scholarly journals Single-Station Coda Wave Interferometry: A Feasibility Study Using Machine Learning

Materials ◽  
2021 ◽  
Vol 14 (13) ◽  
pp. 3451
Author(s):  
Erik H. Saenger ◽  
Claudia Finger ◽  
Sadegh Karimpouli ◽  
Pejman Tahmasebi
Keyword(s):  
Machine Learning ◽  
Feasibility Study ◽  
Crack Density ◽  
Machine Learning Techniques ◽  
Coda Wave ◽  
Intrinsic Attenuation ◽  
Single Station ◽  
Background Material ◽  
Velocity Changes ◽  
Coda Wave Interferometry

Coda wave interferometry usually is applied with pairs of stations analyzing the signal transmitted from one station to another. A feasibility study was performed to evaluate if one single station could be used. In this case, the reflected coda wave signal from a zone to be identified was analyzed. Finite-difference simulations of wave propagation were used to study whether ultrasonic measurements could be used to detect velocity changes in such a zone up to a depth of 1.6 m in a highly scattering medium. For this aim, 1D convolutional neural networks were used for prediction. The crack density, the crack length, and the intrinsic attenuation were varied in the considered background material. The influence of noise and the sensor width was elaborated as well. It was shown that, in general, the suggested single-station approach is a possible way to identify damage zones, and the method was robust against the studied variations. The suggested workflow also took advantage of machine-learning techniques, and can be transferred to the detection of defects in concrete structures.

The Role of Uncertainty in Machine Learning As an Element of Control for Material Systems and Structures

2018 ◽  
Author(s):  
Muthu Ram Prabhu Elenchezhian ◽  
Md Rassel Raihan ◽  
Kenneth Reifsnider
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Composite Material ◽  
Health Monitoring ◽  
Crack Density ◽  
Regression Function ◽  
Fatigue Loading ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Material State

Recurrent neural networks (RNN) have been used to interpret data in situations wherein our knowledge of the active physics is incomplete. The currency of these methods is the data that are generated by a physical system. Unfortunately, if we are uncertain about the physics of the system, we also do not know the level of uncertainty in the data that we use to represent it. Typically, data provided to an RNN is provided by measurements of system state information, e.g., data that define speed, position, accelerations, configurations of system elements (like the flaps and elevators on an airplane) etc. But recently, data are being collected that indicate the state of the materials themselves that are used to construct the system. Material state may include the defect state of the materials such as the crack density and patterns in composite material in structural elements (obtained from health monitoring data). In this paper, we address the question of teaching a control system (e.g., for testing equipment, aircraft control systems, health monitoring systems, etc.) to recognize composite material degradation during service and to adjust applied loads and fields as part of a control scheme to avoid failure of the material during service. Topics will include defining a proper cost function for the above objectives, formulation of a ‘failure hypothesis’ as a regression function, and the quantification of uncertainty when the physics of the situation is not completely defined. Examples of machine learning techniques for a uniaxial fatigue loading of composite coupons with a circular hole are presented. Example models are random forest regression algorithms and artificial neural networks for linear regression.

scholarly journals Relative source location using coda-wave interferometry: Method, code package, and application to mining-induced earthquakes

Geophysics ◽  
2019 ◽  
Vol 84 (3) ◽  
pp. F73-F84 ◽  
Author(s):  
Youqian Zhao ◽  
Andrew Curtis
Keyword(s):  
Single Channel ◽  
Source Region ◽  
Source Location ◽  
Coda Wave ◽  
Data Set ◽  
Seismic Stations ◽  
Location Method ◽  
Wide Range ◽  
Single Station ◽  
Coda Wave Interferometry

A wide range of applications requires the relative locations of sources of energy to be known accurately. Most conventional location methods are either subject to errors that depend strongly on inaccuracy in the model of propagation velocity used or demand a well-distributed network of surrounding seismic stations to produce reliable results. A new source location method based on coda-wave interferometry (CWI) is relatively insensitive to the number of seismic stations and to the source-to-station azimuthal coverage. Therefore, it opens new avenues for research, for applications in areas with unfavorable recording geometries, and for applications that require a complementary method. This method uses CWI to estimate distances between pairs of seismic events with a similar source mechanism recorded at the same station. These separation estimates are used to solve for the locations of clusters of events relative to one another within a probabilistic framework through optimization. It is even possible to find the relative locations of clusters of events with one single-channel station. Given these advantages, it is likely that one reason that the method is not used more widely is the lack of reliable code that implements this multistage method. Therefore, we have developed a well-commented MATLAB code that does so, and we evaluate examples of its applications. It can be used with seismic data from a single-station channel, and it enables data recorded by different channels and stations to be used simultaneously. It is therefore possible to combine data from permanent yet sparse networks and from temporary arrays closer to the source region. We use the code to apply the location method to a selected data set of the New Ollerton earthquakes in England to demonstrate the validity of the code. The worked example is provided within the package. A way to assess the quality of the location results is also provided.

