Abstract
The Groningen gas field in the Netherlands is experiencing induced seismicity as a result of ongoing depletion. The physical mechanisms that control seismicity have been studied through rock mechanical experiments and combined physical-statistical models to support development of a framework to forecast induced-seismicity risks. To investigate whether machine learning techniques such as Random Forests and Support Vector Machines bring new insights into forecasts of induced seismicity rates in space and time, a pipeline is designed that extends time-series analysis methods to a spatiotemporal framework with a factorial setup, which allows probing a large parameter space of plausible modelling assumptions, followed by a statistical meta-analysis to account for the intrinsic uncertainties in subsurface data and to ensure statistical significance and robustness of results. The pipeline includes model validation using e.g. likelihood ratio tests against average depletion thickness and strain thickness baselines to establish whether the models have statistically significant forecasting power. The methodology is applied to forecast seismicity for two distinctly different gas production scenarios. Results show that seismicity forecasts generated using Support Vector Machines significantly outperform beforementioned baselines. Forecasts from the method hint at decreasing seismicity rates within the next 5 years, in a conservative production scenario, and no such decrease in a higher depletion scenario, although due to the small effective sample size no statistically solid statement of this kind can be made. The presented approach can be used to make forecasts beyond the investigated 5-years period, although this requires addition of limited physics-based constraints to avoid unphysical forecasts.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
Data availability
All data used in this study is publicly available: The seismic data is available through the KNMI Seismic and Acoustic Data Portal and EPOS (European Plate Observatory System). The reservoir models are also available through EPOS. Velocity models can be downloaded from NAM report repository website.
References
van Elk, J., Doornhof, D., Bommer, J.J., Bourne, S.J., Oates, S.J., Pinho, R., Crowley, H.: Hazard and risk assessments for induced seismicity in Groningen. Neth. J. Geosci. 96, s259–s269 (2017). https://doi.org/10.1017/njg.2017.37
Bourne, S.J., Oates, S.J., Van Elk, J., Doornhof, D.: A seismological model for earthquakes induced by fluid extraction from a subsurface reservoir. J. Geophys. Res. Solid Earth. 119, 8991–9015 (2014). https://doi.org/10.1002/2014JB011663
Statistics Netherlands (CBS): Natural gas revenues almost 417 billion euros, https://www.cbs.nl/en-gb/news/2019/22/natural-gas-revenues-almost-417-billion-euros. Accessed 31 Jan 2020
Foulger, G.R., Wilson, M.P., Gluyas, J.G., Julian, B.R., Davies, R.J.: Global review of human-induced earthquakes. Earth-Sci. Rev. 178, 438–514 (2018). https://doi.org/10.1016/j.earscirev.2017.07.008
Candela, T., Wassing, B., ter Heege, J., Buijze, L.: How earthquakes are induced. Science. 360(80), 598–600 (2018). https://doi.org/10.1126/science.aat2776
van Thienen-Visser, K., Breunese, J.N.: Induced seismicity of the Groningen gas field: history and recent developments. Lead. Edge. 34, 664–671 (2015). https://doi.org/10.1190/tle34060664.1
van Thienen-Visser, K., Pruiksma, J.P., Breunese, J.N.: Compaction and subsidence of the Groningen gas field in the Netherlands. Proc. Int. Assoc. Hydrol. Sci. 372, 367–373 (2015). https://doi.org/10.5194/piahs-372-367-2015
