Automatic Velocity Analysis Using a Hybrid Regression Approach With Convolutional Neural Networks

Ferreira, Rodrigo S.; Oliveira, Dário Augusto Borges; Semin, Daniil; Zaytsev, Semen

doi:10.1109/tgrs.2020.3022744

Cited by 14 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the regression results of this method were continuous values, there was no excellent result on the field data in the experimental part. Unlike the method described above, Ferreira et al [21] proposed an iterative estimation method, which is more practical and closer to the operation process of the industry. In each iteration, the prestack CMP gathers were conducted NMO correction by a set of NMO velocities, particularly which were estimated on the velocity spectrum for initialization.…”

Section: Introductionmentioning

confidence: 99%

“…Because SGS contains the adjacent sample information as well as the velocity prior information, it improves not only the picking accuracy of the low SNR velocity spectrum, but also the robustness of picking results. Moreover, compared with the iterative method [21], our method just requires one prediction, where the computational cost has been reduced significantly. In our work, to address the instability of local estimation and balance the capacity to recognize the energy clusters with different sizes, we also propose a velocity spectrum enhance method to obtain the multi-observation spectra, which simulate that people observe the spectrum with different distances and focus.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Velocity Picking Using a Multi-Information Fusion Deep Semantic Segmentation Network

Wang,

Zhang,

Zhao

et al. 2022

Preprint

View full text Add to dashboard Cite

Velocity picking, a critical step in seismic data processing, has been studied for decades. Although manual picking can produce accurate normal moveout (NMO) velocities from the velocity spectra of prestack gathers, it is time-consuming and becomes infeasible with the emergence of large amount of seismic data. Numerous automatic velocity picking methods have thus been developed. In recent years, deep learning (DL) methods have produced good results on the seismic data with medium and high signal-to-noise ratios (SNR). Unfortunately, it still lacks a picking method to automatically generate accurate velocities in the situations of low SNR. In this paper, we propose a multiinformation fusion network (MIFN) to estimate stacking velocity from the fusion information of velocity spectra and stack gather segments (SGS). In particular, we transform the velocity picking problem into a semantic segmentation problem based on the velocity spectrum images. Meanwhile, the information provided by SGS is used as a prior in the network to assist segmentation. The experimental results on two field datasets show that the picking results of MIFN are stable and accurate for the scenarios with medium and high SNR, and it also performs well in low SNR scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Velocity Picking Using a Multi-Information Fusion Deep Semantic Segmentation Network

Wang,

Zhang,

Zhao

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Zhang et al [5] combined You Only Look Once (YOLO) and Long Short-Term Memory (LSTM) to build a discriminant model and Xu et al [6] built a regression model between normal moveout (NMO) correction time and velocity estimation losses by using a convolutional neural network (CNN) to find the energy peaks. Ferreira et al [7] simultaneously combined the information of both the velocity spectrum and the CMP gather for velocity analysis. Recently, transfer learning is introduced to improve the generalization ability on different data sets for the supervised learning methods [8].…”

Section: Introductionmentioning

confidence: 99%

“…Even in different geological conditions, the chosen objective functions are different. For the supervised learning approaches, the deep learning models [5] [6] [7] [8] can achieve high picking accuracy. But as far as the current pickup model is concerned, its training tag velocity spectrum energy peak is a huge project and the trained model is difficult to generalize to other geological conditions.…”

Section: Introductionmentioning

confidence: 99%

Automatic Velocity Picking Using Unsupervised Ensemble Learning

Wang¹,

Zhang²,

Zhao³

et al. 2022

Preprint

View full text Add to dashboard Cite

In seismic data processing, accurate and efficient automatic velocity picking algorithms can significantly accelerate the processing, and the main branch is to use velocity spectra for velocity pickup. Recently, machine learning algorithms have been widely used in automatic spectrum picking. Even though deep learning methods can address the problem well in supervised cases, they are often accompanied by expensive computational costs and low interpretability. On the contrast, unsupervised learning methods based on the physical knowledge have great potential to efficiently resolve the task. In this paper, we propose an unsupervised ensemble learning (UEL) method to pick the root mean square (RMS) velocities on the spectrum. In particular, UEL utilizes the information of nearby velocity spectra and the nearest seed velocity curve to assist the selection of effective and reasonable velocity points. To increase the coherence of energy peaks, an information gain method is developed by local normalization. In addition, we designed the attention scale-space filter (ASSF) clustering method to incorporate the coherence information into the picking process. Experiments on three datasets demonstrate that compared to traditional clustering methods, UEL can recognize energy clusters better, especially with smaller blobs. Moreover, the injection of nearby spectra and interval velocity constraint in UEL significantly improves the robustness and accuracy of picking results.

show abstract

“…Earthquake itself is extremely destructive and can destroy buildings and other structures in a short time. In addition, secondary disasters such as tsunami, debris flow, fire and leakage of toxic and harmful substances, which seriously threaten people's life and property safety, will also be triggered [1][2]. China has a vast territory and is located between the Pacific plate and the Asia-Europe plate.…”

Section: Introductionmentioning

confidence: 99%

Earthquake Distribution and Crustal Seismic Wave Velocity Based on Machine Learning

2020

View full text Add to dashboard Cite

It is of great significance to accurately pick up the first arrival of P wave and S wave for the accurate location of earthquakes and the explanation of seismogenic mechanism. This paper focuses on the analysis of seismic distribution and seismic wave velocity of the bottom shell based on machine learning. In this paper, convolutional neural network is used to pick up seismic P and S waves when they first arrive. Compared with the traditional STA/LTA, the convolutional neural network method does not manually set thresholds and manually select feature functions, but only relies on convolutional neural network to automatically extract waveform features, and the model has good generalization. The research results of this paper can provide a new idea for picking up P and S waves at their first arrival in the future, so as to pick up P and S waves at their first arrival more accurately, and it is expected to provide technical support for the location of earthquakes and the explanation of seismogenic mechanism of earthquakes.

show abstract

Automatic Velocity Analysis Using a Hybrid Regression Approach With Convolutional Neural Networks

Cited by 14 publications

References 17 publications

Automatic Velocity Picking Using a Multi-Information Fusion Deep Semantic Segmentation Network

Automatic Velocity Picking Using a Multi-Information Fusion Deep Semantic Segmentation Network

Automatic Velocity Picking Using Unsupervised Ensemble Learning

Earthquake Distribution and Crustal Seismic Wave Velocity Based on Machine Learning

Contact Info

Product

Resources

About