Suscripción a Biblioteca: Guest
Journal of Machine Learning for Modeling and Computing

Publicado 4 números por año

ISSN Imprimir: 2689-3967

ISSN En Línea: 2689-3975

Indexed in

DATA-INFORMED EMULATORS FOR MULTI-PHYSICS SIMULATIONS

Volumen 2, Edición 2, 2021, pp. 33-54
DOI: 10.1615/JMachLearnModelComput.2021038577
Get accessDownload

SINOPSIS

Machine learning techniques are powerful tools for construction of emulators for complex systems. We explore different machine learning methods and conceptual methodologies, ranging from functional approximations to dynamical approximations, to build such emulators for coupled thermal, hydrological, mechanical, and chemical processes that occur near an engineered barrier system in the nuclear waste repository. Two nonlinear approximators, random forests and neural networks, are deployed to capture the complexity of the physics-based model and to identify its most significant hydrological and geochemical parameters. Our emulators capture the temporal evolution of the uranium distribution coefficient of the clay buffer and identify its functional dependence on these key parameters. The emulators' accuracy is further enhanced by assimilating relevant simulated predictors and clustering strategy. The relative performance of random forests and neural networks shows the advantage of ensemble learning in the random forests algorithm, especially for highly nonlinear problems with limited data.

REFERENCIAS
  1. Audigane, P., Gaus, I., Czernichowski-Lauriol, I., Pruess, K., and Xu, T., Two-Dimensional Reactive Transport Modeling of CO2 Injection in a Saline Aquifer at the Sleipner Site, North Sea, Am. J. Sci., vol. 307, no. 7, pp. 974-1008,2007.

  2. Barthelemy, J.F.M. and Haftka, R.T., Approximation Concepts for Optimum Structural Design-A Review, Struct. Optimiz., vol. 5, no. 3, pp. 129-144,1993.

  3. Basu, S., Kumbier, K., Brown, J.B., and Yu, B., Iterative Random Forests to Discover Predictive and Stable High-Order Interactions, Proc. Nat. Acad. Sci., vol. 115, no. 8, pp. 1943-1948,2018.

  4. Bea, S.A., Wainwright, H., Spycher, N., Faybishenko, B., Hubbard, S.S., and Denham, M.E., Identifying Key Controls on the Behavior of an Acidic-U (VI) Plume in the Savannah River Site Using Reactive Transport Modeling, J. Contam. Hydrol, vol. 151, pp. 34-54,2013.

  5. Bianchi, M., Zheng, L., and Birkholzer, J.T., Combining Multiple Lower-Fidelity Models for Emulating Complex Model Responses for CCS Environmental Risk Assessment, Int. J. Greenhouse Gas Contr., vol. 46, pp. 248-258,2016.

  6. Booker, D. and Woods, R., Comparing and Combining Physically-Based and Empirically-Based Approaches for Estimating the Hydrology of Ungauged Catchments, J. Hydrol., vol. 508, pp. 227-239, 2014.

  7. Breiman, L., Random Forests, Mach. Learn., vol. 45, no. 1, pp. 5-32,2001.

  8. Breiman, L., Friedman, J., Stone, C.J., and Olshen, R.A., Classification and Regression Trees, Boca Raton, FL: CRC press, 1984.

  9. Chaturantabut, S. and Sorensen, D.C., Nonlinear Model Reduction via Discrete Empirical Interpolation, SIAMJ. Sci. Comput, vol. 32, no. 5, pp. 2737-2764,2010.

  10. Chollet, F., Keras, accessed from https://keras.io, 2015.

  11. Ermakova, D., Wainwright, H., Zheng, L., Shirley, I., and Lu, H., Global Sensitivity Analysis for U(VI) Transport for Integrating Coupled Thermal-Hydrological-Chemical Processes Models into Performance Assessment Model, ASMEJ. Nuclea. Rad. Sci, vol. 7, no. 4, p. 041902,2020.

  12. Forrester, A.I.J. and Keane, A.J., Recent Advances in Surrogate-Based Optimization, Progr. Aerosp. Sci., vol. 45, nos. 1-3, pp. 50-79,2009.

  13. Friedman, J., Hastie, T., and Tibshirani, R., The Elements of Statistical Learning, vol. 1, New York, NY: Springer, 2001.

  14. He, K., Zhang, X., Ren, S., and Sun, J., Delving Deep into Rectifiers: Surpassing Human-Level Performance on Imagenet Classification, in Proc. of the IEEE Int. Conf. on Computer Vision, pp. 1026-1034, 2015.

  15. He, K., Zhang, X., Ren, S., and Sun, J., Deep Residual Learning for Image Recognition, in Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, pp. 770-778,2016.

