Unsupervised machine learning algorithm for detecting and outlining surface waves on seismic shot gathers

Xia, Keyao; Hilterman, Fred; Hu, Hao

doi:10.1016/j.jappgeo.2018.07.003

Cited by 14 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the similar dispersive characteristics between guided waves and surface waves, a similar workflow (including transfer learning / re‐training of the CNN) could be used for identification of surface waves in land seismic or near‐surface DAS records (e.g. Xia et al ., 2018).…”

Section: Discussionmentioning

confidence: 99%

Convolutional neural network‐based classification of microseismic events originating in a stimulated reservoir from distributed acoustic sensing data

Liu

Huff

Luo

et al. 2022

Geophysical Prospecting

View full text Add to dashboard Cite

This study presents a workflow of using a convolutional neural network to automatically classify microseismic events originating from a more productive oil and gasbearing formation (the Eagle Ford Shale), as compared to events originating in less productive formations (the Austin Chalk and Buda Limestone). These microseismic events occur due to hydraulic stimulation and are recorded by fibre optic-distributed acoustic sensing measurements from a horizontal monitoring well. The convolutional neural network is trained to recognize guided wave energy in distributed acoustic sensing seismograms, since microseismic events originating within or close to a lowvelocity reservoir (such as the Eagle Ford) generate significant guided wave energy. The training of convolutional neural network is conducted using synthetic seismograms overlain with real noise profiles from field data. Field events with guided waves are then classified by the convolutional neural network as occurring within or close to the Eagle Ford, while events without guided waves are classified as occurring far outside the Eagle Ford. Noise attenuation steps (including a bandpass filter, median filter and non-local means filter) are implemented to increase the signal-to-noise ratio of the field data and improve the classification accuracy. The accuracy of the convolutional neural network is measured by comparison with labels of the events determined by human inspection of guided wave presence. We also evaluate the impact of different network architectures and noise attenuation methods on classification accuracy. The accuracy and F1-score of the final classification are both 0.85 when tested on a high signal-to-noise ratio subset of the field data. On the complete dataset including low signal-to-noise ratio events, an accuracy and F1-score of 0.80 are achieved. These results demonstrate the high effectiveness of the trained convolutional neural network on guided wave detection and classification of microseismic events inside and outside the Eagle Ford formation.

show abstract

Section: Discussionmentioning

confidence: 99%

Convolutional neural network‐based classification of microseismic events originating in a stimulated reservoir from distributed acoustic sensing data

Liu

Huff

Luo

et al. 2022

Geophysical Prospecting

View full text Add to dashboard Cite

show abstract

“…To identify normal and abnormal geophones from their corresponding PCCs, the proposed workflow additionally takes advantage of unsupervised clustering algorithms. Data clustering algorithms have been successfully utilized in diverse geophysical applications such as signal recognition, velocity picking, seismic facies analysis, and salt‐boundary delineation (Barnes and Laughlin, 2002; Marroquín, Brault and Hart 2009a, 2009b; Zhang and Lu, 2016; Galvis et al ., 2017; Xia et al ., 2018; Di et al ., 2018; Liu et al ., 2018; Wrona et al ., 2018; Huang, 2019; Waheed et al ., 2019). In the proposed workflow, the k ‐means clustering (MacQueen, 1967) is employed to distinguish groups of PCCs, which segregate normal and abnormal geophones.…”

Section: Introductionmentioning

confidence: 99%

Quality control for the geophone reorientation of ocean bottom seismic data using k‐means clustering

Jeong

Almubarak

Tsingas

2021

Geophysical Prospecting

View full text Add to dashboard Cite

During ocean bottom seismic acquisition, seafloor multicomponent geophones located in rugose and sloping water bottom can be affected by skewed energy distribution, such as leaked shear energy on the vertical geophones and leaked compressional energy on the horizontal geophones. To correct for the tilted energy distribution, which is one of most effective preprocessing steps, a geophone reorientation step is applied. This is a simple and straightforward process that applies a 3‐dimensional rotation matrix with respect to the orientation angles. Since the reorientation process highly affects the outcome of the entire data processing workflow, it has to be accompanied by a careful quality control process to verify its validity for the whole survey area. In this study, we propose a quality control workflow for the geophone reorientation by using unsupervised machine learning. A correlation analysis is employed to compare numerical versus analytical solutions of both the azimuth and the incidence angles for the direct arrivals. A comparison of both solutions aims to generate correlation coefficients that are indicative of the accuracy of geophone orientation. The correlation coefficients are subsequently investigated by the k‐means clustering algorithm to differentiate and identify normally and abnormally deployed/reoriented geophones. Numerical experiments on a field ocean bottom seismic data set confirm that the proposed workflow effectively provides reliable labels for normally and abnormally deployed/reoriented geophones. The labelling assigned by the proposed quality control workflow is a suitable indicator for abnormalities in the geophone reorientation step and will be helpful for further investigation, such as re‐correction or removal of abnormally reoriented geophones.

show abstract

Guidelines for Minimization of Uncertainties and Estimation of a Reliable Shear Wave Velocity Profile Using MASW Testing: A State-of-the-Art Review

Jakka

Desai

Foti

2022

Springer Tracts in Civil Engineering

View full text Add to dashboard Cite

Unsupervised machine learning algorithm for detecting and outlining surface waves on seismic shot gathers

Cited by 14 publications

References 50 publications

Convolutional neural network‐based classification of microseismic events originating in a stimulated reservoir from distributed acoustic sensing data

Convolutional neural network‐based classification of microseismic events originating in a stimulated reservoir from distributed acoustic sensing data

Quality control for the geophone reorientation of ocean bottom seismic data using k‐means clustering

Guidelines for Minimization of Uncertainties and Estimation of a Reliable Shear Wave Velocity Profile Using MASW Testing: A State-of-the-Art Review

Contact Info

Product

Resources

About