Rutqvist, J., Rinaldi, A.P., Cappa, F., Moridis, G.J.: Modeling of fault activation and seismicity by injection directly into a fault zone associated with hydraulic fracturing of shale-gas reservoirs. J. Pet. Sci. Eng. 127, 377–386 (2015). https://doi.org/10.1016/j.petrol.2015.01.019
Fan, Z., Eichhubl, P., Gale, J.F.W.: Geomechanical analysis of fluid injection and seismic fault slip for the M w 4.8 Timpson, Texas, earthquake sequence. J. Geophys. Res. Solid Earth. 121, 2798–2812 (2016). https://doi.org/10.1002/2016JB012821
Stabile, T.A., Giocoli, A., Perrone, A., Piscitelli, S., Lapenna, V.: Fluid injection induced seismicity reveals a NE dipping fault in the southeastern sector of the high Agri Valley (southern Italy). Geophys. Res. Lett. 41, 5847–5854 (2014). https://doi.org/10.1002/2014GL060948
Izadi, G., Elsworth, D.: Reservoir stimulation and induced seismicity: roles of fluid pressure and thermal transients on reactivated fractured networks. Geothermics. 51, 368–379 (2014). https://doi.org/10.1016/j.geothermics.2014.01.014
Walsh, F.R., Zoback, M.D.: Oklahoma’s recent earthquakes and saltwater disposal. Sci. Adv. 1, e1500195 (2015). https://doi.org/10.1126/sciadv.1500195
Van Wees, J.-D., Fokker, P.A., Van Thienen-Visser, K., Wassing, B.B.T., Osinga, S., Orlic, B., Ghouri, S.A., Buijze, L., Pluymaekers, M.: Geomechanical models for induced seismicity in the Netherlands: inferences from simplified analytical, finite element and rupture model approaches. Neth. J. Geosci. 96, s183–s202 (2017). https://doi.org/10.1017/njg.2017.38
Spiers, C.J., Hangx, S.J.T., Niemeijer, A.R.: New approaches in experimental research on rock and fault behaviour in the Groningen gas field. Neth. J. Geosci. 96, s55–s69 (2017). https://doi.org/10.1017/njg.2017.32
Hunfeld, L.B., Niemeijer, A.R., Spiers, C.J.: Frictional properties of simulated fault gouges from the Seismogenic Groningen gas field under in situ P - T -chemical conditions. J. Geophys. Res. Solid Earth. 122, 8969–8989 (2017). https://doi.org/10.1002/2017JB014876
Bourne, S.J., Oates, S.J.: Extreme threshold failures within a heterogeneous elastic thin sheet and the spatial-temporal development of induced seismicity within the Groningen gas field. J. Geophys. Res. Solid Earth. 122, 299–320 (2017). https://doi.org/10.1002/2017JB014356
Orlic, B., Wassing, B.B.T.: A study of stress change and fault slip in producing gas reservoirs overlain by elastic and viscoelastic caprocks. Rock Mech. Rock. Eng. 46, 421–435 (2013). https://doi.org/10.1007/s00603-012-0347-6
Postma, T., Jansen, J.D.: The small effect of Poroelastic pressure transients on triggering of production-induced earthquakes in the Groningen natural gas field. J. Geophys. Res. Solid Earth. 123, 401–417 (2018). https://doi.org/10.1002/2017JB014809
van der Linden, A., Makurat, A., Marcelis, F., Hol, S., Bierman, S.: Rock physical controls on production-induced compaction in the Groningen field. Sci. Rep. 8, 1–13 (2018). https://doi.org/10.1038/s41598-018-25455-z
Mignan, A., Broccardo, M., Wiemer, S., Giardini, D.: Induced seismicity closed-form traffic light system for actuarial decision-making during deep fluid injections. Sci. Rep. 7, 1–10 (2017). https://doi.org/10.1038/s41598-017-13585-9
Broccardo, M., Mignan, A., Wiemer, S., Stojadinovic, B., Giardini, D.: Hierarchical Bayesian modeling of fluid-induced seismicity. Geophys. Res. Lett. 44(11), 357–11,367 (2017). https://doi.org/10.1002/2017GL075251
van Elk, J., Doornhof, D.: Review and Update of: Study and Data Acquisition Plan Induced Seismicity in Groningen - Update Post-Winningsplan 2016, Assen, Netherlands (2019). https://nam-feitenencijfers.data-app.nl/download/rapport/529d284a-a8e9-4aa8-a52e-3aa17761f40d?open=true. Accessed 31 Jan 2020