  16. Hesthaven, J.S. andUbbiali, S.,Nonintrusive Reduced Order Modeling of Nonlinear Problems Using Neural Networks, J. Comput. Phys, vol. 363, pp. 55-78,2018.

  17. Ho, T.K., A Data Complexity Analysis of Comparative Advantages of Decision Forest Constructors, Pattern Anal. Appl., vol. 5, no. 2, pp. 102-112,2002.

  18. Hornik, K., Approximation Capabilities of Multilayer Feedforward Networks, Neural Net., vol. 4, no. 2, pp. 251-257,1991.

  19. Izmailov, P., Podoprikhin,D., Garipov, T., Vetrov, D., and Wilson, A.G., Averaging Weights Leads to Wider Optima and Better Generalization, 2018. arXiv: 1803.05407.

  20. Kerschen, G., Golinval, J.C., Vakakis, A.F., and Bergman, L.A., The Method of Proper Orthogonal Decom-position for Dynamical Characterization and Order Reduction of Mechanical Systems: An Overview, Nonlinear Dyna., vol. 41, nos. 1-3, pp. 147-169,2005.

  21. Korneev, S. and Battiato, I., Sequential Homogenization of Reactive Transport in Polydisperse Porous Media, Multiscale Model. Simul, vol. 14, no. 4, pp. 1301-1318,2016.

  22. Krogh, A. and Vedelsby, J., Neural Network Ensembles, Cross Validation, and Active Learning, Adv. Neural Inform. Proc. Sys., pp. 231-238,1995.

  23. Kutz, J.N., Brunton, S.L., Brunton, B.W., and Proctor, J.L., Dynamic Mode Decomposition: Data-Driven Modeling of Complex Systems, Philadelphia, PA: SIAM, 2016.

  24. Lichtner, P.C. and Tartakovsky, D.M., Stochastic Analysis of Effective Rate Constant for Heterogeneous Reactions, Stoch. Environm. Res. Risk Assess., vol. 17, no. 6, pp. 419-429,2003.

  25. Lucia, D.J., Beran, P.S., and Silva, W.A., Reduced-Order Modeling: New Approaches for Computational Physics, Progr. Aerosp. Sci., vol. 40, nos. 1-2, pp. 51-117,2004.

  26. Maday, Y. and Mula, O., A Generalized Empirical Interpolation Method: Application of Reduced Basis Techniques to Data Assimilation, in Analysis and Numerics of Partial Differential Equations, Berlin, Germany: Springer, pp. 221-235,2013.

  27. Naghibi, S.A., Pourghasemi, H.R., and Dixon, B., GIS-Based Groundwater Potential Mapping Using Boosted Regression Tree, Classification and Regression Tree, and Random Forest Machine Learning Models in Iran, Environ. Monitor. Assess., vol. 188, no. 1, p. 44,2016.

  28. Neuman, S.P. and Tartakovsky, D.M., Perspective on Theories of Nonfickian Transport in Heterogeneous Media, Adv. Water Res, vol. 32, no. 5, pp. 670-680,2009.

  29. Opitz, D. and Maclin, R., Popular Ensemble Methods: An Empirical Study, J. Artif. Intel. Res., vol. 11, pp. 169-198,1999.

  30. Pau, G.S.H., Zhang, Y., and Finsterle, S., Reduced Order Models for Many-Query Subsurface Flow Applications, Comput. Geosci., vol. 17, no. 4, pp. 705-721,2013.

  31. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E., Scikit-Learn: Machine Learning in Python, J. Mach. Learn. Res, vol. 12, pp. 2825-2830,2011.

  32. Pinkus, A., Approximation Theory of the MLP Model in Neural Networks, Acta Numer., vol. 8, no. 1, pp. 143-195,1999.

  33. Polikar, R., Ensemble Based Systems in Decision Making, IEEE Circ. Sys. Mag., vol. 6, no. 3, pp. 21-45, 2006.

  34. Qin, T., Chen, Z., Jakeman, J., and Xiu, D., Data-Driven Learning of Nonautonomous Systems, 2020. arXiv: 2006.02392.

  35. Qin, T., Wu, K., and Xiu, D., Data Driven Governing Equations Approximation Using Deep Neural Networks, J. Comput. Phys, vol. 395, pp. 620-635,2019.

  36. Rasmussen, C.E., Gaussian Processes in Machine Learning, Summer School on Machine Learning, Berlin, Germany: Springer, pp. 63-71,2003.

  37. Razavi, S., Tolson, B.A., and Burn, D.H., Review of Surrogate Modeling in Water Resources, Water Res. Res., vol. 48, no. 7, 2012.

