Application of the Adam Gradient Descent Optimizer (AGDO) for One-Dimensional Magnetotelluric (MT) Data Inversion
DOI:
https://doi.org/10.22373/p-jpft.v12i2.34593Keywords:
Electromagnetic, Magnetotelluric, Inverse Modelling, Resistivity, Adam Gradient Descent OptimizerAbstract
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
Issue
Section
License
Copyright (c) 2026 M. Fadhilah Al Yasir Harahap, Selvi Misnia Irawati, Wahyu Eko Junian

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with Jurnal Phi agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).

