scholarly journals SeisDeNet: An Intelligent Seismic Data Denoising Network for the Internet of Things

2021 ◽  
Author(s):  
Yu Sang ◽  
Yanfei Peng ◽  
Mingde Lu ◽  
Liquan Li
Keyword(s):  
Internet Of Things ◽  
Seismic Data ◽  
Leading Edge ◽  
Seismic Signal ◽  
Seismic Exploration ◽  
Real Field ◽  
Signal Acquisition ◽  
Multi Scale ◽  
Seismic Records ◽  
The Internet Of Things

Abstract Deep learning (DL) has attracted tremendous interest in various fields in last few years. Convolutional neural networks (CNNs) based DL architectures have been successfully applied in computer vision, medical image processing, remote sensing, and many other fields. A recent work has proved that CNNs based models can also be used to handle geophysical problems. Due to noises in seismic signals acquired by geophone equipment this kind of important multimedia resources cannot be effectively utilized in practice. To this end, from the perspective of seismic exploration informatization, this paper takes informatization data in seismic signal acquisition and energy exploration field using cutting-edge technologies such as Internet of things and cloud computing as the research object, presenting a novel CNNs based seismic data denoising (SeisDeNet) architecture is suggested. Firstly, a multi-scale residual dense (MSRD) block is built to leverage the characteristics of seismic data. Then, a deep MSRD network (MSRDN) is proposed to restore the noisy seismic data in a coarse-to-fine manner by using cascading MSRDs. Additionally, the denoising problem is formulated into predicting transform-domain coefficients, by which noises can be further removed by MSRDNs while richer structure details are preserved comparing with the results in spatial domain. By using synthetic seismic records, public SEG and EAGE salt and overthrust seismic model and real field seismic data, the proposed method is qualitatively and quantitatively compared with other leading edge schemes to evaluate it performance, and some results shows that the proposed scheme can produce data with higher quality evaluation while maintaining far more useful data comparing with other schemes. The feasibility of this approach is confirmed by the denoising results, and this approach is shown to be promising in suppressing the seismic noise automatically.

scholarly journals Low-frequency noise suppression for desert seismic data based on a wide inference network

2019 ◽  
Vol 16 (4) ◽  
pp. 801-810
Author(s):  
Yue Li ◽  
Wei Yu ◽  
Chao Zhang ◽  
Baojun Yang
Keyword(s):  
Seismic Data ◽  
Low Frequency ◽  
Seismic Exploration ◽  
Frequency Noise ◽  
Layer By Layer ◽  
Low Frequency Noise ◽  
Time Space ◽  
Manual Adjustment ◽  
Inference Network ◽  
Seismic Records

Abstract The importance of seismic exploration has been recognized by geophysicists. At present, low-frequency noise usually exists in seismic exploration, especially in desert seismic records. This low-frequency noise shares the same frequency band with effective signals. This leads to the limitation or failure of traditional methods. In order to overcome the shortcomings of traditional denoising methods, we propose a novel desert seismic data denoising method based on a Wide Inference Network (WIN). The WIN aims to minimize the error between the prediction and target by residual learning during training, and it can obtain a set of optimal parameters, such as weights and biases. In this article, we construct a high-quality training set for a desert seismic record and this ensures the effective training of a WIN. In this way, each layer of the trained WIN can automatically extract a set of time–space characteristics without manual adjustment. These characteristics are transmitted layer by layer. Finally, they are utilized to extract effective signals. To verify the effectiveness of the WIN, we apply it to synthetic and real desert seismic records, respectively. In addition, we compare WIN with f – x deconvolution, variational mode decomposition (VMD) and shearlet transform. The results show that WIN has the best denoising performance in suppressing low-frequency noise and preserving effective signals.

INCOME – Multi-scale Context Management for the Internet of Things

2012 ◽  
pp. 338-347 ◽  
Author(s):  
Jean-Paul Arcangeli ◽  
Amel Bouzeghoub ◽  
Valérie Camps ◽  
Marie-Françoise Canut ◽  
Sophie Chabridon ◽  
...  
Keyword(s):  
Internet Of Things ◽  
The Internet ◽  
Context Management ◽  
Multi Scale ◽  
The Internet Of Things

Simulation Research on Synthesis Algorithm of Directional Illumination Data

2011 ◽  
Vol 403-408 ◽  
pp. 2337-2340
Author(s):  
Shu Cong Liu ◽  
Yan Xing Song ◽  
Jing Song Yang
Keyword(s):  
Seismic Data ◽  
Seismic Waves ◽  
Seismic Analysis ◽  
Signal To Noise Ratio ◽  
A Priori ◽  
Effective Means ◽  
Seismic Signal ◽  
Geological Structure ◽  
Seismic Exploration ◽  
The Impact