  38. Rokach, L., Ensemble-Based Classifiers, Artif. Intel. Rev, vol. 33, nos. 1-2, pp. 1-39,2010.

  39. Rowley, C.W., Model Reduction for Fluids, Using Balanced Proper Orthogonal Decomposition, Int. J. Bifurcat. Chaos, vol. 15, no. 3,pp. 997-1013,2005.

  40. Rutqvist, J., Zheng, L., Chen, F., Liu, H.H., and Birkholzer, J., Modeling of Coupled Thermo-Hydro-Mechanical Processes with Links to Geochemistry Associated with Bentonite-Backfilled Repository Tunnels in Clay Formations, RockMech. Rock Eng., vol. 47, no. 1, pp. 167-186,2014.

  41. Saridakis, K.M. and Dentsoras, A.J., Soft Computing in Engineering Design-A Review, Adv. Eng. Inform, vol. 22, no. 2, pp. 202-221,2008.

  42. Schmid, P. J., Dynamic Mode Decomposition ofNumerical and Experimental Data, J. FluidMech, vol. 656, pp. 5-28,2010.

  43. Schmit, L., Jr. and Farshi, B., Some Approximation Concepts for Structural Synthesis, AIAA J, vol. 12, no. 5, pp. 692-699,1974.

  44. Simpson, T.W., Poplinski, J., Koch, P.N., and Allen, J.K., Metamodels for Computer-Based Engineering Design: Survey and Recommendations, Eng. Comput., vol. 17,no.2,pp. 129-150,2001.

  45. Steefel, C.I., Appelo, C.A.J., Arora, B., Jacques, D., Kalbacher, T., Kolditz, O., Lagneau, V., Lichtner, P.C., Mayer, K.U., Meeussen, J.C.L., Reactive Transport Codes for Subsurface Environmental Simulation, Comput. Geosci, vol. 19, no. 3,pp. 445-478,2015.

  46. Steefel, C.I., DePaolo, D.J., and Lichtner, P.C., Reactive Transport Modeling: An Essential Tool and a New Research Approach for the Earth Sciences, Earth Planet. Sci. Lett., vol. 240, nos. 3-4, pp. 539-558, 2005.

  47. Tavenard, R., Faouzi, J., Vandewiele, G., Divo, F., Androz, G., Holtz, C., Payne, M., Yurchak, R., RuBwurm, M., Kolar, K., and Woods, E., Tslearn, a Machine Learning Toolkit for Time Series Data, J. Mach. Learn. Res., vol. 21, no. 118, pp. 1-6,2020.

  48. Tripathy, R.K. and Bilionis, I., Deep UQ: Learning Deep Neural Network Surrogate Models for High Dimensional Uncertainty Quantification, J. Comput. Phys., vol. 375, pp. 565-588,2018.

  49. Xiong, Y., Fakcharoenphol, P., Winterfeld, P., Zhang, R., and Wu, Y.S., Coupled Geomechanical and Reactive Geochemical Model for Fluid and Heat Flow: Application for Enhanced Geothermal Reservoir, SPE Reservoir Characterization and Simulation Conf. and Exhibition, Society of Petroleum Engineers, 2013.

  50. Xu, T., Sonnenthal, E., Spycher, N., and Zheng, L., TOUGHREACT V3. 0-0MP Reference Manual: A Parallel Simulation Program for Non-Isothermal Multiphase Geochemical Reactive Transport, University of California, Berkeley, CA, 2014.

  51. Zheng, L., Rutqvist, J., Xu, H., and Birkholzer, J.T., Coupled THMC Models for Bentonite in an Argillite Repository for Nuclear Waste: Illitization and Its Effect on Sweling Stress under High Temperature, Eng. Geol., vol. 230, pp. 118-129,2017.

  52. Zhou, Z. and Tartakovsky, D.M., Markov Chain Monte Carlo with Neural Network Surrogates: Application to Contaminant Source Identification, Stoch. Env. Res. Risk Assess., 2020.

  53. Zhu,R.,Zeng,D., and Kosorok,M.R., Reinforcement Learning Trees, J. Am. Stat. Assoc., vol. 110, no. 512, pp. 1770-1784,2015.

  54. Zhu, Y., Zabaras, N., Koutsourelakis, P.S., and Perdikaris, P., Physics-Constrained Deep Learning for High-Dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data, J. Comput. Phys.., vol. 394, pp. 56-81,2019.

CITADO POR
  1. Degen Denise, Cacace Mauro, Wellmann Florian, 3D multi-physics uncertainty quantification using physics-based machine learning, Scientific Reports, 12, 1, 2022. Crossref

Portal Digitalde Biblioteca Digital eLibros Revistas Referencias y Libros de Ponencias Colecciones Precios y Políticas de Suscripcione Begell House Contáctenos Language English 中文 Русский Português German French Spain