Deep-neural-networks-based approaches for Biot-squirt model in rock physics

• Autorzy: Xiong Fansheng , Liu Jiawei , Guo Zhenwei , Liu Jianxin

Identyfikatory

DOI

10.1007/s11600-022-00740-8

• Języki publikacji: EN

Abstrakty

EN

A new cost-effective surrogate model using deep neural network (DNN) for seismic wave propagation in rocks saturated with fluid is presented. In this field, the dispersion/attenuation analysis and wave-field simulation are two key measurements which can be carried out by solving wave equations. The Biot–squirt (BISQ) equation is a classical wave propagation model in geophysical forward modeling and has been widely used. The solution of such equation, especially by numerical method, is often complex and time-consuming. In this work, a DNN model is trained with the dataset of velocity and inverse quality factor generated from BISQ model. The results show that the relative mean square error between the predictions of DNN model and that of BISQ model on the test sets are all less than 3%. It indicates that the DNN model has learned the high-dimensional space well and then can realize the dispersion/attenuation analysis for any given rock physical parameters. Besides, the other well-trained DNN model is used to obtain the simulation results with second-order accuracy according to results by finite difference scheme with first-order accuracy. It reveals that the fast wave-field simulation can be implemented once the results with lower accuracy are obtained.

Słowa kluczowe

EN

wave propagation model; deep neural network; training; test; dispersion; attenuation; numerical simulation

PL

model propagacji fali; głęboka sieć neuronowa; szkolenie; test; dyspersja; tłumienie; symulacja numeryczna

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2022
• Tom: Vol. 70, no 2
• Strony: 593--607
• Opis fizyczny: Bibliogr. 35 poz.

Twórcy

autor

Xiong Fansheng

• Institute of Applied Physics and Computational Mathematics, Beijing, China
• Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring (Central South University), Ministry of Education, Changsha 410083, China

autor

Liu Jiawei

• Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring (Central South University), Ministry of Education, Changsha 410083, China
• School of Geosciences and Info-Physics, Central South University, Changsha 410083, China
• Advanced Institute for Materials Research, Tohoku University, Sendai 980-8577, Japan

• https://orcid.org/0000-0001-5168-6039

autor

Guo Zhenwei

• Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring (Central South University), Ministry of Education, Changsha 410083, China
• School of Geosciences and Info-Physics, Central South University, Changsha 410083, China

autor

Liu Jianxin

• Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring (Central South University), Ministry of Education, Changsha 410083, China
• School of Geosciences and Info-Physics, Central South University, Changsha 410083, China
• Hunan Key Laboratory of Nonferrous Resources and Geological Hazard Exploration, Changsha 410083, China