Seismic illumination analysis was an effective means of recognizing and studying the energy distributions in the underground geological structure in seismic data acquisition. Effective seismic illumination analysis to a priori targeted-geological model to identify the energy distribution of seismic waves, can apply to seismic analysis and amplitude compensation analysis. To increase the signal to noise ratio and resolution of seismic data when vibrator seismic exploration, it was necessary to strengthen the energy of a certain direction to get the High-Precision imaging and the best illumination of the target areas.Simulation research were done on single source directional illumination seismic technology, with seismic illumination analysis, and the impact of source number, spacing change on directional illumination seismic technology were also analyzed. Simulation results showed that the directional seismic technology could improved SNR of seismic data, and could be used for seismic signal processing.

scholarly journals Noise Attenuation of Seismic Data via Deep Multiscale Fusion Network

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Yu Sang ◽  
Jinguang Sun ◽  
Dacheng Gao ◽  
Hao Wu
Keyword(s):  
Deep Learning ◽  
Seismic Data ◽  
Medical Image ◽  
Leading Edge ◽  
Great Success ◽  
Noise Attenuation ◽  
Seismic Data Processing ◽  
Signal Features ◽  
Useful Signal ◽  
Seismic Records

Convolutional neural network- (CNN-) based deep learning (DL) architectures have achieved great success in many fields such as remote sensing, medical image processing, and computer vision. Recently, CNN-based models have also been attempted to solve geophysical problems. This paper presents a noise attenuation method of seismic data via a novel deep learning (DL) architecture, namely, deep multiscale fusion network (MSFN). Firstly, we integrate multiscale fusion (MSF) block to adaptively exploit local signal features at different scales from seismic data. And then, a series of stacked MSF blocks are formed into MSFN, which can restore the noisy seismic data effectively and preserve more useful signal information. Furthermore, a comparative study of our method and other leading edge ones is conducted by using synthetic seismic records and the SEG/EAGE salt and overthrust models. The results qualitatively and quantitatively show the capability of our method of achieving higher peak signal-to-noise ratios (PSNRs) while preserving much more useful information, comparing with other methods. Finally, our method is utilized in the real seismic data processing, obtaining satisfactory results.

Signal enhancement in seismic data and in the migration process: appliation to 2D seismic exploration data

2020 ◽  
Author(s):  
Maxim I. Protasov ◽  
◽  
Dmitry A. Neklyudov ◽  
Alexandr A. Meretskiy ◽  
◽  
...  
Keyword(s):  
Seismic Data ◽  
Object Oriented ◽  
Seismic Signal ◽  
Signal Enhancement ◽  
Seismic Exploration ◽  
Gaussian Beams ◽  
Reflected Waves ◽  
The North ◽  
First Case ◽  
Useful Signal

The paper presents the results of testing two procedures: signal enhancement by local coherent summation of the seismic data and object–oriented migration along Gaussian beams. Both of these procedures provide extraction and accumulation of a useful seismic signal (primarily reflected waves). In the first case, this process is implemented directly on the seismic data, while in the migration procedure the useful signal is accumulated due to the properties of Gaussian beams. The procedures tested on the 2D real seismic data obtained in the north of the Krasnoyarsk Territory.

ELECTRICAL RECORDER FOR SEISMIC DATA

Geophysics ◽  
1957 ◽  
Vol 22 (4) ◽  
pp. 829-841
Author(s):  
C. F. Hadley ◽  
J. D. Eisler
Keyword(s):  
Seismic Data ◽  
Rotational Speed ◽  
Rotating Disk ◽  
Seismic Signal ◽  
Signal Timing ◽  
Electrical Pulses ◽  
Axis Parallel ◽  
Seismic Records

A method of making multitrace seismic records using electrically sensitive paper is described. The record is immediately available for use without any type of processing. A disk carrying wire brushes on its periphery is revolved with its axis parallel to the direction of the motion of the electrical paper. The paper is pulled under the scanning disk and is shaped so that brushes remain in contact with it. Short electrical pulses are fed to the brushes to produce a number of traces composed of closely spaced dots. The position of the dots is determined by the time of occurrence of the pulses. This time is a function of the amplitude of the seismic signal. Timing lines are placed on the record by feeding a series of dots to all brushes. Provision is made to count down and emphasize the fifth and tenth timing lines. A system of multiplexing is used to employ each brush on many traces and thus reduce the rotational speed of the rotating disk. This recorder has proved its usefulness in reproduction of magnetically recorded seismic data.

