Cooperative deep learning inversion of controlled-source electromagnetic data for salt delineation

Geophysics ◽  
2020 ◽  
Vol 85 (4) ◽  
pp. E121-E137 ◽  
Author(s):  
Seokmin Oh ◽  
Kyubo Noh ◽  
Soon Jee Seol ◽  
Joongmoo Byun
Keyword(s):  
Deep Learning ◽  
Test Data ◽  
Seismic Data ◽  
Surrounding Medium ◽  
Geophysical Data ◽  
Single Type ◽  
Inversion Method ◽  
Data Types ◽  
Controlled Source ◽  
Cooperative Inversion

Various geophysical data types have advantages for exploring the subsurface, and more reliable exploration can be realized through integration of such data. However, the imaging of physical properties based on deep learning (DL) techniques, which has received considerable attention because of its enormous potential, has generally been performed using only a single type of data. We have developed a cooperative inversion method based on supervised DL for salt delineation. Controlled-source electromagnetic (CSEM) data, which can effectively distinguish a salt body with high electrical resistivity from the surrounding medium, are used as data for cooperative inversion, with high-resolution information derived from seismic data used as the constraint. This approach can entrain seismic information into a fully convolutional network designed to invert CSEM data to reconstruct the resistivity distribution. The inversion network is trained using large synthetic data sets, including the seismic information derived from seismic data as well as CSEM data and resistivity models. A cooperative strategy for reasonable entrainment of seismic information into the inversion network is established based on analysis of the network and kernels of the convolutional layers. The performance of the proposed method is demonstrated through experiments on test data generated for resistivity models for complex salt structures. The trained cooperative inversion network shows improved salt delineation results compared to the independent inversion network, irrespective of noise levels added to the test data, due to restriction of the resistivity model to fit seismic information. Moreover, training with noise-added data decreased the effects of noise on prediction results, similar to the case of adversarial training. We develop the possibility of combining geophysical data with a constraint using DL-based techniques.

Sensitivity analysis of optimization parameters on cooperative inversion of seismic reflection and gravity data

2020 ◽  
Author(s):  
Maiara Gonçalves ◽  
Emilson Leite
Keyword(s):  
Sensitivity Analysis ◽  
Objective Function ◽  
Seismic Data ◽  
Optimization Methods ◽  
Inversion Method ◽  
Standard Case ◽  
Reflection Seismic ◽  
Gravimetric Data ◽  
Standard Values ◽  
Cooperative Inversion

<p>Reflections of seismic waves are strongly distorted by the presence of complex geological structures (e.g. salt bodies) and their vertical resolution is usually of the order of a few tens of meters, imposing limitations in the construction of subsurface models. One way to improve the reliability of such models is to integrate reflection seismic data with other types of geophysical data, such as gravimetric data, since the latter provide an additional link to map geological structures that exhibit density contrasts with respect to their surroundings. In a previous study, we developed a cooperative inversion method of 2D post-stack and migrated reflection seismic data, and gravimetric data. Using that inversion method, we minimize two problems: (1) the problem of the distortion of reflection seismic data due to the presence of complex geological bodies and (2) the problem of the greater ambiguity and the commonly lower resolution of the models obtained only from gravimetric anomalies. The method incorporates a technique to decrease the number of variables and is solved by optimization of the gravity inverse problem, thus reducing computing time. The objective function of cooperative inversion was minimized using three different methods of optimization: (1) simplex, (2) simulated annealing, and (3) genetic algorithm. However, these optimization methods have internal parameters which affect the convergence rate and objective function values. These parameters are usually chosen accordingly to previous references. Although the usage of these standard values is widely accepted, the best values to assure effectiveness and stability of convergence are case-dependent. In the present study, we propose a sensitivity analysis on the internal parameters of the optimization methods for the previously presented cooperative inversion. First, we developed the standard case, which is an inversion performed using all parameters at their standard values. Then, the sensitivity analysis is performed by running multiple inversions, each one with a set of parameters. Each set is obtained by modifying the value of a single parameter either for a lower or for a higher value, keeping all other values at their standard values. The results obtained by each setting are compared to the results of the standard case. The compared results are both the number of evaluations and the final value of the objective function. We then classify parameters accordingly to their relative influence on the optimization processes. The sensitivity analysis provides insight into the best practices to deal with object-based cooperative inversion schemes. The technique was tested using a synthetic model calculated from the Benchmark BP 2004, representing an offshore sedimentary basin containing salt bodies and small hydrocarbons reservoirs.</p>

