scholarly journals Accelerating High-Resolution Seismic Imaging by Using Deep Learning

2020 ◽  
Vol 10 (7) ◽  
pp. 2502 ◽  
Author(s):  
Wei Liu ◽  
Qian Cheng ◽  
Linong Liu ◽  
Yun Wang ◽  
Jianfeng Zhang
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Seismic Imaging ◽  
Training Data ◽  
High Resolution Imaging ◽  
Data Set ◽  
Time Migration ◽  
Resolution Imaging ◽  
Computationally Intensive ◽  
Dimension Space

The emerging applications of deep learning in solving geophysical problems have attracted increasing attention. In particular, it is of significance to enhance the computational efficiency of the computationally intensive geophysical algorithms. In this paper, we accelerate deabsorption prestack time migration (QPSTM), which can yield higher-resolution seismic imaging by compensating absorption and correcting dispersion through deep learning. This is implemented by training a neural network with pairs of small-sized patches of the stacked migrated results obtained by conventional PSTM and deabsorption QPSTM and then yielding the high-resolution imaging volume by prediction with the migrated results of conventional PSTM. We use an encoder-decoder network to highlight the features related to high-resolution migrated results in a high-order dimension space. The training data set of small-sized patches not only reduces the required high-resolution migrated result (for instance, only several inline is required) but leads to a fast convergence in training. The proposed deep-learning approach accelerates the high-resolution imaging by more than 100 times. Field data is used to demonstrate the effectiveness of the proposed method.

Migration in orthorhombic media: A prestack time-migration approach

Geophysics ◽  
2019 ◽  
Vol 84 (5) ◽  
pp. C217-C227 ◽  
Author(s):  
Baoqing Tian ◽  
Jiangjie Zhang
Keyword(s):  
Synthetic Data ◽  
Real Data ◽  
High Resolution Imaging ◽  
Model Data ◽  
Data Set ◽  
Realistic Case ◽  
Time Migration ◽  
Novel Approach ◽  
Resolution Imaging ◽  
Prestack Time Migration

High-resolution imaging has become more popular recently in exploration geophysics. Conventionally, geophysicists image the subsurface using the isotropy approximation. When considering the anisotropy effects, one can expect to obtain an imaging profile with higher accuracy than the isotropy approach allows. Orthorhombic anisotropy is considered an ideal approximation in the realistic case. It has been used in the industry for several years. Although being attractive, broad application of orthorhombic anisotropy has many problems to solve. We have developed a novel approach of prestack time migration in the orthorhombic case. The traveltime and amplitude of a wave propagating in orthorhombic media are calculated directly by launching new anisotropic velocity and anisotropic parameters. We validate our methods with synthetic data. We also highlight our methods with model data set and real data. The results found that our methods work well for prestack time migration in orthorhombic media.

scholarly journals The High-Resolution Imaging (HRI) Portable Array: A Seismic (and Internet) Network Dedicated to Kilometric-scale Seismic Imaging

2008 ◽  
Vol 79 (1) ◽  
pp. 47-54 ◽  
Author(s):  
O. Coutant ◽  
F. Dore ◽  
F. Brenguier ◽  
J. F. Fels ◽  
D. Brunel ◽  
...  
Keyword(s):  
High Resolution ◽  
Seismic Imaging ◽  
High Resolution Imaging ◽  
Resolution Imaging ◽  
Internet Network

Single shot real-time high-resolution imaging through dynamic turbid media based on deep learning

2022 ◽  
Vol 149 ◽  
pp. 106819
Author(s):  
Huazheng Wu ◽  
Xiangfeng Meng ◽  
Xiulun Yang ◽  
Xianye Li ◽  
Yongkai Yin
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Real Time ◽  
Turbid Media ◽  
Single Shot ◽  
High Resolution Imaging ◽  
Resolution Imaging

scholarly journals Automated Detection, Classification and Counting of Fish in Fish Passages With Deep Learning

2022 ◽  
Vol 8 ◽  
Author(s):  
Vishnu Kandimalla ◽  
Matt Richard ◽  
Frank Smith ◽  
Jean Quirion ◽  
Luis Torgo ◽  
...  
Keyword(s):  
At Risk ◽  
Deep Learning ◽  
High Resolution ◽  
Real Time ◽  
Fish Species ◽  
Fish Passage ◽  
High Resolution Imaging ◽  
Fish Ladder ◽  
Resolution Imaging ◽  
Imaging Sonar

The Ocean Aware project, led by Innovasea and funded through Canada's Ocean Supercluster, is developing a fish passage observation platform to monitor fish without the use of traditional tags. This will provide an alternative to standard tracking technology, such as acoustic telemetry fish tracking, which are often not appropriate for tracking at-risk fish species protected by legislation. Rather, the observation platform uses a combination of sensors including acoustic devices, visual and active sonar, and optical cameras. This will enable more in-depth scientific research and better support regulatory monitoring of at-risk fish species in fish passages or marine energy sites. Analysis of this data will require a robust and accurate method to automatically detect fish, count fish, and classify them by species in real-time using both sonar and optical cameras. To meet this need, we developed and tested an automated real-time deep learning framework combining state of the art convolutional neural networks and Kalman filters. First, we showed that an adaptation of the widely used YOLO machine learning model can accurately detect and classify eight species of fish from a public high resolution DIDSON imaging sonar dataset captured from the Ocqueoc River in Michigan, USA. Although there has been extensive research in the literature identifying particular fish such as eel vs. non-eel and seal vs. fish, to our knowledge this is the first successful application of deep learning for classifying multiple fish species with high resolution imaging sonar. Second, we integrated the Norfair object tracking framework to track and count fish using a public video dataset captured by optical cameras from the Wells Dam fish ladder on the Columbia River in Washington State, USA. Our results demonstrate that deep learning models can indeed be used to detect, classify species, and track fish using both high resolution imaging sonar and underwater video from a fish ladder. This work is a first step toward developing a fully implemented system which can accurately detect, classify and generate insights about fish in a wide variety of fish passage environments and conditions with data collected from multiple types of sensors.