Distributed Wireless Acquisition System for Seismic Signal with Vibration and Noise

2013 ◽  
Vol 340 ◽  
pp. 75-79 ◽  
Author(s):  
Huai Liang Li ◽  
Xian Guo Tuo ◽  
Ming Zhe Liu
Keyword(s):  
Data Transmission ◽  
Seismic Data ◽  
Seismic Signal ◽  
Field Application ◽  
Acquisition System ◽  
Signal Acquisition ◽  
Time Sharing ◽  
Technical Problems ◽  
Problems And Solutions ◽  
Low Efficiency

This work presented the design and implementation of a wireless acquisition system for seismic signal. 4 distributed signal acquisition stations were integrated to the low-power prototype which composed of 48 acquisition channels, and a star-shaped wireless network was built which is suitable for seismic data transmission using the networking mode of multi-pipe and multi-address switching. A distributed seismic data acquisition system was accomplished which has the function of synchronous control and asynchronous transmission. The key technical problems and solutions of time balance distribution between multi-channel time-sharing switching acquisition and temporary storage, and wireless seismic data transmission is analyzed in detail in this paper. Thus the additional accessories of traditional wired seismograph were greatly reduced, to improve its cable layout trouble and low efficiency of construction in an adverse environment. This system increased efficiency more than 50% and took same exploration effect compared with wired mode in the field application.

Advancing Artificial Intelligence-Enabled Cybersecurity for the Internet of Things

2021 ◽  
pp. 118-143
Author(s):  
Alper Kamil Demir ◽  
Shahid Alam
Keyword(s):  
Artificial Intelligence ◽  
Internet Of Things ◽  
Leading Edge ◽  
Digital Transformation ◽  
The Internet ◽  
New Wave ◽  
Transportation Energy ◽  
Different Types ◽  
Iot Devices ◽  
The Internet Of Things

Internet of things (IoT) has revolutionized digital transformation and is present in every sector including transportation, energy, retail, healthcare, agriculture, etc. While stepping into the new digital transformation, these sectors must contemplate the risks involved. The new wave of cyberattacks against IoT is posing a severe impediment in adopting this leading-edge technology. Artificial intelligence (AI) is playing a key role in preventing and mitigating some of the effects of these cyberattacks. This chapter discusses different types of threats and attacks against IoT devices and how AI is enabling the detection and prevention of these cyberattacks. It also presents some challenges faced by AI-enabled detection and prevention and provides some solutions and recommendations to these challenges. The authors believe that this chapter provides a favorable basis for the readers who intend to know more about AI-enabled technologies to detect and prevent cyberattacks against IoT and the motivation to advance the current research in this area.

Advanced Enterprise Asset Management Systems: Improve Predictive Maintenance and Asset Performance by Leveraging Industry 4.0 and the Internet of Things (IoT)

2021 ◽  
Author(s):  
Sandeep Bhanji ◽  
Howard Shotz ◽  
Sravani Tadanki ◽  
Youssef Miloudi ◽  
Patrick Warren
Keyword(s):  
Internet Of Things ◽  
Asset Management ◽  
Leading Edge ◽  
Predictive Maintenance ◽  
The Internet ◽  
Time Data ◽  
Management Scenarios ◽  
Intelligent Sensors ◽  
Reliability Centered Maintenance ◽  
The Internet Of Things

Abstract Advanced Enterprise Asset Management (EAM) is an approach through which an organization’s assets are systematically and proactively managed throughout their lifecycle — from installation through disposition. The objective of EAM is to prolong the service life and maximize utilization of the assets via adoption of leading-edge standards, practices, and technology. Organizations that implement advanced EAM benefit from reduced operating expenses (OPEX), reduced capital replacement expenses (CAPEX), increased uptime, and overall higher quality asset capability within their portfolio. Successful EAM leverages ISO55000 & IAM 2.0 standards to implement predictive, proactive and reliability centered maintenance best practices. Implementing an EAM provides leading edge technology to the rail industry to track and audit maintenance work using mobility tools, heads-up virtual reality displays, augmented reality expertise and the Internet of Things (IoT); combined with artificial intelligence and machine learning to bolster predictive maintenance and simulate asset performance based on different scenarios. EAM will evolve rapidly following the world’s rapid transformation into the IoT over the next decade. As rail and transit assets become outfitted with interconnected intelligent sensors whose outputs are collected via active and passive devices, real-time data is available for EAM to track, plan and upgrade assets. As systems are modernized, EAM will leverage the IoT revolution to provide critical information to operations in planning railway management scenarios, including predictive maintenance functionality and edge analytics.

Sign in / Sign up

Export Citation Format

Share Document