Deep learning joint inversion of seismic and electromagnetic data for salt reconstruction

Sun, Yen; Denel, Bertrand; Daril, Norman; Evano, Lory; Williamson, Paul; Araya‐Polo, Mauricio

doi:10.1190/segam2020-3426925.1

Cited by 30 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, DL techniques also provide new perspectives of integrating EM methods with other imaging modalities to achieve better resolution [68]- [70], but how to embed different physical principles in a unified neural network remains open.…”

Section: B Physicsmentioning

confidence: 99%

Physics Embedded Machine Learning for Electromagnetic Data Imaging

Guo¹,

Huang²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

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 usually computationally expensive.Machine learning (ML) techniques and especially deep learning (DL) show potential in fast and accurate imaging. However, the high performance of purely data-driven approaches relies on constructing a training set that is statistically consistent with practical scenarios, which is often not possible in EM imaging tasks. Consequently, generalizability becomes a major concern. On the other hand, physical principles underlie EM phenomena and provide baselines for current imaging techniques. To benefit from prior knowledge in big data and the theoretical constraint of physical laws, physics embedded ML methods for EM imaging have become the focus of a large body of recent work. This article surveys various schemes to incorporate physics in learning-based EM imaging. We first introduce background on EM imaging and basic formulations of the inverse problem. We then focus on three types of strategies combining physics and ML for linear and nonlinear imaging and discuss their advantages and limitations. Finally, we conclude with open challenges and possible ways forward in this fast-developing field. Our aim is to facilitate the study of intelligent EM imaging methods that will be efficient, interpretable and controllable.

show abstract

Section: B Physicsmentioning

confidence: 99%

Physics Embedded Machine Learning for Electromagnetic Data Imaging

Guo¹,

Huang²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For example, Oh et al (2020) demonstrate a cooperative DL imaging network for marine controlled-source electromagnetic data and seismic information (i.e., seismic salt-top boundaries) for enhancing salt delineation. Sun et al (2020) proposes a set of deep neural network architectures for marine seismic and electromagnetic data for salt reconstruction. Hu et al (2021) present a DL enhanced joint imaging framework for crosswell seismic and DC resistivity data.…”

Section: Introductionmentioning

confidence: 99%

“…Sun et al. (2020) propose a set of deep neural network architectures for marine seismic and electromagnetic data for salt reconstruction. Hu et al.…”

Section: Introductionmentioning

confidence: 99%

Deep learning multiphysics network for imaging CO₂ saturation and estimating uncertainty in geological carbon storage

Alumbaugh

Commer

et al. 2022

Geophysical Prospecting

View full text Add to dashboard Cite

Multiphysics inversion exploits different types of geophysical data that often complement each other and aims to improve overall imaging resolution and reduce uncertainties in geophysical interpretation.Despite the advantages, traditional multiphysics inversion is challenging because it requires a large amount of computational time and intensive human interactions for preprocessing data and finding tradeoff parameters. These issues make it nearly impossible for traditional multiphysics inversion to be applied as a real-time monitoring tool for geological carbon storage. In this paper, we present a deep-learning (DL) multiphysics network for imaging CO 2 saturation in real time. The multiphysics network consists of three encoders for analyzing seismic, electromagnetic, and gravity data, and shares one decoder for combining imaging capabilities of the different geophysical data for better predicting CO 2 saturation. The network is trained on pairs of CO 2 label models and multiphysics data so that it can directly image CO 2 saturation. We use the bootstrap aggregating method to enhance the imaging accuracy and estimate uncertainties associated with CO 2 saturation images. Using realistic CO 2 label models and multiphysics data derived from the Kimberlina CO 2 storage model, we evaluate the performance of the DL multiphysics network and compare their imaging results to those from the DL single-physics networks.Our modeling experiments show that the DL multiphysics network for seismic, electromagnetic, and gravity data not only improves the imaging accuracy but also reduces uncertainties associated with CO 2 saturation images. Our results also suggest that the DL multiphysics network for the non-seismic data (i.e., electromagnetic and gravity) can be used as an effective low-cost monitoring tool in between regular seismic monitoring.

show abstract

“…However, the acquisition of the labelled data is extremely expensive, only sparse labelled data can be acquired in the field experiments. (Sun et al, 2020) firstly present a joint inversion that reconstruct salt geometry by combining seismic and electromagnetic data, but it still rely on large amount of labelled data, which is impossible to be obtained in the real case.…”

Section: Introductionmentioning

confidence: 99%

Extremely Weak Supervision Inversion of Multi-physical Properties

Feng¹,

Jin²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Multi-physical inversion plays a critical role in geophysics. It has been widely used to infer various physical properties (such as velocity and conductivity), simultaneously. Among those inversion problems, some are explicitly governed by partial differential equations (PDEs), while others are not. Without explicit governing equations, conventional multi-physical inversion techniques will not be feasible and data-driven inversion require expensive full labels. To overcome this issue, we develop a new data-driven multi-physics inversion technique with extremely weakly supervision. Our key finding is that the pseudo labels can be constructed by learning the local relationship among geophysical properties at very sparse locations. We explore a multi-physics inversion problem from two distinct measurements (seismic and EM data) to three geophysical properties (velocity, conductivity, and CO 2 saturation). Our results show that we are able to invert for properties without explicit governing equations. Moreover, the label data on three geophysical properties can be significantly reduced by 50 times (from 100 down to only 2 locations).

show abstract

Deep learning joint inversion of seismic and electromagnetic data for salt reconstruction

Cited by 30 publications

References 13 publications

Physics Embedded Machine Learning for Electromagnetic Data Imaging

Physics Embedded Machine Learning for Electromagnetic Data Imaging

Deep learning multiphysics network for imaging CO₂ saturation and estimating uncertainty in geological carbon storage

Extremely Weak Supervision Inversion of Multi-physical Properties

Contact Info

Product

Resources

About

Deep learning joint inversion of seismic and electromagnetic data for salt reconstruction

Cited by 30 publications

References 13 publications

Physics Embedded Machine Learning for Electromagnetic Data Imaging

Physics Embedded Machine Learning for Electromagnetic Data Imaging

Deep learning multiphysics network for imaging CO2 saturation and estimating uncertainty in geological carbon storage

Extremely Weak Supervision Inversion of Multi-physical Properties

Contact Info

Product

Resources

About

Deep learning multiphysics network for imaging CO₂ saturation and estimating uncertainty in geological carbon storage