Nederlandse Aardolie Maatschappij: Technical Addendum to the Winningsplan Groningen 2016. (2016). https://www.nam.nl/algemeen/mediatheek-en-downloads/winningsplan-2016.html. Accessed 31 Jan 2020
Nederlandse Aardolie Maatschappij: Winningsplan Groningen Gasveld 2016. , Assen, Netherlands (2016). https://www.nam.nl/algemeen/mediatheek-en-downloads/winningsplan-2016.html. Accessed 31 Jan 2020
Melnikov, A.A., Nautrup, H.P., Krenn, M., Dunjko, V., Tiersch, M., Zeilinger, A., Briegel, H.J.: Active learning machine learns to create new quantum experiments. Proc. Natl. Acad. Sci. 115, 1221–1226 (2018). https://doi.org/10.1073/PNAS.1714936115
Carrasquilla, J., Melko, R.G.: Machine learning phases of matter. Nat. Phys. 13, 431–434 (2017). https://doi.org/10.1038/nphys4035
Bergen, K.J., Johnson, P.A., de Hoop, M.V., Beroza, G.C.: Machine learning for data-driven discovery in solid Earth geoscience. Science. 363(8), eaau0323 (2019). https://doi.org/10.1126/science.aau0323
Karpatne, A., Ebert-Uphoff, I., Ravela, S., Babaie, H.A., Kumar, V.: Machine learning for the geosciences: challenges and opportunities. IEEE Trans. Knowl. Data Eng. 31, 1544–1554 (2019). https://doi.org/10.1109/TKDE.2018.2861006
Pathak, J., Hunt, B., Girvan, M., Lu, Z., Ott, E.: Model-free prediction of large spatiotemporally chaotic systems from data: a reservoir computing approach. Phys. Rev. Lett. 120, (2018). https://doi.org/10.1103/PhysRevLett.120.024102
DeVries, P.M.R., Viégas, F., Wattenberg, M., Meade, B.J.: Deep learning of aftershock patterns following large earthquakes. Nature. 560, 632–634 (2018). https://doi.org/10.1038/s41586-018-0438-y
Perol, T., Gharbi, M., Denolle, M.: Convolutional neural network for earthquake detection and location. Sci. Adv. 4, e1700578 (2018). https://doi.org/10.1126/sciadv.1700578
Rouet-Leduc, B., Hulbert, C., Lubbers, N., Barros, K., Humphreys, C.J., Johnson, P.A.: Machine learning predicts laboratory earthquakes. Geophys. Res. Lett. 44, 9276–9282 (2017). https://doi.org/10.1002/2017GL074677
Panakkat, A., Adeli, H.: Recurrent neural network for approximate earthquake time and location prediction using multiple seismicity indicators. Comput. Civ. Infrastruct. Eng. 24, 280–292 (2009). https://doi.org/10.1111/j.1467-8667.2009.00595.x
Asencio-Cortés, G., Morales-Esteban, A., Shang, X., Martínez-Álvarez, F.: Earthquake prediction in California using regression algorithms and cloud-based big data infrastructure. Comput. Geosci. 115, 198–210 (2018). https://doi.org/10.1016/j.cageo.2017.10.011
Asencio-Cortés, G., Martínez-Álvarez, F., Morales-Esteban, A., Reyes, J.: A sensitivity study of seismicity indicators in supervised learning to improve earthquake prediction. Knowl.-Based Syst. 101, 15–30 (2016). https://doi.org/10.1016/j.knosys.2016.02.014
Last, M., Rabinowitz, N., Leonard, G.: Predicting the maximum earthquake magnitude from seismic data in Israel and its neighboring countries. PLoS One. 11, 1–16 (2016). https://doi.org/10.1371/journal.pone.0146101
Mignan, A., Broccardo, M.: One neuron versus deep learning in aftershock prediction. Nature. 574, E1–E3 (2019). https://doi.org/10.1038/s41586-019-1582-8
Mignan, A., Broccardo, M.: Neural Network Applications in Earthquake Prediction (1994–2019): Meta-analytic and statistical insights on their limitations. Seismol. Res. Lett. 1–25, 2330–2342 (2020). https://doi.org/10.1785/0220200021
Meade, B.J.: Reply to: one neuron versus deep learning in aftershock prediction. Nature. 574, E4–E4 (2019). https://doi.org/10.1038/s41586-019-1583-7
Fernández-Delgado, M., Cernadas, E., Barro, S., Amorim, D.: Do we need hundreds of classifiers to solve real world classification problems? J. Mach. Learn. Res. 11, 015020 (2014). https://doi.org/10.1117/1.JRS.11.015020
