Platypus: a Python package for automated surrogate-assisted analysis of process-based simulations via the non-intrusive reduced-basis method
Jorge Nicolas Hayek
CORRESPONDING AUTHOR
GFZ Helmholtz-Zentrum für Geoforschung, Telegrafenberg, 14473 Potsdam, Germany
Mauro Cacace
GFZ Helmholtz-Zentrum für Geoforschung, Telegrafenberg, 14473 Potsdam, Germany
Marthe Faber
GFZ Helmholtz-Zentrum für Geoforschung, Telegrafenberg, 14473 Potsdam, Germany
Yulia Gruzdeva
GFZ Helmholtz-Zentrum für Geoforschung, Telegrafenberg, 14473 Potsdam, Germany
Denise Degen
Institute of Applied Geosciences, TU Darmstadt, Schnittspahnstraße 9, 64287 Darmstadt, Germany
GFZ Helmholtz-Zentrum für Geoforschung, Telegrafenberg, 14473 Potsdam, Germany
Related authors
No articles found.
Mohammad Sabah, Mauro Cacace, Inga Berre, Iman R. Kivi, and Hannes Hofmann
Geosci. Model Dev., 19, 10447–10478, https://doi.org/10.5194/gmd-19-10447-2026, https://doi.org/10.5194/gmd-19-10447-2026, 2026
Short summary
Short summary
Injecting fluids underground for energy projects can trigger earthquakes. Predicting these events is difficult because underground pressure changes slowly, while faults can move in a fraction of a second. We developed a computer method that switches between two ways of calculating these processes. In our test, it reduced computing time by 62 % while giving similar estimates of earthquake size and total fault movement. Differences in the fastest movements show that further testing is needed.
Waqas Hussain, Mauro Cacace, Andrea Bistacchi, and Riccardo Monti
EGUsphere, https://doi.org/10.5194/egusphere-2026-4815, https://doi.org/10.5194/egusphere-2026-4815, 2026
This preprint is open for discussion and under review for Solid Earth (SE).
Short summary
Short summary
PyMeshIt provides an automated way to turn complex three-dimensional geological surfaces into consistent volume models. Its main advance is the ability to handle folded surfaces, concave boundaries, and intersecting structures that are difficult for conventional meshing approaches. Tests on synthetic and real geological examples show that it extends the earlier MeshIt method to more complex geometries while preserving important geological boundaries and labels.
Denise Degen, Ajay Kumar, Magdalena Scheck-Wenderoth, and Mauro Cacace
Geosci. Model Dev., 18, 9219–9236, https://doi.org/10.5194/gmd-18-9219-2025, https://doi.org/10.5194/gmd-18-9219-2025, 2025
Short summary
Short summary
Geodynamical simulations cover a wide spatial and temporal range and are crucial to understand and assess the evolution of the Earth system. To enable computationally efficient modeling approaches that can account for potentially unknown subsurface properties, we present a surrogate modeling technique. This technique combines physics-based and machine-learning techniques to enable reliable predictions of geodynamical applications, as we illustrate for the case study of the Alpine Region.
Denise Degen, Moritz Ziegler, Oliver Heidbach, Andreas Henk, Karsten Reiter, and Florian Wellmann
Solid Earth, 16, 477–502, https://doi.org/10.5194/se-16-477-2025, https://doi.org/10.5194/se-16-477-2025, 2025
Short summary
Short summary
Obtaining reliable estimates of the subsurface state distributions is essential to determine the location of, e.g., potential nuclear waste disposal sites. However, providing these is challenging since it requires solving the problem numerous times, yielding high computational cost. To overcome this, we use a physics-based machine learning method to construct surrogate models. We demonstrate how it produces physics-preserving predictions, which differentiates it from purely data-driven approaches.
Javier Abreu-Torres, Gergő Hutka, Guido Blöcher, Mauro Cacace, Vincent Magnenet, and Jean Schmittbuhl
Adv. Geosci., 65, 117–125, https://doi.org/10.5194/adgeo-65-117-2025, https://doi.org/10.5194/adgeo-65-117-2025, 2025
Short summary
Short summary
We develop a simplified model which describes the geological geometry of the Vendenheim site, the solid and fluid properties were adapted from studies in the area. We implement compute the hydrothermal flow with a temperature dependent density and viscosity in a porous medium, in order to verify if a hydrothermal convective system is compatible with known observations at the Vendenheim site, and to get a better idea of the initial conditions of a model for an induced seismicity model.
