"

This service is provided byAnhui Southland Cold & Heat Integrated Energy Co.(Click for details)title sponsor

The company's main business scope is: regional centralized cooling and heating intelligent operation, energy Internet, building and industrial energy saving, data center cooling and emergency cold source construction, IC clean room, operating room laboratory purification engineering, central air-conditioning engineering, intelligent engineering, information technology system integration and other high-tech services.



Authors | Xu Liang a b c d, Tianfu Xu a b c, Jingyi Chen a b c, Zhenjiao Jiang a b c

Title | A deep-learning based model for fracture network characterization constrained by induced micro-seismicity and tracer test data in enhanced geothermal system

Source | Renewable Energy

Edit | Geothermal Core (add micro-signal: geothermalAI, can get related information)

→This is the Geothermal Energy Online AIgeothermal coreEditor's first1article


01

full text guide



Recently, researchers have proposed a new interpretive framework that aims to explicitly characterize the complex rift network in enhanced geothermal systems (EGS) through hydraulic stimulation. The framework is based on induced microseismic activity data, combined with hydraulic stimulation and tracer test monitoring data, and inverted rift parameters by the Long Short-Term Memory (LSTM)-Multi-Objective Harris Hawk Optimization (MOHHO) algorithm. The optimized LSTM model can be used as a substitute for the numerical models of hydraulic stimulation and tracer testing to effectively predict the monitoring data and provide constraints for the fracture network inversion. In addition, the prediction accuracy can be further improved by expanding the training dataset and employing other deep learning models. The study also compares and analyzes microseismic monitoring (MSM) models and stochastic (Stoch) models, emphasizing the importance of spatial and temporal characteristics of induced microseismic activity for reservoir characterization. In addition, the fracture network serves as a preferential channel for fracturing fluid flow and directly controls the injection wellhead pressure under protocol-specific conditions. Due to the complex interactions between hydraulic and natural fractures, the formation of hydraulically stimulated fracture networks is jointly determined by fracture distribution, size, and hydraulic openings. The reservoir characterization method builds a core framework that can be populated according to different process models, such as electromagnetic surveys and thermal extraction tests. The method has been applied to the Habanero EGS in Australia and validated with field observations from hydraulic stimulation and tracer testing. This method has low monitoring data requirements and high inversion efficiency. Characterization of the rift network is the basis for the development of the EGS project. Based on the inverted fracture network, the production performance can be estimated and well placement and production strategies can be further discussed and optimized.



02

HIGHLIGHT Pictures


Fig. 1 . Workflow of the fracture network characterization method for hydraulically stimulated EGS reservoirs.

Fig. 2 . Location and satellite view of the Habanero EGS with locations of four EGS wells (a), illustration of the conceptual model with the discretized fractured reservoir, and the vertical distribution of the maximum horizontal stress (b).

Fig. 3 . Injection protocol (a), and injection wellhead pressure (b) during the hydraulic stimulation at H04 in 2012.

Fig. 4 . The spatio-temporal distribution of the induced micro-seismicity during the stimulation at H01 in 2003 (a) and at H04 in 2012 (b), and the calculated hydraulic diffusivity (c) [ 33 ].

Fig. 5 . Tracer breakthrough curve during the inter-well tracer test in 2012 [ 24 ].

Fig. 6 . Data sets of the fracture network parameters (a), and the modeling results of WP during the hydraulic stimulation (b), TC (c) and ΔP (d) during the tracer test for the LSTM models training and testing.

Fig. 7 . Comparison of the modeling results and LSTM model predictions of the WH (a) and TC (b) at the minimum, mean, and maximum level of errors, and ΔP (c) in the testing sets.

Fig. 8 . Recorded and selected Pareto optimal solutions of the MSM model parameters (a), and comparison between monitoring data and modeling results of the WP during the hydraulic stimulation (b) and the TC during the tracer test (c).

Fig. 9 . Inversed Stoch model (a) and MSM model (b) after the hydraulic stimulation.

Fig. 10 . Comparison of the solute transport processes in the inversed Stoch model (a) and MSM model (b).

