Physics-embedded machine learning for electromagnetic data imaging: Examining three types of data-driven imaging methods

R Guo, T Huang, M Li, H Zhang… - IEEE Signal Processing …, 2023 - ieeexplore.ieee.org
Electromagnetic (EM) imaging is widely applied in sensing for security, biomedicine,
geophysics, and various industries. It is an ill-posed inverse problem whose solution is …

Physics-driven deep-learning inversion with application to transient electromagnetics

D Colombo, E Turkoglu, W Li, E Sandoval-Curiel… - Geophysics, 2021 - library.seg.org
Machine learning, and specifically deep-learning (DL) techniques applied to geophysical
inverse problems, is an attractive subject, which has promising potential and, at the same …

Electromagnetic subsurface imaging in the presence of metallic structures: a review of numerical strategies

O Castillo-Reyes, P Queralt, P Piñas-Varas, J Ledo… - Surveys in …, 2024 - Springer
Electromagnetic (EM) imaging aims to produce large-scale, high-resolution soil conductivity
maps that provide essential information for Earth subsurface exploration. To rigorously …

[HTML][HTML] A finite element based deep learning solver for parametric PDEs

C Uriarte, D Pardo, ÁJ Omella - Computer Methods in Applied Mechanics …, 2022 - Elsevier
We introduce a dynamic Deep Learning (DL) architecture based on the Finite Element
Method (FEM) to solve linear parametric Partial Differential Equations (PDEs). The …

Deep convolutional generative adversarial networks for modeling complex hydrological structures in Monte-Carlo simulation

Q Chen, Z Cui, G Liu, Z Yang, X Ma - Journal of Hydrology, 2022 - Elsevier
Abstract Characterization of complex subsurface structures is challenging due to the
demand to preserve geological realism of the training images in earth and environmental …

Error control and loss functions for the deep learning inversion of borehole resistivity measurements

M Shahriari, D Pardo, JA Rivera… - International Journal …, 2021 - Wiley Online Library
Deep learning (DL) is a numerical method that approximates functions. Recently, its use has
become attractive for the simulation and inversion of multiple problems in computational …

Coupled physics-deep learning inversion

D Colombo, E Turkoglu, W Li, D Rovetta - Computers & Geosciences, 2021 - Elsevier
Application of machine learning (ML) or deep learning (DL) to geophysical data inversion is
a growing topic of interest. Opportunities are in the areas of enhanced efficiency, resolution …

A deep neural network as surrogate model for forward simulation of borehole resistivity measurements

M Shahriari, D Pardo, B Moser, F Sobieczky - Procedia Manufacturing, 2020 - Elsevier
Inverse problems appear in multiple industrial applications. Solving such inverse problems
require the repeated solution of the forward problem. This is the most time-consuming stage …

Self-supervised, active learning seismic full-waveform inversion

D Colombo, E Turkoglu, E Sandoval-Curiel, T Alyousuf - Geophysics, 2024 - library.seg.org
ABSTRACT A novel recursive, self-supervised machine-learning (ML) inversion scheme is
developed. It is applied for fast and accurate full-waveform inversion of land seismic data …

Deep learning inversion of gravity data for detection of CO2 plumes in overlying aquifers

X Yang, X Chen, MM Smith - Journal of Applied Geophysics, 2022 - Elsevier
We developed an effective U-Net based deep learning (DL) model for inversion of surface
gravity data on a rectangular grid to predict 2-D high-resolution subsurface CO 2 distribution …