Kalliopi Tzoufka, Guido Blöcher, Mauro Cacace, Daniela Pfrang, and Kai Zosseder
Adv. Geosci., 65, 103–111, https://doi.org/10.5194/adgeo-65-103-2024, https://doi.org/10.5194/adgeo-65-103-2024, 2024
Short summary
Short summary
Concepts of High-Temperature Aquifer Thermal Energy Storage (HT-ATES) are investigated for system application in the German Molasse Basin. We quantify via physics-based numerical modelling the system performance with respect to HT-ATES concept development and provide a predictive analysis of HT-ATES application in the Upper Jurassic reservoir. Results demonstrate a non-uniform layer-specific distribution of the thermal front propagation, while promising heat recovery efficiencies are predicted.
Ángela María Gómez-García, Álvaro González, Mauro Cacace, Magdalena Scheck-Wenderoth, and Gaspar Monsalve
Solid Earth, 15, 281–303, https://doi.org/10.5194/se-15-281-2024, https://doi.org/10.5194/se-15-281-2024, 2024
Short summary
Short summary
We compute a realistic three-dimensional model of the temperatures down to 75 km deep within the Earth, below the Caribbean Sea and northwestern South America. Using this, we estimate at which rock temperatures past earthquakes nucleated in the region and find that they agree with those derived from laboratory experiments of rock friction. We also analyse how the thermal state of the system affects the spatial distribution of seismicity in this region.
Denise Degen, Daniel Caviedes Voullième, Susanne Buiter, Harrie-Jan Hendricks Franssen, Harry Vereecken, Ana González-Nicolás, and Florian Wellmann
Geosci. Model Dev., 16, 7375–7409, https://doi.org/10.5194/gmd-16-7375-2023, https://doi.org/10.5194/gmd-16-7375-2023, 2023
Short summary
Short summary
In geosciences, we often use simulations based on physical laws. These simulations can be computationally expensive, which is a problem if simulations must be performed many times (e.g., to add error bounds). We show how a novel machine learning method helps to reduce simulation time. In comparison to other approaches, which typically only look at the output of a simulation, the method considers physical laws in the simulation itself. The method provides reliable results faster than standard.
Denise Degen, Cameron Spooner, Magdalena Scheck-Wenderoth, and Mauro Cacace
Geosci. Model Dev., 14, 7133–7153, https://doi.org/10.5194/gmd-14-7133-2021, https://doi.org/10.5194/gmd-14-7133-2021, 2021
Short summary
Short summary
In times of worldwide energy transitions, an understanding of the subsurface is increasingly important to provide renewable energy sources such as geothermal energy. To validate our understanding of the subsurface we require data. However, the data are usually not distributed equally and introduce a potential misinterpretation of the subsurface. Therefore, in this study we investigate the influence of measurements on temperature distribution in the European Alps.