High-resolution imaging: a wavelet stretch correction in de-absorption prestack time migration approach

2020 ◽  
Vol 51 (4) ◽  
pp. 446-455
Author(s):  
Jin Wang ◽  
Jincheng Xu ◽  
Jiangfeng Zhang ◽  
Qiancheng Liu ◽  
Linong Liu
Keyword(s):  
High Resolution ◽  
High Resolution Imaging ◽  
Time Migration ◽  
Resolution Imaging ◽  
Prestack Time Migration

Alternative approaches to ultra-high resolution imaging

1991 ◽  
Vol 49 ◽  
pp. 650-651
Author(s):  
J.M. Cowley
Keyword(s):  
High Resolution ◽  
High Voltage ◽  
High Resolution Electron Microscopy ◽  
Crystal Defects ◽  
High Resolution Imaging ◽  
General Applicability ◽  
Resolution Electron ◽  
Radiation Resistant ◽  
Resolution Imaging ◽  
Alternative Approaches

By extrapolation of past experience, it would seem that the future of ultra-high resolution electron microscopy rests with the advances of electron optical engineering that are improving the instrumental stability of high voltage microscopes to achieve the theoretical resolutions of 1Å or better at 1MeV or higher energies. While these high voltage instruments will undoubtedly produce valuable results on chosen specimens, their general applicability has been questioned on the basis of the excessive radiation damage effects which may significantly modify the detailed structures of crystal defects within even the most radiation resistant materials in a period of a few seconds. Other considerations such as those of cost and convenience of use add to the inducement to consider seriously the possibilities for alternative approaches to the achievement of comparable resolutions.

Principle and practice of high-resolution imaging with a field-emission TEM

1992 ◽  
Vol 50 (1) ◽  
pp. 138-139
Author(s):  
Max T. Otten ◽  
Wim M.J. Coene
Keyword(s):  
High Resolution ◽  
Field Emission ◽  
Incidence Angle ◽  
Temporal Coherence ◽  
Energy Spread ◽  
High Resolution Imaging ◽  
Major Improvement ◽  
High Resolution Images ◽  
Resolution Imaging

High-resolution imaging with a LaB6 instrument is limited by the spatial and temporal coherence, with little contrast remaining beyond the point resolution. A Field Emission Gun (FEG) reduces the incidence angle by a factor 5 to 10 and the energy spread by 2 to 3. Since the incidence angle is the dominant limitation for LaB6 the FEG provides a major improvement in contrast transfer, reducing the information limit to roughly one half of the point resolution. The strong improvement, predicted from high-resolution theory, can be seen readily in diffractograms (Fig. 1) and high-resolution images (Fig. 2). Even if the information in the image is limited deliberately to the point resolution by using an objective aperture, the improved contrast transfer close to the point resolution (Fig. 1) is already worthwhile.

Imaging of ferroelectric domain walls by electron holography

1992 ◽  
Vol 50 (1) ◽  
pp. 246-247
Author(s):  
Xiao Zhang
Keyword(s):  
Magnetic Field ◽  
High Resolution ◽  
Domain Walls ◽  
Ferroelectric Domain ◽  
Object Wave ◽  
Electron Holography ◽  
High Resolution Imaging ◽  
Quantitative Measurements ◽  
Resolution Imaging ◽  
Electron Microscopes

Electron holography has recently been available to modern electron microscopy labs with the development of field emission electron microscopes. The unique advantage of recording both amplitude and phase of the object wave makes electron holography a effective tool to study electron optical phase objects. The visibility of the phase shifts of the object wave makes it possible to directly image the distributions of an electric or a magnetic field at high resolution. This work presents preliminary results of first high resolution imaging of ferroelectric domain walls by electron holography in BaTiO3 and quantitative measurements of electrostatic field distribution across domain walls.

The method of replication affects metal film granularity and resolution

1989 ◽  
Vol 47 ◽  
pp. 708-709
Author(s):  
George C. Ruben
Keyword(s):  
Electron Beam ◽  
High Resolution ◽  
Film Thickness ◽  
Single Molecule ◽  
Metal Film ◽  
Vertical Surface ◽  
High Resolution Imaging ◽  
Controllable Factors ◽  
Resolution Imaging

Single molecule resolution in electron beam sensitive, uncoated, noncrystalline materials has been impossible except in thin Pt-C replicas ≤ 150Å) which are resistant to the electron beam destruction. Previously the granularity of metal film replicas limited their resolution to ≥ 20Å. This paper demonstrates that Pt-C film granularity and resolution are a function of the method of replication and other controllable factors. Low angle 20° rotary , 45° unidirectional and vertical 9.7±1 Å Pt-C films deposited on mica under the same conditions were compared in Fig. 1. Vertical replication had a 5A granularity (Fig. 1c), the highest resolution (table), and coated the whole surface. 45° replication had a 9Å granulartiy (Fig. 1b), a slightly poorer resolution (table) and did not coat the whole surface. 20° rotary replication was unsuitable for high resolution imaging with 20-25Å granularity (Fig. 1a) and resolution 2-3 times poorer (table). Resolution is defined here as the greatest distance for which the metal coat on two opposing faces just grow together, that is, two times the apparent film thickness on a single vertical surface.

Sign in / Sign up

Export Citation Format

Share Document