Abstract
The magnetotelluric (MT) inversion is nonlinear and ill-posed, which poses great challenges for accurate model reconstruction. To tackle these challenges, in this study, a novel method using a deep neural network for inversion of 1-D MT data is proposed. The proposed network structure combines a convolutional neural network (CNN) for features extraction and a long short-term memory (LSTM) network for resistivity model reconstruction. The implementation of this method consists of three phases. In the dataset acquisition phase, a random sample generation scheme is proposed to ensure a sufficient number and diversity of datasets. In the training phase, an error back-propagation scheme is adopted to update the network parameters to extract and store the complex nonlinear relationship between the models and MT responses. After that, the unknown model can be reconstructed from the MT data using the trained network. Synthetic and field data are considered to verify this method. The corresponding results show that the method proposed in this paper is computationally efficient and has high inversion precision.
Similar content being viewed by others
References
Araya Polo M, Jennings J, Adler A (2018) Deep Learning Tomography. Leading Edge 37(1):58–66
Constable SC, Parker RL, Constable CG (1987) Occam’s inversion: a practical algorithm for generating smooth models from EM sounding data. Geophysics 52(3):289–300
Cui YA, Zhang L, Zhu X, Liu JX, Guo ZW (2020) Inversion for magnetotelluric data using the particle swarm optimization and regularized least squares. J Appl Geophys 181:104156
De Groot-hedlin C, Constable SC (1990) Occam’s inversion to generate smooth, two-dimensional models from magnetotelluric data. Geophysics 55:1613–1624
Deng Z, Chen Y, Liu Y, Kim KC (2019) Time-resolved turbulent velocity field reconstruction using a long short-term memory (LSTM)-based artificial intelligence framework. Phys Fluids 31(7):075108
Ghaedrahmati R, Moradzadeh A, Fathianpour N, Lee SK, Porkhial S (2013) 3-D inversion of MT data from the Sabalan geothermal field, Ardabil. Iran J Appl Geophys 93:12–24
Grandis H (1999) An alternative algorithm for one-dimensional magnetotelluric response calculation. Comput Geosci 25:119–125
Heinson GS, Direen NG, Gill RM (2006) Magnetotelluric evidence for a deep-crustal mineralizing system beneath the Olympic Dam iron oxide copper-gold deposit, southern Australia. Geology 34(7):573–576
Hoversten GM, Myer D, Key K, Alumbaugh D, Hermann O, Hobbet R (2015) Field test of sub-basalt hydrocarbon exploration with marine controlled source electromagnetic and magnetotelluric data. Geophys Prospect 63:1284–1310
Huang L, Dong X, Clee TE (2017) A scalable deep learning platform for identifying geologic fearures from seismic attributes. Lead Edge 36(3):249–256
Klaus G, Rupesh KS, Jan K, Bas RS, Jurgen S (2016) LSTM: A Search Space Odyssey. IEEE Trans Neural Netw Learn Syst 28(10):2222–2232
Li JF, Liu YH, Yin CC, Ren X, Su Y (2020) Fast imaging of time-domain airborne EM data using deep learning technology. Geophysics 85(5):163–170
Liu B, Guo Q, Li SC, Liu B, Ren Y, Pang Y, Guo X, Liu L, Jiang P (2020) Deep learning inversion of electrical resistivity data. IEEE Trans Geosci Remote Sens 58(8):5715–5728
Louise P, Jeffrey MJ, Gerald WH (1996) A numerical evaluation of electromagnetic methods in geothermal exploration. Geophysics 61:121–130
Mccann MT, Jin KH, Unser M (2017) Convolutional neural networks for inverse problems in imaging: a review. IEEE Signal Process Mag 34(6):85–95
Moghadas D (2020) One-dimensional deep learning inversion of electromagnetic induction data using convolutional neural network. Geophys J Int 222(1):247–259
Mosser L, Dubrule O, Blunt MJ (2018) Stochastic reconstructuion of an oolitic limestone by generative adversarial network. Transp Porous Media 125(1):81–203