Disclaimer: This article is for academic communication and dissemination only, and does not constitute investment advice

——-

References:

[1]
M.A. Grant, P.F. Bixley
Well Stimulation and Engineered Geothermal Systems
Elsevier Inc. (2011)
Google Scholar

[2]
M. Soltani, F. Moradi Kashkooli, M. Souri, B. Rafiei, M. Jabarifar, K. Gharali, J.S. Nathwani
Environmental, economic, and social impacts of geothermal energy systems
Renew. Sustain. Energy Rev., 140 (2021), Article 110750
View PDFView articleView in ScopusGoogle Scholar

[3]
MIT
The Future of Geothermal Energy
Massachusetts Institute of Technology, Cambridge, MA (2006)
Report INL/EXT-06-11746, ISBN: 0-615-13438-6
Google Scholar

[4]
Baria Roy, Baumgärtner Jörg, Rummel Fritz, Robert
HDR/HWR Reservoirs: Concepts, Understanding and Creation
Geothermics (1999)
Google Scholar

[5]
A. Aghahosseini, C. Breyer
From hot rock to useful energy: a global estimate of enhanced geothermal systems potential
Appl. Energy, 279 (2020), Article 115769
View PDFView articleView in ScopusGoogle Scholar

[6]
L. Xie, K. Min
Initiation and propagation of fracture shearing during hydraulic stimulation in enhanced geothermal system
Geothermics, 59 (2016), pp. 107-120
View PDFView articleView in ScopusGoogle Scholar

[7]
F.H. Cornet
The engineering of safe hydraulic stimulations for EGS development in hot crystalline rock masses
Geomech. Energy Environ., 26 (2021), Article 100151
View PDFView articleView in ScopusGoogle Scholar

[8]
A. Pollack, T. Mukerji
Accounting for subsurface uncertainty in enhanced geothermal systems to make more robust techno-economic decisions
Appl. Energy, 254 (2019), Article 113666
View PDFView articleView in ScopusGoogle Scholar

[9]
Y. Shi, X. Song, G. Wang, J. Li, L. Geng, X. Li
Numerical study on heat extraction performance of a multilateral-well enhanced geothermal system considering complex hydraulic and natural fractures
Renew. Energy, 141 (2019), pp. 950-963
View PDFView articleView in ScopusGoogle Scholar

[10]
X. Gao, Y. Zhang, Y. Huang, Y. Ma, Y. Zhao, Q. Liu
Study on heat extraction considering the number and orientation of multilateral wells in a complex fractured geothermal reservoir
Renew. Energy, 177 (2021), pp. 833-852
View PDFView articleView in ScopusGoogle Scholar

[11]
G. Liu, C. Zhou, Z. Rao, S. Liao
Impacts of fracture network geometries on numerical simulation and performance prediction of enhanced geothermal systems
Renew. Energy, 171 (2021), pp. 492-504
View PDFView articleView in ScopusGoogle Scholar

[12]
A. Pollack, R. Horne, T. Mukerji
What are the challenges in developing enhanced geothermal systems (EGS)? Observations from 64 EGS sites
Proceedings World Geothermal Congress, Reykjavik, Iceland (2020)
Google Scholar

[13]
M. AbuAisha, B. Loret, D. Eaton
Enhanced geothermal systems (EGS): hydraulic fracturing in a thermo-poroelastic framework
J. Petrol. Sci. Eng., 146 (2016), pp. 1179-1191
View PDFView articleView in ScopusGoogle Scholar

[14]
Z. Wu, C. Cui, P. Jia, Z. Wang, Y. Sui
Advances and Challenges in Hydraulic Fracturing of Tight Reservoirs: A Critical Review
Energy Geoscience (2021)
Google Scholar

[15]
Z. Zhou, Y. Jin, Y. Zeng, X. Zhang, J. Zhou, L. Zhuang, S. Xin
Investigation on fracture creation in hot dry rock geothermal formations of China during hydraulic fracturing
Renew. Energy, 153 (2020), pp. 301-313
View PDFView articleView in ScopusGoogle Scholar