Makridakis, S., Spiliotis, E., Assimakopoulos, V.: Statistical and machine learning forecasting methods: concerns and ways forward. PLoS One. 13, e0194889 (2018). https://doi.org/10.1371/journal.pone.0194889
Limbeck, J., Lanz, F., Barbaro, E., Harris, C., Bisdom, K., Park, T., Oosterbosch, W., Jamali-Rad, H., Nevenzeel, K.: Evaluation of a Machine Learning methodology to forecast induced seismicity event rates within the Groningen Field, Assen, Netherlands (2018). https://nam-feitenencijfers.data-app.nl/download/rapport/d5be89f6-fcea-4237-bc07-6cda25e151d9?open=true. Accessed 31 Jan 2020
Lanz, F., Bisdom, K., Barbaro, E., Limbeck, J., Park, T., Harris, C., Nevenzeel, K.: Evaluation of a Machine Learning methodology for spatiotemporal induced seismicity forecasts within the Groningen field, Assen, Netherlands (2019). https://nam-onderzoeksrapporten.data-app.nl/reports/download/groningen/en/e5535713-46e2-4523-a479-4124f674c55f. Accessed 31 Jan 2020
R Core Team: R: A Language and Environment for Statistical Computing, https://www.r-project.org/, (2018)
Wright, M.N., Ziegler, A.: Ranger : A Fast Implementation of Random Forests for High Dimensional Data in C++ and R. J. Stat. Softw. 77, 1–17 (2017). https://doi.org/10.18637/jss.v077.i01
CGAL Project: CGAL User and Reference Manual, (2018). https://www.cgal.org/
Gärtner, B., Schönherr, S.: An efficient, exact, and generic quadratic programming solver for geometric optimization. Proceedings of the Sixteenth Annual Symposium on Computational Geometry - SCG ’00. ACM Press, New York, NY, USA, 110–118 (2000). https://doi.org/10.1145/336154.336191
Bischl, B., Lang, M., Kotthoff, L., Schiffner, J., Richter, J., Studerus, E., Casalicchio, G., Jones, Z.M.: mlr: Machine Learning in R. J. Mach. Learn. Res. 17, 1–5 (2016)
van Oeveren, H., Valvatne, P., Geurtsen, L., van Elk, J.: History match of the Groningen field dynamic reservoir model to subsidence data and conventional subsurface data. Neth. J. Geosci. 96, s47–s54 (2017). https://doi.org/10.1017/njg.2017.26
Bierman, S., Kraaijeveld, F., Bourne, S.: Regularised Direct Inversion to Compaction in the Groningen Reservoir Using Measurements from Optical Leveling Campaigns. Tech. Report. Shell Glob. Solut. Int. (2015). https://nam-feitenencijfers.data-app.nl/download/rapport/cc5ea278-c093-457b-b930-1869a3c26c21?open=true. Accessed 31 Jan 2020
Burkitov, U., van Oeveren, H., Valvatne, P.: Groningen Field Review 2015 Subsurface Dynamic Modelling Report. (2016)
Ministry of Economic Affairs and Climate Policy: Kamerbrief over gaswinning Groningen (2018) https://www.government.nl/documents/parliamentary-documents/2018/03/29/kamerbrief-over-gaswinning-groningen. Accessed 1 July 2019
Rydelek, P.A., Sacks, I.S.: Testing the completeness of earthquake catalogues and the hypothesis of self-similarity. Nature. 337, 251–253 (1989). https://doi.org/10.1038/337251a0
Dost, B., Goutbeek, F., van Eck, T., Kraaijpoel, D.: Monitoring Induced Seismicity in the North of the Netherlands: Status Report 2010, De Bilt, Netherlands (2012). KNMI report: http://bibliotheek.knmi.nl/knmipubWR/WR2012-03.pdf. Accessed 31 Jan 2018
Bourne, S.J., Oates, S.J.: Development of statistical geomechanical models for forecasting seismicity induced by gas production from the Groningen field. Geol. Mijnbouw/Neth. J. Geosci. 96, s175–s182 (2017). https://doi.org/10.1017/njg.2017.35
Nelder, J.A., Wedderburn, R.W.M.: Generalized linear models. J. R. Stat. Soc. Ser. A. 135, 370 (1972). https://doi.org/10.2307/2344614
López-Ibáñez, M., Dubois-Lacoste, J., Pérez Cáceres, L., Birattari, M., Stützle, T.: The irace package: iterated racing for automatic algorithm configuration. Oper. Res. Perspect. 3, 43–58 (2016). https://doi.org/10.1016/j.orp.2016.09.002
