graduate Univ., Claremont, CA (United States). Inst. of Mathematical Sciences
- C2FO, Leawood, KS (United States). Data & Decision Sciences
- an Diego State Univ., San Diego, CA (United States). Computational Science Research Center; Claremont Graduate Univ., Claremont, CA (United States). Inst. of Mathematical Sciences
- Claremont Graduate Univ., Claremont, CA (United States). Inst. of Mathematical Sciences
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- Publication Date:
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE Laboratory Directed Research and Development (LDRD) Program
- OSTI Identifier:
- 1479976
- Report Number(s):
- LA-UR-17-24300
Journal ID: ISSN 1420-0597
- Grant/Contract Number:
- AC52-06NA25396
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Computational Geosciences
- Additional Journal Information:
- Journal Volume: 22; Journal Issue: 3; Journal ID: ISSN 1420-0597
- Publisher:
- Springer
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; Computer Science; Earth Sciences; Mathematics; Machine learning; Discrete fracture networks; Support vector machines; Random forest Centrality
Citation Formats
Valera, Manuel, Guo, Zhengyang, Kelly, Priscilla, Matz, Sean, Cantu, Vito Adrian, Percus, Allon G., Hyman, Jeffrey D., Srinivasan, Gowri, and Viswanathan, Hari S. Machine learning for graph-based representations of three-dimensional discrete fracture networks. United States: N. p., 2018.
Web. doi:10.1007/s10596-018-9720-1.
Valera, Manuel, Guo, Zhengyang, Kelly, Priscilla, Matz, Sean, Cantu, Vito Adrian, Percus, Allon G., Hyman, Jeffrey D., Srinivasan, Gowri, & Viswanathan, Hari S. Machine learning for graph-based representations of three-dimensional discrete fracture networks. United States. https://doi.org/10.1007/s10596-018-9720-1
Valera, Manuel, Guo, Zhengyang, Kelly, Priscilla, Matz, Sean, Cantu, Vito Adrian, Percus, Allon G., Hyman, Jeffrey D., Srinivasan, Gowri, and Viswanathan, Hari S. Wed .
"Machine learning for graph-based representations of three-dimensional discrete fracture networks". United States. https://doi.org/10.1007/s10596-018-9720-1. https://www.osti.gov/servlets/purl/1479976.
@article{osti_1479976,
title = {Machine learning for graph-based representations of three-dimensional discrete fracture networks},
author = {Valera, Manuel and Guo, Zhengyang and Kelly, Priscilla and Matz, Sean and Cantu, Vito Adrian and Percus, Allon G. and Hyman, Jeffrey D. and Srinivasan, Gowri and Viswanathan, Hari S.},
abstractNote = {Structural and topological information play a key role in modeling flow and transport through fractured rock in the subsurface. Discrete fracture network (DFN) computational suites such as dfnWorks (Hyman et al. Comput. Geosci. 84, 10–19 2015) are designed to simulate flow and transport in such porous media. Flow and transport calculations reveal that a small backbone of fractures exists, where most flow and transport occurs. Restricting the flowing fracture network to this backbone provides a significant reduction in the network’s effective size. However, the particle-tracking simulations needed to determine this reduction are computationally intensive. Such methods may be impractical for large systems or for robust uncertainty quantification of fracture networks, where thousands of forward simulations are needed to bound system behavior. In this paper, we develop an alternative network reduction approach to characterizing transport in DFNs, by combining graph theoretical and machine learning methods. We consider a graph representation where nodes signify fractures and edges denote their intersections. Using random forest and support vector machines, we rapidly identify a subnetwork that captures the flow patterns of the full DFN, based primarily on node centrality features in the graph. Our supervised learning techniques train on particle-tracking backbone paths found by dfnWorks, but run in negligible time compared to those simulations. In conclusion, we find that our predictions can reduce the network to approximately 20% of its original size, while still generating breakthrough curves consistent with those of the original network.},
doi = {10.1007/s10596-018-9720-1},
journal = {Computational Geosciences},
number = 3,
volume = 22,
place = {United States},
year = {Wed Jan 24 00:00:00 EST 2018},
month = {Wed Jan 24 00:00:00 EST 2018}
}
Web of Science
Works referenced in this record:
A training algorithm for optimal margin classifiers
conference, January 1992
- Boser, Bernhard E.; Guyon, Isabelle M.; Vapnik, Vladimir N.
- Proceedings of the fifth annual workshop on Computational learning theory - COLT '92
Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling
journal, August 2015
- Goetz, J. N.; Brenning, A.; Petschko, H.