[16]
J. McBeck, J.M. Aiken, B. Cordonnier, Y. Ben-Zion, F. Renard
Predicting fracture network development in crystalline rocks
Pure Appl. Geophys., 179 (1) (2022), pp. 275-299
CrossRefView in ScopusGoogle Scholar

[17]
R. Kiran, S. Salehi
Assessing the Relation between Petrophysical and Operational Parameters in Geothermal Wells: A Machine Learning Approach. Proceedings 45th Workshop on Geothermal Reservoir Engineering
Stanford University, Stanford, California (2020)
Google Scholar

[18]
F.H. Cornet, T. Bérard, S. Bourouis
How close to failure is a granite rock mass at a 5km depth?
Int. J. Rock Mech. Min., 44 (1) (2007), pp. 47-66
View PDFView articleView in ScopusGoogle Scholar

[19]
C. Glaas, J. Vidal, A. Genter
Structural characterization of naturally fractured geothermal reservoirs in the central Upper Rhine Graben
J. Struct. Geol., 148 (2021), Article 104370
View PDFView articleView in ScopusGoogle Scholar

[20]
C.M. Hartig
Anonymous, discrete fracture network simulation for sedimentary enhanced geothermal systems; red river formation, Williston basin, North Dakota
Trans. Geotherm. Resourc. Council, 39 (2015), pp. 1039-1048
View in ScopusGoogle Scholar

[21]
J.A. Howell, A.W. Martinius, T.R. Good
The application of outcrop analogues in geological modelling: a review, present status and future outlook
Geol. Soc. London, Special Publ., 387 (1) (2014), pp. 1-25
Google Scholar

[22]
Y. Mukuhira, T. Ito, H. Asanuma, M. Häring
Evaluation of flow paths during stimulation in an EGS reservoir using microseismic information
Geothermics, 87 (2020), Article 101843
View PDFView articleView in ScopusGoogle Scholar

[23]
S. Thiel
Electromagnetic monitoring of hydraulic fracturing: relationship to permeability, seismicity, and stress
Surv. Geophys., 38 (5) (2017), pp. 1133-1169
CrossRefView in ScopusGoogle Scholar

[24]
B.F. Ayling, R.A. Hogarth, P.E. Rose
Tracer testing at the Habanero EGS site, central Australia
Geothermics, 63 (2016), pp. 15-26
View PDFView articleView in ScopusGoogle Scholar

[25]
M.O. Häring, U. Schanz, F. Ladner, B.C. Dyer
Characterization of the Basel 1 enhanced geothermal system
Geothermics, 37 (5) (2008), pp. 469-495
View PDFView articleView in ScopusGoogle Scholar

[26]
Z. Jiang, S. Zhang, C. Turnadge, T. Xu
Combining autoencoder neural network and Bayesian inversion to estimate heterogeneous permeability distributions in enhanced geothermal reservoirs : model development and verification
Geothermics, 97 (2021), Article 102262
View PDFView articleView in ScopusGoogle Scholar

[27]
J.R. Peacock, T.E. Earney, M.T. Mangan, W.D. Schermerhorn, J.M. Glen, M. Walters, C. Hartline
Geophysical characterization of the Northwest Geysers geothermal field, California
J. Volcanol. Geoth. Res., 399 (2020), Article 106882
View PDFView articleView in ScopusGoogle Scholar

[28]
Y.L. Didana, G. Heinson, S. Thiel, L. Krieger
Magnetotelluric monitoring of permeability enhancement at enhanced geothermal system project
Geothermics, 66 (2017), pp. 23-38
View PDFView articleView in ScopusGoogle Scholar

[29]
M.W. McClure, R.N. Horne
An investigation of stimulation mechanisms in Enhanced Geothermal Systems
Int. J. Rock Mech. Min., 72 (2014), pp. 242-260
View PDFView articleView in ScopusGoogle Scholar