Cited articles
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, TensorFlow, https://www.tensorflow.org/ (last access: 19 June 2026), 2015. a
Abernathey, R. P., Augspurger, T., Banihirwe, A., Blackmon-Luca, C. C., Crone, T. J., Gentemann, C. L., Hamman, J. J., Henderson, N., Lepore, C., McCaie, T. A., Robinson, N. H., and Signell, R. P.: Cloud-Native Repositories for Big Scientific Data, Comput. Sci. Eng., 23, 26–35, https://doi.org/10.1109/MCSE.2021.3059437, 2021. a, b
Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M.: Optuna: A Next-generation Hyperparameter Optimization Framework, in: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, New York, NY, USA, 2623–2631, ISBN 9781450362016, https://doi.org/10.1145/3292500.3330701, 2019. a
Alla, A., Gräßle, C., and Hinze, M.: Time Adaptivity in Model Predictive Control, J. Sci. Comput., 90, 12, https://doi.org/10.1007/s10915-021-01647-0, 2021. a
Benner, P., Gugercin, S., and Willcox, K.: A Survey of Projection-Based Model Reduction Methods for Parametric Dynamical Systems, SIAM Rev., 57, 483–531, https://doi.org/10.1137/130932715, 2015. a, b
Blöcher, G., Reinsch, T., Henninges, J., Milsch, H., Regenspurg, S., Kummerow, J., Francke, H., Kranz, S., Saadat, A., Zimmermann, G., and Huenges, E.: Hydraulic history and current state of the deep geothermal reservoir Groß Schönebeck, Geothermics, 63, 27–43, https://doi.org/10.1016/j.geothermics.2015.07.008, 2016. a, b
Blöcher, G., Cacace, M., Jacquey, A. B., Zang, A., Heidbach, O., Hofmann, H., Kluge, C., and Zimmermann, G.: Evaluating Micro-Seismic Events Triggered by Reservoir Operations at the Geothermal Site of Groß Schönebeck (Germany), Rock Mech. Rock Eng., 51, 3265–3279, 2018. a
Cacace, M. and Jacquey, A. B.: Flexible parallel implicit modelling of coupled thermal–hydraulic–mechanical processes in fractured rocks, Solid Earth, 8, 921–941, https://doi.org/10.5194/se-8-921-2017, 2017. a
Cacace, M., Hofmann, H., and Shapiro, S. A.: Projecting seismicity induced by complex alterations of underground stresses with applications to geothermal systems, Sci. Rep., 11, 23560, https://doi.org/10.1038/s41598-021-02857-0, 2021. a, b, c
Christi, L. F., Sass, I., Norden, B., Blöcher, G., Zimmermann, G., and Hofmann, H.: Repurposing of hydrocarbon wells for Enhanced Geothermal System (EGS) development, Geothermics, 128, 103268, https://doi.org/10.1016/j.geothermics.2025.103268, 2025. a
Degen, D. and Wellmann, F.: Guidelines for Conducting Sensitivity Analyses in Process Simulations for Solid Earth Geosciences, Math. Geosci., https://doi.org/10.1007/s11004-025-10267-5, 2026. a
Degen, D., Caviedes Voullième, D., Buiter, S., Hendricks Franssen, H.-J., Vereecken, H., González-Nicolás, A., and Wellmann, F.: Perspectives of physics-based machine learning strategies for geoscientific applications governed by partial differential equations, Geosci. Model Dev., 16, 7375–7409, https://doi.org/10.5194/gmd-16-7375-2023, 2023. a, b, c, d, e, f, g, h
Degen, D., Cacace, M., and Wellmann, F.: Exploring physics-based machine learning for geothermal applications, in: 49th Workshop on Geothermal Reservoir Engineering, 1–9, https://pangea.stanford.edu/ERE/db/IGAstandard/record_detail.php?id=36316 (last access: 19 June 2026), 2024. a
Degen, D., Kumar, A., Scheck-Wenderoth, M., and Cacace, M.: Exploiting physics-based machine learning to quantify geodynamic effects – insights from the Alpine region, Geosci. Model Dev., 18, 9219–9236, https://doi.org/10.5194/gmd-18-9219-2025, 2025a. a
Degen, D., Ziegler, M., Heidbach, O., Henk, A., Reiter, K., and Wellmann, F.: About the trustworthiness of physics-based machine learning – considerations for geomechanical applications, Solid Earth, 16, 477–502, https://doi.org/10.5194/se-16-477-2025, 2025b. a