Puzyrev V, Swidinsky A (2020) Inversion of 1D frequency- and time-domain electromagnetic data with convolutional neural networks. Computer & Geosciences 149:104681
Rodi W, Mackie RL (2001) Nonlinear conjugate gradients algorithm for 2-D magnetotelluric inversion. Geophysics 66(1):174–187
Sepp H, Jürgen S (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Siripunvaraporn W, Egbert G (2000) An efficient data-subspace inversion method for 2-D magnetotelluric data. Geophysics 65(3):791–803
Smith JT, Boober JR (1991) Rapid inversion of two-and three-dimensional magnetotelluric data. Chin J Geophys 96(B3):3905–3922
Souza JFL, Santos MD, Magalhaes RM, Neto EM, Oliveira GP, Roque WL (2019) Autosmatic classification of hydrocarbon “lead” in seismic images through artificial and convolutional neural networks. Comput Geosice 132:23–32
Sudakov O, Burnaev E, Koroteev D (2019) Driving digital rock towards machine learning: prediting permeability with gradient boosting and deep neural networks. Comput Geosci 127:91–98
Ueda T, Mitsuhata Y, Uchida T, Marui A, Ohsawa K (2014) A new marine magnetotelluric measurement system in a shallow-water environment for hydrogeological study. J Appl Geophys 100:23–31
Wang Y, Li H (2018) A novel intelligent modeling framework integrating convolutional neural network with an adaptive time-series window and its application to industrial process operational optimization. Chemom Intell Lab Syst 179:64–72
Wang J, Wang W, Wen G (2018) Multi-scale deep alternative neural network for large-scale video classification. IEEE Trans Multimedia 99:1–1
Wang H, Liu W, Xi ZZ (2019) Nonlinear inversion for magnetotelluric sounding based on deep belief network. J Central South Univ 26(9):2482–2494
Wei WB, Unsworth M, Jones A, Booker J, Tan HD (2001) Detection of widespread fluids in the tibetan crust by magnetotelluric studies. Science 292(5517):716–719
Wei Y, Wei X, Min L, Huang J, Ni B, Jian D, Yao Z, Yan S (2016) HCP: A flexible CNN framework for multi-label image classification. IEEE Trans Software Eng 38(9):1901–1907
Wu Y, Lin Y, Zhou Z (2018) InversionNet: Accurate and efficient seismic waveform inversion with convolutional neural networks. SEG Technical Program Expanded Abstracts 2018. Society of Exploration Geophysicists, Tulsa, OK, USA, pp 2096–2100
Wu X, Liang L, Shi Y, Fomel S (2019) FaultSeg3D: Using synthetic data sets to train an end-toend concolutional neural network for 3D seismic fault segmentation. Geophysics 84(3):35–45
Yamamoto K, Hiromatsu R, Ohtsuki T (2020) ECG signal reconstruction via Doppler sensor by hybrid deep learning model with CNN and LSTM. IEEE Access 8:130551–130560
Yu SW, Ma JW, Wang WL (2019) Deep learning for denoising. Geophysics 84(6):333–350
Yuan SY, Liu JW, Wang SX, Wang T, Shi P (2018) Seismic waveform classification and first-break picking using convolution neural networks. IEEE Geosci Remote Sens Lett 15(2):272–276
Zhang K, Wei WB, Lu QT, Dong H, Li YQ (2014) Theoretical assessment of 3-D magnetotelluric method for oil and as exploration:synthetic examples. J Appl Geophys 106:23–36
Zhang ZH, Liao XL, Cao YY, Hou ZL, Fan XT, Xu ZX, Lu RQ, Feng T, Yao Y, Shi ZY (2021) Joint gravity and gravity gradient inversion based on deep learning. Chin J Geophys 64(4):1435–1452
Funding
This work was financially supported by the National Key Research and Development Program of China (No. 2018YFC1505401), the Research and Development Projects of Sichuan Science and Technology Department (No. 2019YF0460,2020YGF0303,2021YJ0031), and the Technology Research and Development Program of China Railway Group Limited (No. CZ01-Key Point-05).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Responsible editor: Narasimman Sundararajan
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liao, X., Zhang, Z., Yan, Q. et al. Inversion of 1-D magnetotelluric data using CNN-LSTM hybrid network. Arab J Geosci 15, 1430 (2022). https://doi.org/10.1007/s12517-022-10687-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12517-022-10687-1