First Arrival Time Identification Using Transfer Learning With Continuous Wavelet Transform Feature Images

Liao, Xiaofang; Cao, Junxing; Hu, Jiangtao; You, Jiachun; Jiang, Xudong; Liu, Zhege

doi:10.1109/lgrs.2019.2955950

Cited by 24 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides feeding raw signals, various methods are proposed that take as inputs spectrograms [18], [19]. For example, Dokht et al [20] propose a CNN model to classify the input spectrogram into earthquake or noise.…”

Section: A Binary Classificationmentioning

confidence: 99%

Microseismic Event Classification With Time-, Frequency-, and Wavelet-Domain Convolutional Neural Networks

Jiang

Stankovic

Stanković

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Passive seismics help us understand subsurface processes, e.g. landslides, mining, geothermal systems etc. and help predict and mitigate their effects. Continuous monitoring results in long seismic records that may contain various sources, which need to be classified. Manual detection and labeling of recorded seismic events is not only time consuming but can also be inconsistent when done manually, even in the case where it is done by the same expert. Therefore, an automated approach for classification of continuous microseismic recordings based on a Convolutional Neural Network (CNN) is proposed, with a multiclassifier architecture that classifies earthquakes, rockfalls and low signal to noise ratio quakes. Furthermore, we propose three CNN architectures that take as input time series data, Short Time Fourier Transform (STFT) and Continuous Wavelet Transform (CWT) maps. The suitability of these three networks is rigorously assessed over five months of continuous seismometer recordings from the active Super-Sauze landslide in France. We observe that all three architectures have excellent and very similar performance. Furthermore, we evaluate transferability to a geographically distinct seismically active site in Larissa, Greece. We demonstrate that the proposed network is able to detect all 86 catalogued earthquake events, having only been trained on the Super-Sauze dataset and shows good agreement with manually detected events. This is promising as it could replace painstaking manual labelling of events in large recordings.

show abstract

Section: A Binary Classificationmentioning

confidence: 99%

Microseismic Event Classification With Time-, Frequency-, and Wavelet-Domain Convolutional Neural Networks

Jiang

Stankovic

Stanković

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Transfer learning can save a significant amount of training time by enabling the reuse of the CNN model trained in other domains. The author in [24] www.ijacsa.thesai.org applied the idea for FB identification and arrival time picking using Continuous Wavelet Transform (CWT) as input features for AlexNet, GoogleNet and SqueezeNet. Though the models had superb performance compared to STA/LTA and Adaptive Multiband Picking Algorithm (AMPA), the accuracy was only about 90%.A summary of all related work is given in Table I.…”

Section: Related Workmentioning

confidence: 99%

A Comparative Analysis of Machine Learning Models for First-break Arrival Picking

Ayub¹,

SanLinn²

2021

IJACSA

View full text Add to dashboard Cite

First-break (FB) picking is an important and necessary step in seismic data processing and there is a need to develop precise and accurate auto-picking solutions. Our investigation in this study includes eight machine learning models. We use 1195 raw traces to extract several features and train for accurate picking and monitoring the performance of each model using well-defined evaluation metrics. Careful investigation of the scores shows that a single metric alone is not sufficient to evaluate the arrival picking models in real-time. Correlation analysis of predicted probabilities and predicted classes of machine learning models confirm that the performance metrics that use predicted probabilities have higher score value than those that use predicted classes. Our study which incorporates comparisons of different machine learning models based on different performance metrics, training time, and feature importance indicates that the approach we developed in this study is helpful and provides an opportunity to determine the real-time suitability of different methodologies for automatic FB arrival picking with clear deep insight. Based on performance scores, we bench-marked the Extra Tree classifier as the most efficient model for FB arrival picking with accuracy and F1score above 95%.

show abstract

“…For a random walk [6,7] in a network, the expectation of the average first arrival time [8,9] from a vertex p to another vertex q selected according to the stable distribution of Markov process [10][11][12][13] is called Kemeny's constant of the network. Kemeny's constant is given by…”

Section: Introductionmentioning

confidence: 99%

Several Topological Indices of Two Kinds of Tetrahedral Networks

Liu

Fang

2021

Journal of Mathematics

View full text Add to dashboard Cite

Tetrahedral network is considered as an effective tool to create the finite element network model of simulation, and many research studies have been investigated. The aim of this paper is to calculate several topological indices of the linear and circle tetrahedral networks. Firstly, the resistance distances of the linear tetrahedral network under different classifications have been calculated. Secondly, according to the above results, two kinds of degree-Kirchhoff indices of the linear tetrahedral network have been achieved. Finally, the exact expressions of Kemeny’s constant, Randic index, and Zagreb index of the linear tetrahedral network have been deduced. By using the same method, the topological indices of circle tetrahedral network have also been obtained.

show abstract

First Arrival Time Identification Using Transfer Learning With Continuous Wavelet Transform Feature Images

Cited by 24 publications

References 14 publications

Microseismic Event Classification With Time-, Frequency-, and Wavelet-Domain Convolutional Neural Networks

Microseismic Event Classification With Time-, Frequency-, and Wavelet-Domain Convolutional Neural Networks

A Comparative Analysis of Machine Learning Models for First-break Arrival Picking

Several Topological Indices of Two Kinds of Tetrahedral Networks

Contact Info

Product

Resources

About