Dorward, H., Knowles, D. M., Demir, E., Mostafavi, M., and Peel, M. J.: Calibration and surrogate model-based sensitivity analysis of crystal plasticity finite element models, Mater. Design, 247, 113409, https://doi.org/10.1016/j.matdes.2024.113409, 2024. a
Gräßle, C., Hinze, M., Lang, J., and Ullmann, S.: POD model order reduction with space-adapted snapshots for incompressible flows, Adv. Comput. Math., 45, 2401–2428, https://doi.org/10.1007/s10444-019-09716-7, 2019. a
Guo, M. and Hesthaven, J. S.: Reduced order modeling for nonlinear structural analysis using Gaussian process regression, Comput. Method. Appl. M., 341, 807–826, https://doi.org/10.1016/j.cma.2018.07.017, 2018. a
Halton, J. H.: On the efficiency of certain quasi-random sequences of points in evaluating multi-dimensional integrals, Numer. Math., 2, 84–90, https://doi.org/10.1007/BF01386213, 1960. a
Harbour, L., Giudicelli, G., Lindsay, A. D., German, P., Hansel, J., Icenhour, C., Li, M., Miller, J. M., Stogner, R. H., Behne, P., Yankura, D., Prince, Z. M., DeChant, C., Schwen, D., Spencer, B. W., Tano, M., Choi, N., Wang, Y., Nezdyur, M., Miao, Y., Hu, T., Kumar, S., Matthews, C., Langley, B., Nobre, N., Blair, A., MacMackin, C., Rocha, H. B., Palmer, E., Carter, J., Meier, J., Slaughter, A. E., Andrš, D., Carlsen, R. W., Kong, F., Gaston, D. R., and Permann, C. J.: 4.0 MOOSE: Enabling massively parallel Multiphysics simulation, SoftwareX, 31, 102264, https://doi.org/10.1016/j.softx.2025.102264, 2025. a, b
Hayek, J. N., Cacace, M., Faber, M., Gruzdeva, Y., and Degen, D.: Platypus: A Python package for automated surrogate-assisted analysis of process-based simulations via the non-intrusive reduced-basis method, Zenodo [code], https://doi.org/10.5281/zenodo.20734438, 2026. a
Herman, J. and Usher, W.: SALib: An open-source Python library for Sensitivity Analysis, Journal of Open Source Software, 2, https://doi.org/10.21105/joss.00097, 2017. a, b, c
Hesthaven, J. S., Rozza, G., and Stamm, B.: Reduced Basis Methods, Springer International Publishing, Cham, 27–43, ISBN 978-3-319-22470-1, https://doi.org/10.1007/978-3-319-22470-1_3, 2016. a
Hoyer, S. and Hamman, J.: xarray: N-D labeled Arrays and Datasets in Python, Journal of Open Research Software, https://doi.org/10.5334/jors.148, 2017. a, b, c
Iwanaga, T., Usher, W., and Herman, J.: Toward SALib 2.0: Advancing the accessibility and interpretability of global sensitivity analyses, Socio-Environmental Systems Modelling, 4, 18155, https://doi.org/10.18174/sesmo.18155, 2022. a, b
Jacquey, A. B. and Cacace, M.: GOLEM, a MOOSE-based application, Zenodo [code], https://doi.org/10.5281/zenodo.999401, 2017. a, b
Kwiatek, G., Bohnhoff, M., Dresen, G., Schulze, A., Schulte, T., Zimmermann, G., and Huenges, E.: Microseismicity induced during fluid-injection: A case study from the geothermal site at Groß Schönebeck, North German Basin, Acta Geophys., 58, 995–1020, https://doi.org/10.2478/s11600-010-0032-7, 2010. a
Lindner, N., Degen, D., Grayver, A., and Wellmann, F.: Sensitivity analysis using physics-based machine learning: an example from surrogate modelling for magnetotellurics, Geophys. J. Int., 242, ggaf166, https://doi.org/10.1093/gji/ggaf166, 2025. a
Liu, H., Ong, Y.-S., and Cai, J.: A survey of adaptive sampling for global metamodeling in support of simulation-based complex engineering design, Struct. Multidiscip. O., 57, 393–416, https://doi.org/10.1007/s00158-017-1739-8, 2018. a
Liu, H., Ong, Y.-S., Shen, X., and Cai, J.: When Gaussian Process Meets Big Data: A Review of Scalable GPs, IEEE T. Neur. Net. Lear., 31, 4405–4423, https://doi.org/10.1109/TNNLS.2019.2957109, 2020. a
