Geophysics, Geotechnical Engineering and Engineering Geology, Signal Processing
8
Scopus Publications
122
Scholar Citations
5
Scholar h-index
4
Scholar i10-index
Scopus Publications
TFCGAN: Nonstationary Ground-Motion Simulation in the Time–Frequency Domain Using Conditional Generative Adversarial Network (CGAN) and Phase Retrieval Methods Reza D. D. Esfahani, Fabrice Cotton, Matthias Ohrnberger, Frank Scherbaum Bulletin of the Seismological Society of America, 2023 Despite the exponential growth of the amount of ground-motion data, ground-motion records are not always available for all distances, magnitudes, and site conditions cases. Given the importance of using time histories for earthquake engineering (e.g., nonlinear dynamic analysis), simulations of time histories are therefore required. In this study, we present a model for simulating nonstationary ground-motion recordings, which combines a conditional generative adversarial network to predict the amplitude part of the time–frequency representation (TFR) of ground-motion recordings and a phase retrieval method. This model simulates the amplitude and frequency contents of ground-motion data in the TFR as a function of earthquake moment magnitude, source to site distance, site average shear-wave velocity, and a random vector called a latent space. After generating the phaseless amplitude of the TFR, the phase of the TFR is estimated by minimizing all differences between the observed and reconstructed spectrograms. The simulated accelerograms produced by the proposed method show similar characteristics to conventional ground-motion models in terms of their mean values and standard deviations for peak ground accelerations and Fourier amplitude spectral values.
Exploring the dimensionality of ground-motion data by applying autoencoder techniques Reza Dokht Dolatabadi Esfahani, Kristin Vogel, Fabrice Cotton, Matthias Ohrnberger, Frank Scherbaum, et al. Bulletin of the Seismological Society of America, 2021 In this article, we address the question of how observed ground-motion data can most effectively be modeled for engineering seismological purposes. Toward this goal, we use a data-driven method, based on a deep-learning autoencoder with a variable number of nodes in the bottleneck layer, to determine how many parameters are needed to reconstruct synthetic and observed ground-motion data in terms of their median values and scatter. The reconstruction error as a function of the number of nodes in the bottleneck is used as an indicator of the underlying dimensionality of ground-motion data, that is, the minimum number of predictor variables needed in a ground-motion model. Two synthetic and one observed datasets are studied to prove the performance of the proposed method. We find that mapping ground-motion data to a 2D manifold primarily captures magnitude and distance information and is suited for an approximate data reconstruction. The data reconstruction improves with an increasing number of bottleneck nodes of up to three and four, but it saturates if more nodes are added to the bottleneck.
An inexact augmented Lagrangian method for nonlinear dispersion-curve inversion using Dix-type global linear approximation Reza Dokht Dolatabadi Esfahani, Ali Gholami, Matthias Ohrnberger Geophysics, 2020 Dispersion-curve inversion of Rayleigh waves to infer subsurface shear-wave velocity is a long-standing problem in seismology. Due to nonlinearity and ill-posedness, sophisticated regularization techniques are required to solve the problem for a stable velocity model. We have formulated the problem as a minimization problem with nonlinear operator constraint and then solve it by using an inexact augmented Lagrangian method, taking advantage of the Haney-Tsai Dix-type relation (a global linear approximation of the nonlinear forward operator). This replaces the original regularized nonlinear problem with iterative minimization of a more tractable regularized linear problem followed by a nonlinear update of the phase velocity (data) in which the update can be performed accurately with any forward modeling engine, for example, the finite-element method. The algorithm allows discretizing the medium with thin layers (for the finite-element method) and thus omitting the layer thicknesses from the unknowns and also allows incorporating arbitrary regularizations to shape the desired velocity model. In this research, we use total variation regularization to retrieve the shear-wave velocity model. We use two synthetic and two real data examples to illustrate the performance of the inversion algorithm with total variation regularization. We find that the method is fast and stable, and it converges to the solution of the original nonlinear problem.
Sparsity-promoting method to estimate the dispersion curve of surface-wave group velocity Reza Dokht Dolatabadi Esfahani, Roohollah Askari, Ali Gholami Geophysics, 2019 Group velocity is an important characteristic of surface wave that is defined as the velocity of an envelope of frequencies. Although many studies have shown the promises of analyzing the group velocity to obtain subsurface S-wave velocity, the estimation of the group velocity is not straightforward due to the uncertainties of selecting an optimum envelope of frequencies. Conventional transformations or filtering algorithms used to define an optimum envelope usually give reasonable results just for a narrow frequency or velocity range. We introduced a new approach for the estimation of the group velocity using the sparse S transform (SST) and sparse linear Radon transform (SLRT). In SST, the width of the Gaussian window is optimally calculated by energy concentration to eliminate energy smearing in the time-frequency (TF) domain, and then the sparsity is applied to enhance the TF resolution. Compared with conventional methods for the estimation of the group velocity based on the generalized S transforms, SST does not require any adjustment to the Gaussian window and yields accurate estimates of the group velocity. We apply SST to each seismic trace of a seismic shot record to obtain a 3D cube of frequency, time, and offset. For any frequency, we obtain a common frequency gather of time and offset to which we apply SLRT to obtain the group velocity of the surface wave. Our approach is robust at calculating high-resolution distinguishable dispersion curves of the group velocity in particular when data are extremely sparse.