[30]
S.A. Shapiro
An inversion for fluid transport properties of three-dimensionally heterogeneous rocks using induced microseismicity
Geophys. J. Int., 143 (3) (2000), pp. 931-936
View in ScopusGoogle Scholar

[31]
S.A. Shapiro, E. Rothert, V. Rath, J. Rindschwentner
Characterization of fluid transport properties of reservoirs using induced microseismicity
Geophysics, 67 (1) (2002), p. 212
View in ScopusGoogle Scholar

[32]
N. Hummel, S.A. Shapiro
Microseismic estimates of hydraulic diffusivity in case of non-linear fluid-rock interaction
Geophys. J. Int., 188 (3) (2012), pp. 1441-1453
CrossRefView in ScopusGoogle Scholar

[33]
T. Xu, X. Liang, Y. Xia, Z. Jiang, F. Gherardi
Performance evaluation of the Habanero enhanced geothermal system, Australia: optimization based on tracer and induced micro-seismicity data
Renew. Energy, 181 (2022), pp. 1197-1208
View PDFView articleView in ScopusGoogle Scholar

[34]
M. Tarrahi, B. Jafarpour
Inference of permeability distribution from injection-induced discrete microseismic events with kernel density estimation and ensemble Kalman filter
Water Resour. Res., 48 (10) (2012)
Google Scholar

[35]
J. Chen, T. Xu, X. Liang, Z. Jiang
Stochastic inversion of tracer test data with seismicity constraint for permeability imaging in enhanced geothermal reservoirs
Geophysics, 87 (6) (2022), pp. M307-M319
CrossRefView in ScopusGoogle Scholar

[36]
H. Aydin, S. Akin
Discrete Fracture Network Modeling of Alaşehir Geothermal Field. Proceedings 44th Workshop on Geothermal Reservoir Engineering
Stanford University, Stanford, California (2019)
Google Scholar

[37]
R. Egert, M.G. Korzani, S. Held, T. Kohl
Implications on Large-Scale Flow of the Fractured EGS Reservoir Soultz Inferred from Hydraulic Data and Tracer Experiments, vol. 84 (2020), Article 101749
View PDFView articleView in ScopusGoogle Scholar

[38]
P. Deb, D. Knapp, G. Marquart, C. Clauser, E. Trumpy
Stochastic workflows for the evaluation of Enhanced Geothermal System (EGS) potential in geothermal greenfields with sparse data: the case study of Acoculco, Mexico
Geothermics, 88 (2020), Article 101879
View PDFView articleView in ScopusGoogle Scholar

[39]
S. Hochreiter, J. Schmidhuber
Long short-term memory
Neural Comput., 9 (8) (1997), pp. 1735-1780
CrossRefView in ScopusGoogle Scholar

[40]
B. Aaha, C. Sm, D. Hf, D. Ia, E. Mm, F. Hc
Harris hawks optimization: algorithm and applications
Future Generat. Comput. Syst., 97 (2019), pp. 849-872
Google Scholar

[41]
A. Yaghoubi
Hydraulic fracturing modeling using a discrete fracture network in the Barnett Shale
Int. J. Rock Mech. Min., 119 (2019), pp. 98-108
View PDFView articleView in ScopusGoogle Scholar

[42]
N.I. Fisher, T. Lewis, B.J.J. Embleton
Statistical Analysis of Spherical Data
Cambridge University Press, Cambridge (1987)
Google Scholar

[43]
H. Wang, J. Pan, S. Wang, H. Zhu
Relationship between macro-fracture density, P-wave velocity, and permeability of coal
J. Appl. Geophys. vol. 117 (2015), pp. 111-117
View PDFView articleView in ScopusGoogle Scholar

[44]
A. Finnila, B. Forbes, R. Podgorney
Building and Utilizing a Discrete Fracture Network Model of the FORGE Utah Site
Proceedings 44th Workshop on Geothermal Reservoir Engineering, Stanford University, Stanford, California (2019)
Google Scholar