Seismic wave propagation concepts applied to the interpretation of marine controlled-source electromagnetics

Geophysics ◽  
2015 ◽  
Vol 80 (2) ◽  
pp. E63-E81 ◽  
Author(s):  
Rune Mittet
Keyword(s):  
Seismic Data ◽  
Maxwell Equations ◽  
Seismic Wave Propagation ◽  
Finite Difference Schemes ◽  
Data Types ◽  
Controlled Source ◽  
Electromagnetic Data ◽  
Inverse Transform ◽  
Refraction Seismic ◽  
Marine Csem

Concepts such as reflections, refractions, diffractions, and transmissions are very useful for the interpretation of seismic data. Moreover, these concepts play a key role in the design of processing algorithms for seismic data. Currently, however, the same concepts are not widely used for the analysis and interpretation of marine controlled-source electromagnetic (CSEM) data. Connections between seismic and marine CSEM data are established by analytically transforming the diffusive Maxwell equations to wave-domain Maxwell equations. Seismic data and wave-domain electromagnetic data are simulated with 3D finite-difference schemes. The two data types are similar; however, the wave-domain electromagnetic data must be transformed back to the diffusive domain to properly describe realistic field propagation in the earth. We analyzed the inverse transform from the wave domain to the diffusive domain. Concepts like reflections, refractions, diffractions and transmissions were found to be valid also for marine CSEM data but the properties of the inverse transform favored refracted and guided events over reflected and diffracted events. In this sense, marine CSEM data were found to be similar to refraction seismic data.

Cooperative inversion of geophysical data

Geophysics ◽  
1988 ◽  
Vol 53 (1) ◽  
pp. 8-20 ◽  
Author(s):  
Larry R. Lines ◽  
Alton K. Schultz ◽  
Sven Treitel
Keyword(s):  
Seismic Data ◽  
Field Model ◽  
Gravity Data ◽  
Geophysical Data ◽  
Rock Properties ◽  
Model Parameters ◽  
Borehole Data ◽  
Geophysical Inversion ◽  
Sonic Logs ◽  
Cooperative Inversion

Geophysical inversion by iterative modeling involves fitting observations by adjusting model parameters. Both seismic and potential‐field model responses can be influenced by the adjustment of the parameters of the rock properties. The objective of this “cooperative inversion” is to obtain a model which is consistent with all available surface and borehole geophysical data. Although inversion of geophysical data is generally non‐unique and ambiguous, we can lessen the ambiguities by inverting all available surface and borehole data. This paper illustrates this concept with a case history in which surface seismic data, sonic logs, surface gravity data, and borehole gravity meter (BHGM) data are adequately modeled by using least‐squares inversion and a series of forward modeling steps.

Application of deep learning for seismic horizon interpretation

2019 ◽  
Vol 59 (1) ◽  
pp. 426
Author(s):  
James Lowell ◽  
Jacob Smith
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Test Data ◽  
Seismic Data ◽  
Training Data ◽  
Learning Networks ◽  
Learning Network ◽  
Deep Learning Network

The interpretation of key horizons on seismic data is an essential but time-consuming part of the subsurface workflow. This is compounded when surfaces need to be re-interpreted on variations of the same data, such as angle stacks, 4D data, or reprocessed data. Deep learning networks, which are a subset of machine learning, have the potential to automate this reinterpretation process, and significantly increase the efficiency of the subsurface workflow. This study investigates whether a deep learning network can learn from a single horizon interpretation in order to identify that event in a different version of the same data. The results were largely successful with the target horizon correctly identified in an alternative offset stack, and was correctly repositioned in areas where there was misalignment between the training data and the test data.

scholarly journals Interactive broadband constrained inversion

1989 ◽  
Vol 20 (2) ◽  
pp. 253
Author(s):  
G. Mansfield
Keyword(s):  
Seismic Data ◽  
Low Frequency ◽  
Inversion Method ◽  
Data Types ◽  
Frequency Model ◽  
Impedance Model ◽  
Interactive Environment ◽  
Seismic Amplitudes ◽  
Diverse Data ◽  
Geologic Information