Accurate estimation of the group velocity of surface waves using sparse S-transform and sparse slant-stacking 79th Eage Conference and Exhibition 2017, 2017
RECENT SCHOLAR PUBLICATIONS
Seismic precursors to the Blatten, Switzerland landslide revealed by unsupervised machine learning R Esfahani, M Campillo, L Seydoux, K Nishida, G Favre‐Bulle Geophysical Research Letters 53 (10), e2025GL121175 , 2026 2026 Citations: 4
Ambient Field Analysis Using Unsupervised Machine Learning and Blind Source Separation for Groundwater Monitoring in California R Esfahani, L Seydoux, S Mao, M Campillo EGU26 , 2026 2026
Learning wave scattering properties from seismograms R Esfahani, M Bracale, L Seydoux, M Campillo Journal of Geophysical Research: Machine Learning and Computation 3 (1 … , 2026 2026 Citations: 2
Embedding seismic scattering from seismograms R Esfahani, M Bracale, L Seydoux, M Campillo EarthArXiv , 2025 2025 Citations: 1
Improving the Safety Level of Electricity Infrastructure in Border Provinces with the Aim of Reducing Vulnerability and Increasing Resilience R Esfahani 2024
Temporal variations of the ‘ in-situ ’ nonlinear behaviour of shallow sediments during the 2016 Kumamoto Earthquake sequence R Esfahani, F Cotton, LF Bonilla Geophysical Journal International 238 (3), 1626-1637 , 2024 2024 Citations: 7
Detailed clustering of continuous seismic waveforms with deep scattering networks: a case study on the Ridgecrest earthquake sequence R Esfahani, M Campillo, L Seydoux, S Mouaoued, QY Wang European Geosciences Union General Assembly 2024 (EGU24), 6371 , 2024 2024
Revealing and interpreting patterns from continuous seismic data with unsupervised learning L Seydoux, R Steinmann, S Mouaoued, R Esfahani, M Campillo European Geosciences Union General Assembly 2024 (EGU24), 8924 , 2024 2024 Citations: 2
Failures, successes and challenges of machine-learning-based engineering ground-motion models F Cotton, R Esfahani, H Lilienkamp European Geosciences Union General Assembly 2024 (EGU24), 12197 , 2024 2024
TFCGAN package: Conditional Generative Models in Time-Frequency domain for Ground motion simulation R Esfahani, R Zaccarelli GFZ Data Service , 2024 2024
TFCGAN: Nonstationary ground‐motion simulation in the time–frequency domain using conditional generative adversarial network (CGAN) and phase retrieval methods RDD Esfahani, F Cotton, M Ohrnberger, F Scherbaum Bulletin of the Seismological Society of America 113 (1), 453-467 , 2023 2023 Citations: 47
Steganography Audio Based on Zero-Tree Wavelet Transform Algorithm R Esfahani, AR Matinfar Scientific Journal of Passive Defence 14 (3) , 2023 2023
Predicting time-histories using machine learning and hybrid-datasets (simulations and observations) R Esfahani, F Cotton, F Scherbaum, M Ohrnberger XXVIII General Assembly of the International Union of Geodesy and Geophysics … , 2023 2023
Prediction of Near-Field Time-Histories Using Machine Learning and a Hybrid Dataset (Calibrated Physics-Based Ground-Motion Simulations and Observations) R Esfahani, F Cotton, F Scherbaum, M Ohrnberger SSA Annual Meeting 2023 , 2023 2023
Temporal Variations of Shallow Material Properties During the Kumamoto Earthquake Sequence RDD Esfahani, F Cotton, F Bonilla EGU General Assembly Conference Abstracts, EGU22-2984 , 2022 2022
Novel representations of traditional Georgian vocal music in times of online access F Scherbaum, S Rosenzweig, RD Esfahani, N Mzhavanadze, S Schwär, ... 2022 Citations: 2
Time-dependent monitoring of near-surface and ground motion modelling: developing new data processing approaches based on Music Information Retrieval (MIR) strategies R Esfahani https://doi.org/10.25932/publishup-56767 , 2022 2022 Citations: 3
Seperating Intrinsic and Scattering Attenuation using Rotational Sensor Recordings of Vibroseis Sweeps G Izgi, E Eibl, R Dokht Dolatabadi Esfahani, F Bernauer, J Wassermann, ... AGU Fall Meeting Abstracts 2021, S25H-10 , 2021 2021
Exploring the Dimensionality of Ground‐Motion Data by Applying Autoencoder Techniques RDD Esfahani, K Vogel, F Cotton, M Ohrnberger, F Scherbaum, ... Bulletin of the Seismological Society of America 111 (3), 1563-1576 , 2021 2021 Citations: 17
An efficient physic-based event detection algorithm inspired by music information retrieval R Dokht Dolatabadi Esfahani, F Scherbaum, F Cotton, M Ohrnberger EGU General Assembly Conference Abstracts, EGU21-13572 , 2021 2021
