One-Dimensional Modeling of Magnetotelluric Data using Convolutional Neural Network-Gated Recurrent Unit Based Inversion and Its Implementation on Field Data

Authors

  • Achmad Aulia Fikri Earth Physics and Complex Systems Research Group, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Jalan Ganesha 10, Bandung 40132
  • Nurhasan Earth Physics and Complex Systems Research Group, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Jalan Ganesha 10, Bandung 40132
  • Marshanda Adisti Rahmadini Earth Physics and Complex Systems Research Group, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Jalan Ganesha 10, Bandung 40132
  • Auza Naufal Abraar Earth Physics and Complex Systems Research Group, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Jalan Ganesha 10, Bandung 40132
  • Hamzah Firoos Fauzi Earth Physics and Complex Systems Research Group, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Jalan Ganesha 10, Bandung 40132
  • Dini Fitriani Department of Geophysics, Faculty of Mathematics and Natural Sciences, University of Padjadjaran, Bandung 45363, Indonesia

DOI:

https://doi.org/10.21009/SPEKTRA.102.04

Keywords:

one-dimensional inversion, magnetotellurics, convolutional neural network, gated recurrent unit

Abstract

The magnetotelluric method is a geophysical method that utilizes natural variations in the electromagnetic field to map the resistivity distribution beneath the surface. In this method, inversion is the primary process used to estimate the resistivity structure from field data. This study proposes a deep learning-based approach for one-dimensional magnetotelluric inversion, combining Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) as an alternative inversion method. The dataset consists of 20 layers with resistivity and thickness values randomly selected within a specific range at 4000 meters depths and a probability value. Apparent resistivity and phase are obtained through forward modeling based on selected resistivity and thicknesses as input, while the resistivity structure is used as output, with a large data sample. The dataset was standardized and normalized using a logarithmic scale and the MinMax method to map values into the 0-1 range. The dataset was used to train the proposed CNN-GRU model, which is capable of mapping the resistivity distribution in the subsurface. The results show that the CNN-GRU model could map the resistivity distribution model and predict its thicknesses with small error based on the apparent resistivity and phase data, indicating that it can be used for one-dimensional inversion in magnetotellurics. Nevertheless, the model performed quite well on several field datasets, showing a good fit between predicted and true values.

References

F. Simpson and K. Bahr, “Practical magnetotellurics,” Pract. Magnetotellurics, vol. 9780521817, pp. 1–254, 2005, doi: 10.1017/CBO9780511614095.

Nurhasan, D. Sutarno, W. Srigutomo, S. Viridi, and D. Fitriani, “Integrated geophysical measurements for subsurface mapping at Papandayan volcano, Garut, Indonesia (preliminary result),” 2012, pp. 154–157. doi: 10.1063/1.4730710.

D. Diba, Nurhasan, D. Sutarno, and Y. Ogawa, “Subsurface Structure around Mas Crater of Papandayan Volcano based on Magnetotelluric and Geomagnetic Data,” J. Phys. Conf. Ser., vol. 1949, no. 1, p. 012013, Jun. 2021, doi: 10.1088/1742-6596/1949/1/012013.

N. Nurhasan et al., “Analysis of Subsurface Resistivity Distribution of the Kelud Volcano Using Magnetotelluric Method,” J. Phys. Conf. Ser., vol. 2733, no. 1, p. 012020, Mar. 2024, doi: 10.1088/1742-6596/2733/1/012020.

E. J. Mustopa, Nurhasan, W. Srigutomo, and D. Sutarno, “Resistivtiy Structure in Tangkuban Parahu Area Drived from CSAMT Data,” J. Phys. Conf. Ser., vol. 877, p. 012055, Jul. 2017, doi: 10.1088/1742-6596/877/1/012055.

E. J. Mustopa, D. Sutarno, Nurhasan, A. R. Naulia, M. L. Baskoro, and N. S. Asih, “Subsurface structure of Tangkuban Parahu area derived from CSAMT and gravity investigation,” J. Phys. Conf. Ser., vol. 1080, p. 012049, Aug. 2018, doi: 10.1088/1742-6596/1080/1/012049.