- Computers & Geosciences, Vol. 81
A particle tracking transport method for the simulation of resident and flux-averaged concentration of solute plumes in groundwater models
journal, May 2010
- Robinson, Bruce A.; Dash, Zora V.; Srinivasan, Gowri
- Computational Geosciences, Vol. 14, Issue 4
Fracture networks in sea ice
journal, April 2014
- Vevatne, Jonas Nesland; Rimstad, Eivind; Hope, Sigmund Mongstad
- Frontiers in Physics, Vol. 2
Topology of fracture networks
journal, January 2013
- Andresen, Christian André; Hansen, Alex; Le Goc, Romain
- Frontiers in Physics, Vol. 1
Topological impact of constrained fracture growth
journal, September 2015
- Hope, Sigmund Mongstad; Davy, Philippe; Maillot, Julien
- Frontiers in Physics, Vol. 3
Influence of injection mode on transport properties in kilometer-scale three-dimensional discrete fracture networks: INFLUENCE OF INJECTION MODE IN 3-D DFNs
journal, September 2015
- Hyman, J. D.; Painter, S. L.; Viswanathan, H.
- Water Resources Research, Vol. 51, Issue 9
PFLOTRAN User Manual: A Massively Parallel Reactive Flow and Transport Model for Describing Surface and Subsurface Processes
report, January 2015
- Lichtner, Peter; Hammond, Glenn; Lu, Chuan
A descriptive study of fracture networks in rocks using complex network metrics
journal, March 2016
- Santiago, Elizabeth; Velasco-Hernández, Jorge X.; Romero-Salcedo, Manuel
- Computers & Geosciences, Vol. 88
Particle tracking approach for transport in three-dimensional discrete fracture networks: Particle tracking in 3-D DFNs
journal, September 2015
- Makedonska, Nataliia; Painter, Scott L.; Bui, Quan M.
- Computational Geosciences, Vol. 19, Issue 5
Upscaling discrete fracture network simulations: An alternative to continuum transport models: UPSCALING FRACTURE NETWORK SIMULATIONS
journal, February 2005
- Painter, S.; Cvetkovic, V.
- Water Resources Research, Vol. 41, Issue 2
A measure of betweenness centrality based on random walks
journal, January 2005
- Newman, M. E. J.
- Social Networks, Vol. 27, Issue 1
Validity of Cubic Law for fluid flow in a deformable rock fracture
journal, December 1980
- Witherspoon, P. A.; Wang, J. S. Y.; Iwai, K.
- Water Resources Research, Vol. 16, Issue 6
Fracture size and transmissivity correlations: Implications for transport simulations in sparse three-dimensional discrete fracture networks following a truncated power law distribution of fracture size: FRACTURE SIZE AND TRANSMISSIVITY CORRELATIONS
journal, August 2016
- Hyman, J. D.; Aldrich, G.; Viswanathan, H.
- Water Resources Research, Vol. 52, Issue 8
A Large-Scale Flow and Tracer Experiment in Granite: 2. Results and Interpretation
journal, December 1991
- Abelin, Harald; Birgersson, Lars; Moreno, Luis
- Water Resources Research, Vol. 27, Issue 12
dfnWorks: A discrete fracture network framework for modeling subsurface flow and transport
journal, November 2015
- Hyman, Jeffrey D.; Karra, Satish; Makedonska, Nataliia
- Computers & Geosciences, Vol. 84
Connectivity, permeability, and channeling in randomly distributed and kinematically defined discrete fracture network models: PERMEABILITY OF DISCRETE FRACTURE NETWORK
journal, November 2016
- Maillot, J.; Davy, P.; Le Goc, R.
- Water Resources Research, Vol. 52, Issue 11
Trends, prospects and challenges in quantifying flow and transport through fractured rocks
journal, February 2005
- Neuman, Shlomo P.
- Hydrogeology Journal, Vol. 13, Issue 1
Support-vector networks
journal, September 1995
- Cortes, Corinna; Vapnik, Vladimir
- Machine Learning, Vol. 20, Issue 3
Random walk particle tracking simulations of non-Fickian transport in heterogeneous media
journal, June 2010
- Srinivasan, G.; Tartakovsky, D. M.; Dentz, M.
- Journal of Computational Physics, Vol. 229, Issue 11
A methodology for the characterization of flow conductivity through the identification of communities in samples of fractured rocks
journal, February 2014
- Santiago, Elizabeth; Velasco-Hernández, Jorge X.; Romero-Salcedo, Manuel
- Expert Systems with Applications, Vol. 41, Issue 3
Understanding hydraulic fracturing: a multi-scale problem
journal, October 2016
- Hyman, J. D.; Jiménez-Martínez, J.; Viswanathan, H. S.
- Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 374, Issue 2078
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
Power-law velocity distributions in fracture networks: Numerical evidence and implications for tracer transport: POWER-LAW VELOCITY DISTRIBUTIONS IN FRACTURE NETWORKS
journal, July 2002
- Painter, Scott; Cvetkovic, Vladimir; Selroos, Jan-Olof
- Geophysical Research Letters, Vol. 29, Issue 14
A Set of Measures of Centrality Based on Betweenness
journal, March 1977
- Freeman, Linton C.
- Sociometry, Vol. 40, Issue 1
An Introduction to Statistical Learning
book, January 2013
- James, Gareth; Witten, Daniela; Hastie, Trevor
- Springer Texts in Statistics
Pathline tracing on fully unstructured control-volume grids
journal, July 2012
- Painter, S. L.; Gable, C. W.; Kelkar, S.
- Computational Geosciences, Vol. 16, Issue 4
Influence of fracture scale heterogeneity on the flow properties of three-dimensional discrete fracture networks (DFN): 3D FRACTURE NETWORK PERMEABILITY
journal, November 2012
- de Dreuzy, J. -R.; Méheust, Y.; Pichot, G.
- Journal of Geophysical Research: Solid Earth, Vol. 117, Issue B11
Numerical and analytical modeling of advective travel times in realistic three-dimensional fracture networks: MODELING OF ADVECTIVE TRAVEL TIMES
journal, February 2011
- Frampton, A.; Cvetkovic, V.
- Water Resources Research, Vol. 47, Issue 2
The state of the art in monitoring and verification—Ten years on
journal, September 2015
- Jenkins, Charles; Chadwick, Andy; Hovorka, Susan D.
- International Journal of Greenhouse Gas Control, Vol. 40
Radionuclide Transport in Fast Channels in Crystalline Rock
journal, August 1986
- Rasmuson, Anders; Neretnieks, Ivars
- Water Resources Research, Vol. 22, Issue 8
The random subspace method for constructing decision forests
journal, January 1998
- Tin Kam Ho,
- IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, Issue 8
Analysis and Visualization of Discrete Fracture Networks Using a Flow Topology Graph
journal, August 2017
- Aldrich, Garrett; Hyman, Jeffrey D.; Karra, Satish
- IEEE Transactions on Visualization and Computer Graphics, Vol. 23, Issue 8
miRNALoc: predicting miRNA subcellular localizations based on principal component scores of physico-chemical properties and pseudo compositions of di-nucleotides
journal, September 2020
- Meher, Prabina Kumar; Satpathy, Subhrajit; Rao, Atmakuri Ramakrishna
- Scientific Reports, Vol. 10, Issue 1
The state of the art in monitoring and verification—Ten years on
text, January 2015
- Jenkins, C.; Chadwick, A.; Hovorka, Susan D.
- The University of Texas at Austin
dfnWorks: A discrete fracture network framework for modeling subsurface flow and transport
journal, November 2015
- Hyman, Jeffrey D.; Karra, Satish; Makedonska, Nataliia
- Computers & Geosciences, Vol. 84
The state of the art in monitoring and verification—Ten years on
journal, September 2015
- Jenkins, Charles; Chadwick, Andy; Hovorka, Susan D.
- International Journal of Greenhouse Gas Control, Vol. 40
Random walk particle tracking simulations of non-Fickian transport in heterogeneous media
journal, June 2010
- Srinivasan, G.; Tartakovsky, D. M.; Dentz, M.
- Journal of Computational Physics, Vol. 229, Issue 11
Sequential geophysical and flow inversion to characterize fracture networks in subsurface systems
text, January 2016
- Mudunuru, M. K.; Karra, S.; Makedonska, N.
- arXiv
Works referencing / citing this record:
Network analysis of particles and grains
journal, April 2018
- Papadopoulos, Lia; Porter, Mason A.; Daniels, Karen E.
- Journal of Complex Networks, Vol. 6, Issue 4
Machine learning for data-driven discovery in solid Earth geoscience
journal, March 2019
- Bergen, Karianne J.; Johnson, Paul A.; de Hoop, Maarten V.
- Science, Vol. 363, Issue 6433
Prediction of Rock Compressive Strength Using Machine Learning Algorithms Based on Spectrum Analysis of Geological Hammer
journal, July 2018
- Ren, Qiubing; Wang, Gang; Li, Mingchao
- Geotechnical and Geological Engineering, Vol. 37, Issue 1
Quantifying Topological Uncertainty in Fractured Systems using Graph Theory and Machine Learning
journal, August 2018
- Srinivasan, Gowri; Hyman, Jeffrey D.; Osthus, David A.
- Scientific Reports, Vol. 8, Issue 1
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
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
New Opportunities and Challenges of Geo-ICT Convergence Technology: GeoCPS and GeoAI
journal, August 2019
- Ryu, Dongwoo
- Journal of the Korean Society of Mineral and Energy Resources Engineers, Vol. 56, Issue 4