Bibliografia

• 1. Agarwal S, Tosi N, Breuer D, Padovan S, Kessel P, Montavon G (2020) A machine-learning-based surrogate model of Mars’ thermal evolution. Geophys J Int 222(3):1656–1670
• 2. Apolinario-Arzube Ó, García-Díaz JA, Medina-Moreira J, Luna-Aveiga H, Valencia-García R (2020) Comparing deep-learning architectures and traditional machine-learning approaches for satire identification in Spanish Tweets. Mathematics 8(11):2075
• 3. Bergstra J, Bengio YJ (2012) Random search for hyper-parameter optimization. J Mach Learn Res 13(10):281–305
• 4. Biot MA (1956a) Theory of elastic waves in a fluid-saturated porous solid. 1. Low frequency range. J Acoust Soc Am 28:168–178
• 5. Biot MA (1956b) Theory of propagation of elastic waves in a fluid-saturated porous solid. II. Higher frequency range. J Acoust Soc Am 28:179–191
• 6. Carcione JM, Quiroga-Goode G (1995) Some aspects of the physics and numerical modelling of Biot compressional waves. J Comput Acoust 3(4):261–280
• 7. Carcione JM (2007) Wave fields in real media: Wave propagation in anisotropic, anelastic, porous and electromagnetic media. Elsevie, Amsterdam.
• 8. Cheng C (1993) Crack models for a transversely isotropic medium. J Geophys Res-Sol Ea 98(B1):675–684
• 9. Dvorkin J, Nur A (1993) Dynamic poroelasticity: a unified model with the squirt and the Biot mechanisms. Geophys 58(4):524–533
• 10. Dvorkin J, Mavko G, Nur A (1995) Squirt flow in fully saturated rocks. Geophys 60(1):97–107
• 11. Grill Jean-Bastien, Florian Strub, Florent Altch´e, Corentin Tallec, Pierre H Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar et al (2020) Bootstrap your own latent: A new approach to self-supervised learning. arXiv preprint arXiv:2006.07733.
• 12. He X, Hu H, Wang X (2013) Finite difference modelling of dipole acoustic logs in a poroelastic formation with anisotropic permeability. Geophys J Int 192(1):359–374
• 13. Jagtap AD, Kawaguchi K, Karniadakis GEM (2020) Adaptive activation functions accelerate convergence in deep and physics-informed neural networks. J Comput Phys 404:109136.
• 14. Kharazmi E, Zhang Z, Karniadakis GEM (2021) hp-VPINNs: Variational physics-informed neural networks with domain decomposition. Comput Method Appl M 374:113547
• 15. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980.
• 16. Li YE, Cheng AC, You N (2019) Shale anisotropy estimation from logs in vertical wells. J Geophys Res- Sol Ea 124(7):6602–6611
• 17. Liu J, Yong W (2016) Stability analysis of the Biot/squirt models for wave propagation in saturated porous media. Geophys J Int 204(1):535–543
• 18. Liu J, Yong W, Liu J, Guo Z (2020) Stable finite-difference methods for elastic wave modeling with characteristic boundary conditions. Mathematics 8(6):1039
• 19. Maiti S, Krishna Tiwari R, Kümpel H (2007) Neural network modelling and classification of lithofacies using well log data: a case study from KTB borehole site. Geophys J Int 169(2):733–746
• 20. Mavko G, Mukerji T, Dvorkin J (2020) The rock physics handbook. Cambridge University Press, Cambridge
• 21. Mehta P, Wang CH, Day AGR, Richardson C, Bukov M, Fisher CK, Schwab DJ (2019) A high-bias, low-variance introduction to Machine Learning for physicists. Phys Rep 810:1–124
• 22. Moseley B, Nissen-Meyer T, Markham A (2020) Deep learning for fast simulation of seismic waves in complex media. Solid Earth 11:1527–1549
• 23. Müller TM, Gurevich B, Lebedev M (2010) Seismic wave attenuation and dispersion resulting from wave-induced flow in porous rocks—a review. Geophys 75(5):75A147–175A164.
• 24. Nosratabadi S, Mosavi A, Duan P, Ghamisi P, Filip F, Band SS, Reuter U, Gama J, Gandomi AH (2020) Data science in economics: comprehensive review of advanced machine learning and deep learning methods. Mathematics 8(10):1799
• 25. Oostwal E, Straa M, Biehl M (2021) Hidden unit specialization in layered neural networks: ReLU vs. sigmoidal activation. Physica A 564:125517.
• 26. Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer L (2017) Automatic differentiation in pytorch. Paper presented at the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA.
• 27. Pilz M, Cotton F, Kotha SR (2020) Data-driven and machine learning identification of seismic reference stations in Europe. Geophys J Int 222(2):861–873
• 28. Rice JR, Cleary MP (1976) Some basic stress diffusion solutions for fluid-saturated elastic porous media with compressible constituents. Rev Geophys 14(2):227–241
• 29. Siahkoohi A, Louboutin M, Herrmann F (2019) Neural network augmented wave-equation simulation. arXiv preprint arXiv:00925.
• 30. Wang D (2017) A study on the rock physics model of gas reservoir in tight sandstone. Chin J Geophys 60:64–83
• 31. Xiong F, Sun W, Liu J (2020b) The stability of poro-elastic wave equations in saturated porous media. Acta Geophys 69:65–75. https://doi.org/10.1007/s11600-020-00508-y
• 32. Xiong F, Sun W, Ba J Carcione JM (2020a) Effects of fluid rheology and pore connectivity on rock permeability based on a network model. J Geophys Res Sol Ea 125(3):2019JB018857.
• 33. Yang F, Ma J (2019) Deep-learning inversion: a next-generation seismic velocity model building method. Geophys 84(4):R583–R599
• 34. Yang D, Zhang Z (2002) Poroelastic wave equation including the Biot/squirt mechanism and the solid/fluid coupling anisotropy. Wave Motion 35:223–245
• 35. You N, Li YE, Cheng A (2020) Shale anisotropy model building based on deep neural networks. J Geophys Res- Sol Ea 125(2):e2019JB019042.

Uwagi

PL

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).