M. R. Naufal and N. Nurhasan, “2D Magnetotelluric Resistivity Structure Modeling Using Finite Element Method Based on Vector Triangular Grid and Its Application to Lembang Fault MT Data,” J. Phys. Conf. Ser., vol. 2866, no. 1, p. 012067, Oct. 2024, doi: 10.1088/1742-6596/2866/1/012067.

Nurhasan et al., “Resistivity Distribution of Lembang Fault Based on Magnetotelluric Data,” J. Phys. Conf. Ser., vol. 2734, no. 1, p. 012014, Mar. 2024, doi: 10.1088/1742-6596/2734/1/012014.

L. Y. Roodhiyah et al., “Interpretation of a 3D Magnetotellurics Model of the Aceh and Seulimeum Segments of the Sumatran Fault Zone,” Appl. Sci., vol. 14, no. 23, p. 11335, Dec. 2024, doi: 10.3390/app142311335.

Nurhasan et al., “Resistivity structure of Sumatran Fault (Aceh segment) derived from 1-D magnetotelluric modeling,” 2012, pp. 150–153. doi: 10.1063/1.4730709.

Nurhasan, N. D. Setyo Risky, A. Pratama, I. Zahra, and Y. Ogawa, “Analysis of subsurface Resistivity Structures in Relation to the Level of Damage Caused by Earthquakes Using the Audio-Magnetotelluric (AMT) Method (Case study: the 2006 Yogyakarta Earthquake),” J. Phys. Conf. Ser., vol. 2866, no. 1, p. 012072, Oct. 2024, doi: 10.1088/1742-6596/2866/1/012072.

A. Susilawati et al., “Resistivity and Density Structure of Limboto Lake—Pentadio, Gorontalo, Indonesia Based on Magnetotelluric and Gravity Data,” Appl. Sci., vol. 13, no. 1, p. 644, Jan. 2023, doi: 10.3390/app13010644.

Nurhasan et al., “Dimensionality analysis using phase tensor and induction vector on magnetotelluric data in Tomori Region, Central Sulawesi,” 2023, p. 050003. doi: 10.1063/5.0164138.

H. Zhou et al., “Super-resolution magnetotelluric data inversion with seismic texture constraint,” GEOPHYSICS, vol. 90, no. 3, pp. WA153–WA168, May 2025, doi: 10.1190/geo2024-0113.1.

W. Wei, Z. Hu, Z. Zhang, H. Zhang, S. Xu, and R. Zhang, “Application of MT data in the study of ultra-deep basement structure of Precambrian in Tarim Basin,” in SEG 1st Tarim Ultra-Deep Oil & Gas Exploration Technology Workshop, Korla, China, June 3-5, 2024, Aug. 2024, pp. 113–116. doi: 10.1190/Ultra-Deep2024-030.1.

H. Grandis, Introduction to Geophysical Inversion Modeling. Bandung: Indonesian Association of Geophysicists (HAGI), 2009.

J. Ding, H. Chen, Y. Feng, and T. Hossain, “Applications of Deep Learning Techniques,” Electronics, vol. 13, no. 17, p. 3354, Aug. 2024, doi: 10.3390/electronics13173354.

E. Grossi and M. Buscema, “Introduction to artificial neural networks,” Eur. J. Gastroenterol. Hepatol., vol. 19, no. 12, pp. 1046–1054, Dec. 2007, doi: 10.1097/MEG.0b013e3282f198a0.

I. D. Mienye, T. G. Swart, and G. Obaido, “Recurrent Neural Networks: A Comprehensive Review of Architectures, Variants, and Applications,” Information, vol. 15, no. 9, p. 517, Aug. 2024, doi: 10.3390/info15090517.

T. Ren et al., “Seismic severity estimation using convolutional neural network for earthquake early warning,” Geophys. J. Int., vol. 234, no. 2, pp. 1355–1362, Mar. 2023, doi: 10.1093/gji/ggad137.

J. Huang et al., “Implementation of Deep Convolutional Neural Network to Reconstruct Subsurface Resistivity Using Gramian Angular Field for Airborne Electromagnetic System,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 18, pp. 10374–10387, 2025, doi: 10.1109/JSTARS.2025.3550437.

