Application of the Adam Gradient Descent Optimizer (AGDO) for One-Dimensional Magnetotelluric (MT) Data Inversion

Authors

  • M. Fadhilah Al Yasir Harahap Department of Geophysical Engineering, Faculty of Industrial Technology, Institut Teknologi Sumatera
  • Selvi Misnia Irawati Department of Geophysical Engineering, Faculty of Industrial Technology, Institut Teknologi Sumatera
  • Wahyu Eko Junian Department of Geophysical Engineering, Faculty of Industrial Technology, Institut Teknologi Sumatera

DOI:

https://doi.org/10.22373/p-jpft.v12i2.34593

Keywords:

Electromagnetic, Magnetotelluric, Inverse Modelling, Resistivity, Adam Gradient Descent Optimizer

Abstract

This study investigates the application of the Adam Gradient Descent Optimizer (AGDO) for one-dimensional (1D) magnetotelluric (MT) inversion. The algorithm was evaluated using a benchmark function, synthetic MT datasets generated from layered Earth models with 5% Gaussian noise, and field MT data from the Cloncurry region, Australia. For the synthetic datasets, AGDO successfully reconstructed the target resistivity structures, yielding RMSE values ranging from 0.0599 to 0.0603 across four models with different resistivity configurations. For the field datasets, the inversion produced RMSE values between 0.0225 and 0.0582, indicating good agreement between the observed and calculated responses. The ensemble of models obtained from 100 independent runs clustered around the best-fit solutions, demonstrating stable convergence and consistent inversion results despite different random initial populations. These results indicate that AGDO provides an effective and reliable optimization framework for one-dimensional MT inversion and represents a promising alternative for addressing the nonlinear and non-unique nature of the problem.

References

Baba, K., & Chave, A. D. (2005). Correction of seafloor magnetotelluric data for topographic effects during inversion. Journal of Geophysical Research: Solid Earth, 110(12), 1–16. https://doi.org/10.1029/2004JB003463

Chave, A. D., & Jones, A. G. (2021). The Magnetotelluric Method: Theory and Practice (Vol. 32, Issue 3).

Constable, S. C., Parker, R. L., & Constable, C. G. (1987). Occam’s inversion: a practical algorithm for generating smooth models from electromagnetic sounding data. Geophysics, 52(3), 289–300. https://doi.org/10.1190/1.1442303

Dell’aversana, P. (2023). Inversion of geophysical data supported by Reinforcement Learning. Bulletin of Geophysics and Oceanography, 64(1), 45–60. https://doi.org/10.4430/bgo00411

Desifatma, E., Djaja, I. G. P. F. S., Pratomo, P. M., Supriyadi, Mustopa, E. J., Evita, M., Djamal, M., & Srigutomo, W. (2024). Robust inversion of 1D magnetotelluric data using the Huber loss function. Computational Geosciences, 28(4), 629–643. https://doi.org/10.1007/s10596-024-10286-x

Goyes-Peñafiel, P., Bin Waheed, U., & Arguello, H. (2025). Physically Guided Deep Unsupervised Inversion for 1-D Magnetotelluric Models. IEEE Geoscience and Remote Sensing Letters, 22, 1–5. https://doi.org/10.1109/LGRS.2025.3528767

Grandis, H. (1999). An alternative algorithm for one-dimensional magnetotelluric response calculation. Computers and Geosciences, 25(2), 119–125. https://doi.org/10.1016/S0098-3004(98)00110-1

Grandis, H., & Maulana, Y. (2017). Particle Swarm Optimization (PSO) for Magnetotelluric (MT) 1D Inversion Modeling. IOP Conference Series: Earth and Environmental Science, 62(1). https://doi.org/10.1088/1755-1315/62/1/012033

Hu, X., Bai, N., Han, B., Peng, R., Zhou, J., Zhu, D., & Huang, G. (2025). 3D inversion algorithm of magnetotelluric data based on the solution equivalence constrain. Geophysics, 90(3), E91–E104. https://doi.org/https://doi.org/10.1190/geo2024-0252.1

Junian, W. E., Adilla, R. P., & Irawati, S. M. (2025). Implementasi Algoritma Grey Wolf Optimizer (GWO) Untuk Pemodelan Inversi 1D Data Magnetotellurik. Jurnal Geosaintek, 11(2), 197–206. https://doi.org/10.12962/j25023659.v11i2.2590

Junian, W. E., Grandis, H. (2023). Hybrid Particle Swarm Optimization and Grey Wolf Optimizer Algorithm For Controlled Source Audio- Frequency Magnetotellurics (CSAMT) One- Dimensional Inversion Modelling. Rudarsko-geološko-naftni zbornik, 38 (3), 65-80. https://doi.org/ 10.17794/rgn.2023.3.6

