scholarly journals Spatial-temporal Evolution of Injection Induced Earthquakes in Weiyuan Area by Machine-Learning Phase Picker and Waveform Cross-correlation

2021 ◽  
Vol 5 (0) ◽  
pp. 0-0
Author(s):  
Wing Ching Jeremy Wong ◽  
◽  
◽  
JinPing Zi ◽  
HongFeng Yang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cross Correlation ◽  
Temporal Evolution ◽  
Learning Phase ◽  
Induced Earthquakes ◽  
Waveform Cross Correlation

scholarly journals Injection‐Induced Earthquakes on Complex Fault Zones of the Raton Basin Illuminated by Machine‐Learning Phase Picker and Dense Nodal Array

2020 ◽  
Vol 47 (14) ◽  
Author(s):  
Ruijia Wang ◽  
Brandon Schmandt ◽  
Miao Zhang ◽  
Margaret Glasgow ◽  
Eric Kiser ◽  
...  
Keyword(s):  
Machine Learning ◽  
Fault Zones ◽  
Learning Phase ◽  
Induced Earthquakes ◽  
Complex Fault

scholarly journals Injection-induced earthquakes on complex fault zones of the Raton Basin illuminated by machine-learning phase picker and dense nodal array

2020 ◽  
Author(s):  
Ruijia Wang ◽  
Brandon Schmandt ◽  
Miao Zhang ◽  
Margaret Elizabeth Glasgow ◽  
Eric Kiser ◽  
...  
Keyword(s):  
Machine Learning ◽  
Fault Zones ◽  
Learning Phase ◽  
Induced Earthquakes ◽  
Complex Fault

Machine learning phase space quantum dynamics approaches

2021 ◽  
Vol 154 (18) ◽  
pp. 184104
Author(s):  
Xinzijian Liu ◽  
Linfeng Zhang ◽  
Jian Liu
Keyword(s):  
Machine Learning ◽  
Phase Space ◽  
Quantum Dynamics ◽  
Learning Phase

scholarly journals Cognitive Driven Multilayer Self-Paced Learning with Misclassified Samples

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-10
Author(s):  
Qi Zhu ◽  
Ning Yuan ◽  
Donghai Guan
Keyword(s):  
Machine Learning ◽  
Learning Process ◽  
Human Learning ◽  
Learning Phase ◽  
Machine Learning Algorithms ◽  
Learning Difficulty ◽  
Learning Models ◽  
Negative Effects ◽  
Initial Learning

In recent years, self-paced learning (SPL) has attracted much attention due to its improvement to nonconvex optimization based machine learning algorithms. As a methodology introduced from human learning, SPL dynamically evaluates the learning difficulty of each sample and provides the weighted learning model against the negative effects from hard-learning samples. In this study, we proposed a cognitive driven SPL method, i.e., retrospective robust self-paced learning (R2SPL), which is inspired by the following two issues in human learning process: the misclassified samples are more impressive in upcoming learning, and the model of the follow-up learning process based on large number of samples can be used to reduce the risk of poor generalization in initial learning phase. We simultaneously estimated the degrees of learning-difficulty and misclassified in each step of SPL and proposed a framework to construct multilevel SPL for improving the robustness of the initial learning phase of SPL. The proposed method can be viewed as a multilayer model and the output of the previous layer can guide constructing robust initialization model of the next layer. The experimental results show that the R2SPL outperforms the conventional self-paced learning models in classification task.

Use of Waveform Cross Correlation to Reconstruct the Aftershock Sequence of the August 14, 2016, Sakhalin Earthquake

2019 ◽  
Vol 55 (5) ◽  
pp. 544-558
Author(s):  
I. O. Kitov ◽  
S. B. Turuntaev ◽  
A. V. Konovalov ◽  
A. A. Stepnov ◽  
V. V. Pupatenko
Keyword(s):  
Cross Correlation ◽  
Aftershock Sequence ◽  
Waveform Cross Correlation

scholarly journals Machine Learning Based Preprocessing to Ensure Validity of Cross-Correlated Ultrasound Signals for Time-of-Flight Measurements

2021 ◽  
Vol 40 (1) ◽  
Author(s):  
Simon Herter ◽  
Sargon Youssef ◽  
Michael M. Becker ◽  
Sarah C. L. Fischer
Keyword(s):  
Machine Learning ◽  
High Precision ◽  
Cross Correlation ◽  
Complex Structure ◽  
Time Of Flight ◽  
Industrial Applications ◽  
Ultrasonic Signals ◽  
Ultrasonic Time ◽  
Flight Measurement ◽  
Flight Measurements

AbstractHigh precision ultrasonic time-of-flight measurement is a well known part of non-destructive evaluation used in many scientific and industrial applications, for example stress evaluation or defect detection. Although ultrasonic time-of-flight measurements are widely used there are some limitations where high noise and distorted ultrasonic signals are conflicting with the demand for high precision measurements. Cross-correlation based time-of-flight measurement is one strategy to increase reliability but also exhibits some ambiguous correlation states yielding to wrong time-of-flight results. To improve the reliability of these measurements a new machine learning based approach is presented based on experimental data collected on tightened bolts. Due to the complex structure of the bolts the ultrasonic signal is influenced by boundary conditions of the geometry which lead to high number of the ambiguous cross-correlation results in practice. In this particular application, bolts are in practice evaluated discontinuously and without knowledge of the time-of-flight in the unloaded condition which prevents the use of all other available comparative preprocessing techniques to detect time-of-flight shifts. Three different preprocessing strategies were investigated based on variations in the bolting configurations to ensure a machine learning based model capable of predicting the state of the cross-correlation function for different bolting parameters. With this approach, we achieve up to 100% classification accuracy for both longitudinal and transversal ultrasonic signals under laboratory conditions. In the future the method should be extended to become more robust and be applicable in real-time for industrial applications.

Comprehensive analysis of the March 7, 2019 Somogyszob, Hungary earthquake cluster

2020 ◽  
Author(s):  
Zoltán Wéber ◽  
Barbara Czecze ◽  
Zoltán Gráczer ◽  
Bálint Süle ◽  
Gyöngyvér Szanyi ◽  
...  
Keyword(s):  
Cross Correlation ◽  
Main Shock ◽  
Moment Tensor ◽  
Thrust Fault ◽  
Comprehensive Analysis ◽  
Waveform Cross Correlation ◽  
Event Location ◽  
Earthquake Cluster ◽  
The Moment ◽  
Fault Mechanism

<div>A magnitude ML 4.0 earthquake struck southwest Hungary on March 7, 2019. The earthquake was reported to be felt in some 53 localities with maximum intensity V on the EMS scale. The earthquake was preceded by four foreshocks and followed by four aftershocks. The hypoDD solutions using differential travel times from waveform cross-correlation show significant improvements in event location. We were able to determine the moment tensor solutions for the main shock and one of the foreshocks and aftershocks, each representing thrust fault mechanism with a horizontal P-axis pointing towards N-NE. The obtained moment magnitudes range from Mw 1.5 to 3.8 with source radii between 100 and 500 m. The stress drop spans from 12 to 19 bars.</div><div> <div> <div> </div> </div> </div>

Sign in / Sign up

Export Citation Format

Share Document