MOST CITED SCHOLAR PUBLICATIONS
TFCGAN: Nonstationary ground‐motion simulation in the time–frequency domain using conditional generative adversarial network (CGAN) and phase retrieval methods RDD Esfahani, F Cotton, M Ohrnberger, F Scherbaum Bulletin of the Seismological Society of America 113 (1), 453-467 , 2023 2023 Citations: 47
Exploring the Dimensionality of Ground‐Motion Data by Applying Autoencoder Techniques RDD Esfahani, K Vogel, F Cotton, M Ohrnberger, F Scherbaum, ... Bulletin of the Seismological Society of America 111 (3), 1563-1576 , 2021 2021 Citations: 17
Sparsity-promoting method to estimate the dispersion curve of surface-wave group velocity RDD Esfahani, R Askari, A Gholami Geophysics 84 (1), V33-V43 , 2019 2019 Citations: 16
An inexact augmented Lagrangian method for nonlinear dispersion curve inversion using Dix-type global linear approximation R Dokht Dolatabadi Esfahani, A Gholami, M Ohrnberger Geophysics 85 (5), 1-38 , 2020 2020 Citations: 13
Temporal variations of the ‘ in-situ ’ nonlinear behaviour of shallow sediments during the 2016 Kumamoto Earthquake sequence R Esfahani, F Cotton, LF Bonilla Geophysical Journal International 238 (3), 1626-1637 , 2024 2024 Citations: 7
Seismic precursors to the Blatten, Switzerland landslide revealed by unsupervised machine learning R Esfahani, M Campillo, L Seydoux, K Nishida, G Favre‐Bulle Geophysical Research Letters 53 (10), e2025GL121175 , 2026 2026 Citations: 4
Cover selection for more secure steganography R Esfahani, Z Norozi, G Jandaghi International Journal of Security and Its Applications 12 (1), 21-36 , 2018 2018 Citations: 4
Time-dependent monitoring of near-surface and ground motion modelling: developing new data processing approaches based on Music Information Retrieval (MIR) strategies R Esfahani https://doi.org/10.25932/publishup-56767 , 2022 2022 Citations: 3
Learning wave scattering properties from seismograms R Esfahani, M Bracale, L Seydoux, M Campillo Journal of Geophysical Research: Machine Learning and Computation 3 (1 … , 2026 2026 Citations: 2
Revealing and interpreting patterns from continuous seismic data with unsupervised learning L Seydoux, R Steinmann, S Mouaoued, R Esfahani, M Campillo European Geosciences Union General Assembly 2024 (EGU24), 8924 , 2024 2024 Citations: 2
Novel representations of traditional Georgian vocal music in times of online access F Scherbaum, S Rosenzweig, RD Esfahani, N Mzhavanadze, S Schwär, ... 2022 Citations: 2
Using sparse S transform and sparse-slant stacking for the estimation of the group velocity of surface waves R Dolatabadi, A Gholami, R Askari SEG International Exposition and Annual Meeting, SEG-2017-17641885 , 2017 2017 Citations: 2
Embedding seismic scattering from seismograms R Esfahani, M Bracale, L Seydoux, M Campillo EarthArXiv , 2025 2025 Citations: 1
Identification of near-surface fractures via seismic-radial anisotropy JY Jeng, R Askari, S Chatterjee, R Dolatabadi SEG International Exposition and Annual Meeting, SEG-2018-2996340 , 2018 2018 Citations: 1
Improvement Capacity and Transparency, In Steganography Based On Mod4 AA Hassani, H Dehghani, M Dehghani, R Esfahani JOURNAL OF ELECTRONIC AND CYBER DEFENCE 4 (214), 15-21 , 2016 2016 Citations: 1
Ambient Field Analysis Using Unsupervised Machine Learning and Blind Source Separation for Groundwater Monitoring in California R Esfahani, L Seydoux, S Mao, M Campillo EGU26 , 2026 2026
Improving the Safety Level of Electricity Infrastructure in Border Provinces with the Aim of Reducing Vulnerability and Increasing Resilience R Esfahani 2024
Detailed clustering of continuous seismic waveforms with deep scattering networks: a case study on the Ridgecrest earthquake sequence R Esfahani, M Campillo, L Seydoux, S Mouaoued, QY Wang European Geosciences Union General Assembly 2024 (EGU24), 6371 , 2024 2024
Failures, successes and challenges of machine-learning-based engineering ground-motion models F Cotton, R Esfahani, H Lilienkamp European Geosciences Union General Assembly 2024 (EGU24), 12197 , 2024 2024
TFCGAN package: Conditional Generative Models in Time-Frequency domain for Ground motion simulation R Esfahani, R Zaccarelli GFZ Data Service , 2024 2024