Classification of volcanic and tectonic earthquakes in Kamchatka (Russia) with different machine learning techniques

2020 ◽  
Author(s):  
Natalia Galina ◽  
Nikolai Shapiro ◽  
Leonard Seydoux ◽  
Dmitry Droznin
Keyword(s):  
Machine Learning ◽  
Subduction Zone ◽  
Aftershock Sequence ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Learning Approaches ◽  
Shiveluch Volcano ◽  
Agglomerative Clustering ◽  
Learning Techniques ◽  
Single Station

<p>Kamchatka is an active subduction zone that exhibits intense seismic and volcanic activities. As a consequence, tectonic and volcanic earthquakes are often nearly simultaneously recorded at the same station. In this work, we consider seismograms recorded between December 2018 and April 2019. During this time period when the M=7.3 earthquake followed by an aftershock sequence occurred nearly simultaneously with a strong eruption of Shiveluch volcano. As a result, stations of the Kamchatka seismic monitoring network recorded up to several hundreds of earthquakes per day. In total, we detected almost 7000 events of different origin using a simple automatic detection algorithm based on signal envelope amplitudes. Then, for each detection different features have been extracted. We started from simple signal parameters (amplitude, duration, peak frequency, etc.), unsmoothed and smoothed spectra and finally used a multi-dimensional signal decomposition (scattering coefficients). For events classification both unsupervised (K-means, agglomerative clustering) and supervised (Support Vector Classification, Random Forest) classic machine learning techniques were performed on all types of extracted features. Obtained results are quite stable and do not vary significantly depending on features and method choice. As a result, the machine learning approaches allow us to clearly separate tectonic subduction-zone earthquakes and those associated with the Shiveluch volcano eruptions based on data of a single station.</p>

Multiplet Based Time Lapse Velocity Changes Prior to the 2018 Eruption of Sierra Negra Volcano, Galapagos Island Observed with Coda Wave Interferometry

2020 ◽  
Author(s):  
Mariantonietta Longobardi ◽  
James Grannel ◽  
Christopher Bean ◽  
Andrew Bell ◽  
Mario Ruiz
Keyword(s):  
Wave Velocity ◽  
Seismic Wave ◽  
Seismic Velocity ◽  
Time Lapse ◽  
Coda Wave ◽  
Seismic Wave Velocity ◽  
Galapagos Island ◽  
Velocity Changes ◽  
Coda Wave Interferometry ◽  
Sierra Negra Volcano

<p align="justify"><span>Changes in external stress state and fluid content alter the mechanical properties of an geological media. </span><span>Variations in seismic wave velocity can be used as proxies for changes in stress the onset of mechanical demage and/or possible fluid ingression. Temporal variations in seismic wave velocity have previously been monitored and observed prior to volcanic eruptions. In the absence of additional constraints related to stress or fluid changes on the volcano, these pre-eruptive changes are difficult to interpret and hence the causes of them are often not well understood. </span><span>In this study, Coda Wave Interferometry (CWI) is used to measure time-lapse changes in seismic velocity on seismic multiplets (repeating similar earthquakes). In particular, we focus our analysis on using this technique to calculate the velocity changes on the data recorded prior to the 2018 eruption of Sierra Negra volcano, Galapagos Island.</span> <span>On 26th June 2018 at 09:15 UTC, a magnitude 5.3 earthquake occurred near the south-west caldera rim and an intense seismic swarm started around 17:15 UTC. Seismic tremor dominated at about 19:45 UTC, which marked the onset of the eruption. </span><span>A very large seismicity sequence preceded the eruption. The pricise relationship between the magnitude 5.3 event and the eruption is not fully constraind. Here we search for multiplets in order to achieve high time resolution velocity change information in the hours between the large earthquake and the eruption. </span><span>Our aim is to understand whether changes in seismic velocity measured with CWI on multiplets method provide new insight into the physical processes related to the eruption.</span></p><p align="justify"><br><br></p>

Sign in / Sign up

Export Citation Format

Share Document