Conventional algorithms for the inversion of seismic data generally produce inverted traces which are limited in bandwidth to that of the input seismic data. This necessitates that a low-frequency model be added to the inverted traces in order to produce full bandwidth seismic logs. A problem with this method is that there is usually a gap in frequency between the low end of the seismic and the high end of the model spectra. A further problem with conventional inversion methods is that it is difficult to incorporate well or geologic information into the inversion process. To overcome these problems a new broadband constrained inversion method which combines seismic, well, and geologic information is used. This method simultaneously satisfies constraints imposed by the well and geologic information, whilst inverting the seismic data. The output is an optimized broadband acoustic impedance model. In order to combine the diverse data types of seismic amplitudes, well logs, geologic models, and horizon interpretations, an interactive workstation is used. The interactive environment is ideal for this work as it provides the flexibility required to manipulate and display both the varying incoming data types and the output data model.

Deep Learning in Disease Diagnosis: Models and Datasets

2020 ◽  
Vol 15 ◽  
Author(s):  
Deeksha Saxena ◽  
Mohammed Haris Siddiqui ◽  
Rajnish Kumar
Keyword(s):  
Biological Sciences ◽  
Machine Learning ◽  
Deep Learning ◽  
Disease Diagnosis ◽  
Learning Models ◽  
Data Types ◽  
Related Data ◽  
Abstract Level ◽  
Experimental Validations ◽  
Selection Of

Background: Deep learning (DL) is an Artificial neural network-driven framework with multiple levels of representation for which non-linear modules combined in such a way that the levels of representation can be enhanced from lower to a much abstract level. Though DL is used widely in almost every field, it has largely brought a breakthrough in biological sciences as it is used in disease diagnosis and clinical trials. DL can be clubbed with machine learning, but at times both are used individually as well. DL seems to be a better platform than machine learning as the former does not require an intermediate feature extraction and works well with larger datasets. DL is one of the most discussed fields among the scientists and researchers these days for diagnosing and solving various biological problems. However, deep learning models need some improvisation and experimental validations to be more productive. Objective: To review the available DL models and datasets that are used in disease diagnosis. Methods: Available DL models and their applications in disease diagnosis were reviewed discussed and tabulated. Types of datasets and some of the popular disease related data sources for DL were highlighted. Results: We have analyzed the frequently used DL methods, data types and discussed some of the recent deep learning models used for solving different biological problems. Conclusion: The review presents useful insights about DL methods, data types, selection of DL models for the disease diagnosis.

scholarly journals Multi-Dimensional Underwater Point Cloud Detection Based on Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 884
Author(s):  
Chia-Ming Tsai ◽  
Yi-Horng Lai ◽  
Yung-Da Sun ◽  
Yu-Jen Chung ◽  
Jau-Woei Perng
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Three Dimensional ◽  
Point Clouds ◽  
Training Data ◽  
Network Architectures ◽  
Point Cloud Data ◽  
Data Types ◽  
Raw Data ◽  
Cloud Data

Numerous sensors can obtain images or point cloud data on land, however, the rapid attenuation of electromagnetic signals and the lack of light in water have been observed to restrict sensing functions. This study expands the utilization of two- and three-dimensional detection technologies in underwater applications to detect abandoned tires. A three-dimensional acoustic sensor, the BV5000, is used in this study to collect underwater point cloud data. Some pre-processing steps are proposed to remove noise and the seabed from raw data. Point clouds are then processed to obtain two data types: a 2D image and a 3D point cloud. Deep learning methods with different dimensions are used to train the models. In the two-dimensional method, the point cloud is transferred into a bird’s eye view image. The Faster R-CNN and YOLOv3 network architectures are used to detect tires. Meanwhile, in the three-dimensional method, the point cloud associated with a tire is cut out from the raw data and is used as training data. The PointNet and PointConv network architectures are then used for tire classification. The results show that both approaches provide good accuracy.

On the Processing of Non-Rectangularly Sampled Multi-Dimensional Geophysical Data

1991 ◽  
Vol 02 (01) ◽  
pp. 223-226
Author(s):  
VIRGIL BARDAN
Keyword(s):  
Seismic Data ◽  
Geophysical Data ◽  
Seismic Sections

In this paper the processing of triangularly sampled 2-D seismic data is illustrated by examples of synthetic and field seismic sections.

Sign in / Sign up

Export Citation Format

Share Document