Loh, W.-L.: On Latin hypercube sampling, Ann. Stat., 24, 2058–2080, https://doi.org/10.1214/aos/1069362310, 1996. a
McKay, M. D., Beckman, R. J., and Conover, W. J.: A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code, Technometrics, 21, 239–245, https://doi.org/10.2307/1268522, 1979. a
Moeck, I., Kwiatek, G., and Zimmermann, G.: Slip tendency analysis, fault reactivation potential and induced seismicity in a deep geothermal reservoir, J. Struct. Geol., 31, 1174–1182, https://doi.org/10.1016/j.jsg.2009.06.012, 2009. a
Niederreiter, H.: Random Number Generation and Quasi-Monte Carlo Methods, Society for Industrial and Applied Mathematics, https://doi.org/10.1137/1.9781611970081, 1992. a
OpenAI: Minimalistic platypus logo transitioning into a low poly geometric style, AI-generated image, ChatGPT (DALL·E), https://chatgpt.com (last access: 16 February 2026), 2025. a
Pandey, S., Vishal, V., and Chaudhuri, A.: Geothermal reservoir modeling in a coupled thermo-hydro-mechanical-chemical approach: A review, Earth-Sci. Rev., 185, 1157–1169, https://doi.org/10.1016/j.earscirev.2018.09.004, 2018. a
Raissi, M., Perdikaris, P., and Karniadakis, G. E.: Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations, arXiv [preprint], https://doi.org/10.48550/arXiv.1711.10561, 2017. a
Saltelli, A.: Making best use of model evaluations to compute sensitivity indices, Comput. Phys. Commun., 145, 280–297, https://doi.org/10.1016/S0010-4655(02)00280-1, 2002. a
Santoso, R., Degen, D., Cacace, M., and Wellmann, F.: State-of-the-art physics-based machine learning for hydro-mechanical simulation in geothermal applications, European Geothermal Congress 2022, https://doi.org/10.24406/publica-1122, 2022. a
Sobol, I.: On quasi-Monte Carlo integrations, Math. Comput. Simulat., 47, 103–112, https://doi.org/10.1016/S0378-4754(98)00096-2, 1998. a
Sullivan, B. and Kaszynski, A.: PyVista: 3D plotting and mesh analysis through a streamlined interface for the Visualization Toolkit (VTK), Journal of Open Source Software, 4, 1450, https://doi.org/10.21105/joss.01450, 2019. a, b, c
Swischuk, R., Mainini, L., Peherstorfer, B., and Willcox, K.: Projection-based model reduction: Formulations for physics-based machine learning, Comput. Fluids, 179, 704–717, https://doi.org/10.1016/j.compfluid.2018.07.021, 2019. a, b, c
TensorFlow Developers: TensorFlow (Versions v2.22.0-rc0), Zenodo [code], https://doi.org/10.5281/zenodo.4724125, 2026. a
Vaezi, I., Yoshioka, K., De Simone, S., Gómez-Castro, B. M., Paluszny, A., Jalali, M., Berre, I., Rutqvist, J., Min, K.-B., Lei, Q., Makhnenko, R. Y., Hu, M., Tsang, C.-F., and Vilarrasa, V.: A review of thermo-hydro-mechanical modeling of coupled processes in fractured rock: From continuum to discontinuum perspective,, 17, 7460–7488, Journal of Rock Mechanics and Geotechnical Engineeringhttps://doi.org/10.1016/j.jrmge.2025.04.033, 2025. a
Zhang, N., Luo, Z., Chen, Z., Liu, F., Liu, P., Chen, W., Wu, L., and Zhao, L.: Thermal–hydraulic–mechanical–chemical coupled processes and their numerical simulation: a comprehensive review, Acta Geotech., 18, 6253–6274, https://doi.org/10.1007/s11440-023-01976-4, 2023. a
Short summary
Understanding how reservoirs respond to fluid injection requires complex computer models that are too expensive to run thousands of times for statistical analysis. We developed Platypus, a flexible Python package that automates the workflow from preparing simulations to constructing fast, accurate approximations of expensive simulations. Demonstrated on synthetic and real geothermal scenarios, it makes these analyses more accessible, supporting better decision-making under uncertainty.
Understanding how reservoirs respond to fluid injection requires complex computer models that...