[45]
P.A. Witherspoon, J.S.Y. Wang, K. Iwai, J.E. Gale
Validity of cubic law for fluid in a deformable rock fracture
Water Resour. Res., 16 (6) (1980), pp. 1016-1024
View in ScopusGoogle Scholar

[46]
D.T. Snow
A Parallel Plate Model of Fractured Permeable Media
Ph.d. dissertation
University of California (1965)
Google Scholar

[47]
S. Rogers, P. McLellan, G. Webb
Investigation of the Effects of Natural Fractures and Faults on Hydraulic Fracturing in the Montney Formation
Farrell Creek Gas Field, British Columbia (2014)
%7b%7d
Google Scholar

[48]
R. Huang, C. Wei, B. Wang, J. Yang, X. Xu, S. Wu, S. Huang
Well performance prediction based on Long Short-Term Memory (LSTM) neural network
J. Petrol. Sci. Eng., 208 (2022), Article 109686
View PDFView articleView in ScopusGoogle Scholar

[49]
X. Li, K. Xiao, X. Li, C. Yu, D. Fan, Z. Sun
A well rate prediction method based on LSTM algorithm considering manual operations
J. Petrol. Sci. Eng., 210 (2022), Article 110047
View PDFView articleView in ScopusGoogle Scholar

[50]
N. Srivastava, G. Hinton, A. Krizhevsky
Dropout: a simple way to prevent neural networks from overfitting
J. Mach. Learn. Res., 6 (2014), pp. 1929-1958
View in ScopusGoogle Scholar

[51]
M. Kuşoğlu, U. Yüzgeç
Multi-objective Harris hawks optimizer for multiobjective optimization problems
Bseu J. Eng. Res. Technol. (2020), pp. 31-41
DEC(I)(I)
Google Scholar

[52]
A.A. Heidari, S. Mirjalili, H. Faris, I. Aljarah, M. Mafarja, H. Chen
Harris hawks optimization: algorithm and applications
Future Generat. Comput. Syst., 97 (2019), pp. 849-872
View PDFView articleView in ScopusGoogle Scholar

[53]
A. Abbasi, B. Firouzi, P. Sendur
On the Application of Harris Hawks Optimization (HHO) Algorithm to the Design of Microchannel Heat Sinks
Eng Comput-Germany (2019), pp. 1-20
CrossRefGoogle Scholar

[54]
Y. Tikhamarine, D. Souag-Gamane, A.N. Ahmed, S.S. Sammen, O. Kisi, Y.F. Huang, A. El-Shafie
Rainfall-runoff modelling using improved machine learning methods: Harris hawks optimizer vs. particle swarm optimization
J. Hydrol., 589 (2020), Article 125133
View PDFView articleView in ScopusGoogle Scholar

[55]
H.B. Mills, T. Habanero
Pilot Project - Australia ' S First EGS Power Plant. 35th New Zealand Geothermal Workshop
Rotorua, New Zealand (2013)
Google Scholar

[56]
P. Chopra, D. Wyborn
Initial calculations of performance for an Australian hot dry rock reservoir, Proc
World Geoth. Congr (2000)
Google Scholar

[57]
Y. Kumano, H. Moriya, H. Asanuma, N. Soma, H. Kaieda, K. Tezuka, D. Wyborn, H. Nhtsuma
Interpretation of reservoir creation process at Cooper Basin, Australia by acoustic emission
J. Acoust. Emiss., 23 (Jan/Dec) (2005), pp. 129-135
Google Scholar

[58]
G.W. Delton, B. Chen
Aims of a Basic EGS Model for the Cooper Basin, Australia
Proceedings Australian Geothermal Energy Conference (2009)
Google Scholar

[59]
H.G. Holl, C. Barton
Habanero Field - Structure and State of Stress
ProceedingsWorld Geothermal Congress (2015)
Google Scholar

[60]
H. Asanuma, N. Soma, H. Kaieda, Y. Kumano, T. Izumi, K. Tezuka, H. Niitsuma, D. Wyborn
Microseismic Monitoring of Hydraulic Stimulation at the Australian HDR Project in Cooper Basin, ProceedingsWorld Geothermal Congress
Antalya, Turkey (2005)
Google Scholar