L. Tao, Z. Gu, and H. Ren, “Improving the Seismic Impedance Inversion by Fully Convolutional Neural Network,” J. Mar. Sci. Eng., vol. 13, no. 2, p. 262, Jan. 2025, doi: 10.3390/jmse13020262.

M. I. Khatami and H. Grandis, “One-dimensional magnetotelluric (MT) data inversion modeling using convolutional neural network,” IOP Conf. Ser. Earth Environ. Sci., vol. 1227, no. 1, p. 012023, Aug. 2023, doi: 10.1088/1755-1315/1227/1/012023.

X. Liao, Z. Zhang, Q. Yan, Z. Shi, K. Xu, and D. Jia, “Inversion of 1-D magnetotelluric data using CNN-LSTM hybrid network,” Arab. J. Geosci., vol. 15, no. 17, p. 1430, Sep. 2022, doi: 10.1007/s12517-022-10687-1.

A. Saxena, “An Introduction to Convolutional Neural Networks,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 10, no. 12, pp. 943–947, 2022, doi: 10.22214/ijraset.2022.47789.

J. Rala Cordeiro, A. Raimundo, O. Postolache, and P. Sebastião, “Neural Architecture Search for 1D CNNs—Different Approaches Tests and Measurements,” Sensors, vol. 21, no. 23, p. 7990, Nov. 2021, doi: 10.3390/s21237990.

W. N. Ismail, H. A. Alsalamah, M. M. Hassan, and E. Mohamed, “AUTO-HAR: An adaptive human activity recognition framework using an automated CNN architecture design,” Heliyon, vol. 9, no. 2, p. e13636, Feb. 2023, doi: 10.1016/j.heliyon.2023.e13636.

J. Chen, X. Huang, H. Jiang, and X. Miao, “Low-Cost and Device-Free Human Activity Recognition Based on Hierarchical Learning Model,” Sensors, vol. 21, no. 7, p. 2359, Mar. 2021, doi: 10.3390/s21072359.

K. Cho et al., “Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation,” in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014, pp. 1724–1734. doi: 10.3115/v1/D14-1179.

H. Grandis, “An alternative algorithm for one-dimensional magnetotelluric response calculation,” Comput. Geosci., vol. 25, no. 2, pp. 119–125, 1999, doi: 10.1016/S0098-3004(98)00110-1.

Downloads

Published

2025-08-31

How to Cite

Fikri, A. A., Nurhasan, Rahmadini, M. A., Abraar, A. N., Fauzi, H. F., & Fitriani, D. (2025). One-Dimensional Modeling of Magnetotelluric Data using Convolutional Neural Network-Gated Recurrent Unit Based Inversion and Its Implementation on Field Data. Spektra: Jurnal Fisika Dan Aplikasinya, 10(2), 115–126. https://doi.org/10.21009/SPEKTRA.102.04

Issue

Vol. 10 No. 2 (2025): SPEKTRA: Jurnal Fisika dan Aplikasinya, Volume 10 Issue 2, August 2025

Section

Articles

License

Copyright (c) 2025 Achmad Aulia Fikri, Nurhasan, Marshanda Adisti Rahmadini, Auza Naufal Abraar, Hamzah Firoos Fauzi, Dini Fitriani

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

SPEKTRA: Jurnal Fisika dan Aplikasinya allow the author(s) to hold the copyright without restrictions and  allow the author(s) to retain publishing rights without restrictions. SPEKTRA: Jurnal Fisika dan Aplikasinya CC-BY or an equivalent license as the optimal license for the publication, distribution, use, and reuse of scholarly work. In developing strategy and setting priorities, SPEKTRA: Jurnal Fisika dan Aplikasinya recognize that free access is better than priced access, libre access is better than free access, and libre under CC-BY or the equivalent is better than libre under more restrictive open licenses. We should achieve what we can when we can. We should not delay achieving free in order to achieve libre, and we should not stop with free when we can achieve libre.

SPEKTRA: Jurnal Fisika dan Aplikasinya is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
Share - copy and redistribute the material in any medium or format
Adapt - remix, transform, and build upon the material for any purpose, even commercially.
The licensor cannot revoke these freedoms as long as you follow the license terms.