Hu, L.Y., Huang, M.W., Ke, S.W., Tsai, C.F.: The distance function effect on k-nearest neighbor classification for medical datasets. Springerplus. 5, 1304 (2016). https://doi.org/10.1186/s40064-016-2941-7
Breiman, L.: Random Forrests. Mach. Learn. (2001)
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer New York, New York (2009)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20, 273–297 (1995). https://doi.org/10.1007/BF00994018
Kursa, M.B., Rudnicki, W.R.: Feature Selection with the Boruta Package. J. Stat. Softw. 36, i11 (2010). https://doi.org/10.18637/jss.v036.i11
Fagerland, M.W., Sandvik, L.: The Wilcoxon-Mann-Whitney test under scrutiny. Stat. Med. 28, 1487–1497 (2009). https://doi.org/10.1002/sim.3561
Schorlemmer, D., Gerstenberger, M.C., Wiemer, S., Jackson, D.D., Rhoades, D.A.: Earthquake likelihood model testing. Seismol. Res. Lett. 78, 17–29 (2007). https://doi.org/10.1785/gssrl.78.1.17
Gerstenberger, M., Rhoades, D., Stirlin, M., Brownrigg, R., Christophersen, A.: Continued Development of the New Zealand Earthquake Forecast Testing Centre. (2009). https://www.eqc.govt.nz/sites/public_files/3753-Development-NZ-EQ-Forecast-Centre.pdf. Accessed 31 July 2020
Rhoades, D.A., Schorlemmer, D., Gerstenberger, M.C., Christophersen, A., Zechar, J.D., Imoto, M.: Efficient testing of earthquake forecasting models. Acta Geophys. 59, 728–747 (2011). https://doi.org/10.2478/s11600-011-0013-5
Bray, A., Schoenberg, F.P.: Assessment of point process models for earthquake forecasting. Stat. Sci. 28, 510–520 (2013). https://doi.org/10.1214/13-STS440
Wood, S.N., Pya, N., Säfken, B.: Smoothing parameter and model selection for general smooth models. J. Am. Stat. Assoc. 111, 1548–1563 (2016). https://doi.org/10.1080/01621459.2016.1180986
Karpatne, A., Atluri, G., Faghmous, J.H., Steinbach, M., Banerjee, A., Ganguly, A., Shekhar, S., Samatova, N., Kumar, V.: Theory-guided data science: a new paradigm for scientific discovery from data. IEEE Trans. Knowl. Data Eng. 29, 2318–2331 (2017). https://doi.org/10.1109/TKDE.2017.2720168
Goldstein, A., Kapelner, A., Bleich, J., Pitkin, E.: Peeking inside the black box: visualizing statistical learning with plots of individual conditional expectation. J. Comput. Graph. Stat. 24, 44–65 (2015). https://doi.org/10.1080/10618600.2014.907095
Acknowledgements
We are grateful to colleagues from Shell (Peter van den Bogert, Xander Campman, Pandu Devarakota, Hadi Jamali-Rad, Gerard Joosten, Kees Hindriks, Roger Yuan, Rick Wentinck, Alan Wood), NAM (Hermann Baehr, Leendert Geurtsen, Per Valvatne, Assaf Mar-Or, Remco Romijn, Richard Vietje, Clemens Visser, Onno van der Wal) and IBM (Munish Goyal, Stephen Lord, Mo Zhang) for providing their expertise input and for fruitful discussions and review comments. We thank NAM for funding this work and allowing for its publication. We thank the three anonymous reviewers for their useful comments that greatly improved this paper.
Funding
Funding was provided by the Nederlandse Aardolie Maatschappij (NAM).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest/competing interest
The authors declare that they have no conflict of interest.
Code availability
The code is available upon individual request, with guidance on its usage and integration with the data.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Limbeck, J., Bisdom, K., Lanz, F. et al. Using machine learning for model benchmarking and forecasting of depletion-induced seismicity in the Groningen gas field. Comput Geosci 25, 529–551 (2021). https://doi.org/10.1007/s10596-020-10023-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10596-020-10023-0