[61]
S. Baisch, R. Weidler, R. Voros, D. Wyborn, L. de Graaf
Induced seismicity during the stimulation of a geothermal HFR reservoir in the Cooper Basin, Australia
Bull. Seismol. Soc. Am., 96 (6) (2006), pp. 2242-2256
CrossRefView in ScopusGoogle Scholar

[62]
S. Baisch, R. Voros, R. Weidler, D. Wyborn
Investigation of fault mechanisms during geothermal reservoir stimulation experiments in the Cooper Basin, Australia
Bull. Seismol. Soc. Am., 99 (1) (2009), pp. 148-158
CrossRefView in ScopusGoogle Scholar

[63]
L. Xie, K. Min, Y. Song
Observations of hydraulic stimulations in seven enhanced geothermal system projects
Renew. Energy, 79 (2015), pp. 56-65
View PDFView articleView in ScopusGoogle Scholar

[64]
S. Baisch, A. Mcmahon
Seismic Real-Time Monitoring of a Massive Hydraulic Stimulation of a Geothermal Reservoir in the Cooper Basin, Australia
Proceedings Eage/dgg Workshop on Microssmic Monitoring (2014)
Google Scholar

[65]
S. Baisch, E. Rothert, H. Stang, R. Vörös, C. Koch, A. McMahon
Continued geothermal reservoir stimulation experiments in the Cooper Basin (Australia)
Bull. Seismol. Soc. Am., 105 (1) (2015), pp. 198-209
CrossRefView in ScopusGoogle Scholar

[66]
S. Baisch
Inferring in situ hydraulic pressure from induced seismicity observations: an application to the Cooper Basin (Australia) geothermal reservoir
J. Geophys. Res. Solid Earth, 125 (8) (2020)
Google Scholar

[67]
E.J. Nelson, S.T. Chipperfield, R.R. Hillis, J. Gilbert, J. Mcgowen
Using geological information to optimize fracture stimulation practices in the Cooper Basin, Australia
Petrol. Geosci., 13 (1) (2007), pp. 3-16
CrossRefView in ScopusGoogle Scholar

[68]
C. Xu, P. Dowd, R. Mohais
Connectivity analysis of the Habanero enhanced geothermal system
Thirty-Seventh Workshop on Geothermal Reservoir Engineering, Stanford University, Stanford, California (2012), pp. e177-e181
View in ScopusGoogle Scholar

[69]
Y. Wang, T. Li, Y. Chen, G. Ma
A three-dimensional thermo-hydro-mechanical coupled model for enhanced geothermal systems (EGS) embedded with discrete fracture networks
Comput. Methods Appl. Math., 356 (2019), pp. 465-489
View PDFView articleGoogle Scholar

[70]
D. Kulikowski, K. Amrouch, D. Cooke
Geomechanical modelling of fault reactivation in the Cooper Basin, Australia
Aust. J. Earth Sci., 63 (3) (2016), pp. 295-314
CrossRefView in ScopusGoogle Scholar

[71]
M.D. Zoback, C.A. Barton, M. Brudy, D.A. Castillo, T. Finkbeiner, B.R. Grollimund, D.B. Moos, P. Peska, C.D. Ward, D.J. Wiprut
Determination of stress orientation and magnitude in deep wells
Int. J. Rock Mech. Min., 40 (7-8) (2003), pp. 1049-1076
View PDFView articleView in ScopusGoogle Scholar

[72]
M. Mckay, R. Beckman, W. Conover
A comparison of three methods for selecting values of input variables in the analysis of output from a computer code
Technometrics (No. 1) (2000), pp. 55-61
View in ScopusGoogle Scholar

[73]
B. Teixeira Silveira, D. Roehl, E.C. Mejia Sanchez
Forecasting of the interaction between hydraulic and natural fractures using an artificial neural network
J. Petrol. Sci. Eng., 208 (2022), Article 109446
View PDFView articleView in ScopusGoogle Scholar