Junian, W. E., Styawan, Y., Prasetyo, N., Paembonan, A. Y. (2026). Applying the One-to-One-Based Optimizer (OOBO) Algorithm for One-Dimensional Inversion Modeling of Magnetotellurics Data. Pure Appl. Geophys. https://doi.org/10.1007/ s00024-026-03998-x

Kingma, D. P., & Ba, J. L. (2015). Adam: A method for stochastic optimization. 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, 1–15. https://doi.org/https://doi.org/10.48550/arXiv.1412.6980

Li, F., Wang, P., & Lu, K. (2026). Gauss-Newton inversion of ground transient electromagnetic data using COMSOL multiphysics. Scientific Reports, 16(1), 1–13. https://doi.org/10.1038/s41598-025-30438-y

Liu, W., Wang, H., Xi, Z., Zhang, R., & Huang, X. (2022). Physics-Driven Deep Learning Inversion with Application to Magnetotelluric. Remote Sensing, 14(13). https://doi.org/10.3390/rs14133218

Mirjalili, S., Mohammad, S., & Lewis, A. (2014). Advances in Engineering Software Grey Wolf Optimizer. Advances in Engineering Software, 69, 46–61. https://doi.org/10.1016/j.advengsoft.2013.12.007

Mukesh, Sarkar, K., & Singh, U. K. (2023). The joint application of a metaheuristic algorithm and a Bayesian statistics approach for uncertainty and stability assessment of nonlinear magnetotelluric data. Nonlinear Processes in Geophysics, 30(4), 435–456. https://doi.org/10.5194/npg-30-435-2023

Muttaqien, I., & Nurjaman, J. (2021). Two-dimensional inversion modeling of magnetotelluric (MT) synthetic data of a graben structure using SimPEG. Riset Geologi Dan Pertambangan, 31(1), 1–12. https://doi.org/10.14203/risetgeotam2021.v31.1121

Oryński, S., Jóźwiak, W., Nowożyński, K., & Klityński, W. (2022). Comparison of 3D, 2D, and 1D Magnetotelluric Inversion Results on the Example of Data from Fore-Sudetic Monocline. International Journal of Geophysics, 2022.

Parker, R. L. (1983). The magnetotelluric inverse problem. Most, 6, 5–25.

Pedersen, J., & Hermance, J. F. (1986). Least squares inversion of one-dimensional magnetotelluric data: An assessment of procedures employed by Brown University. Surveys in Geophysics, 8(2), 187–231. https://doi.org/10.1007/BF01902413

Poli, R., Kennedy, J., & Blackwell, T. (2007). Quantification & Assessment of the chemical form of residual gadolinium in the brain.pdf. Swarm Intell, 1, 33–57. https://doi.org/10.1007/s11721-007-0002-0

Rodi, W., & Mackie, R. L. (2001). Nonlinear conjugate gradients algorithm for 1D magnetotelluric inversion. Geophysical Prospecting for Petroleum, 66(1), 174–187. https://doi.org/10.3969/j.issn.1000-1441.2014.06.017

Simpson, F., & Bahr, K. (1997). Practical Magnetotellurics. Geophysical Journal International.

Siripunvaraporn, W. (2012). Three-Dimensional Magnetotelluric Inversion: An Introductory Guide for Developers and Users. Surveys in Geophysics, 33(1), 5–27. https://doi.org/10.1007/s10712-011-9122-6

Spies, B. R. (1989). Depth of investigation in electromagnetic sounding methods. Geophysics, 54(7), 872–888. https://doi.org/10.1190/1.1442716

Syaripudin, A., & Grandis, H. (2001). Kontribusi Fisika Indonesia. 12(2), 49–55.

Vozoff, K. (1990). Magnetotellurics: Principles and practice. Proc. Indian Acad. Sci. (Earth Planet. Sci.), 99(4), 441–471. https://doi.org/10.1258/135626203765947842

Wang, P., Chen, X., & Zhang, Y. (2023). Synthesizing magnetotelluric time series based on forward modeling. Frontiers in Earth Science, 11(February), 1–13. https://doi.org/10.3389/feart.2023.1086749

Wijaya, R. A. K., Bahri, A. S., Warnana, D. D. W., & Darmawan, A. D. (2016). Inversi 1-D Pada Data Magnetotellurik Di Lapangan X Menggunakan Metode Occam Dan Simulated Annealing. Jurnal Geosaintek, 2(2), 75. https://doi.org/10.12962/j25023659.v2i2.1920

Xia, Y., & Ji, Y. (2025). Application of a novel metaheuristic algorithm inspired by Adam gradient descent in distributed Xia, Y., Ji, Y., 2025. Application of a novel metaheuristic algorithm inspired by Adam gradient descent in distributed permutation flow shop scheduling problem. 1–61. https://doi.org/https://doi.org/10.1038/s41598-025-01678-9

Downloads

Published

2026-07-19

Issue

Section

Artikel