Automatic classification with an autoencoder of seismic signals on a distributed acoustic sensing cable

Chien, Chih-Chieh; Jenkins, William F.; Gerstoft, Peter; Zumberge, Mark A.; Mellors, R. J.

doi:10.1016/j.compgeo.2022.105223

Cited by 4 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For data clustering, Jenkins et al [30] developed a machine learning technique for low frequency icequakes and earthquake data. Chien et al [33] applied unsupervised clustering for microseismicity induced by fluid injection. Recently, Mousavi and Beroza [34] gave a thorough review of machine learning methods in earthquake seismology.…”

Section: Introductionmentioning

confidence: 99%

Monitoring Subsurface Fracture Flow Using Unsupervised Deep Learning of Borehole Microseismic Waveform Data

Duan,

Huang,

Gross

et al. 2024

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Fracture flow is the fluid movement in a fracture or a fracture zone. Since fracture flow can induce long-duration (LD) microseismic events, classifying different types of microseismicity is crucial for reliable monitoring of subsurface fracture flow. We analyze hydraulic fracturing-induced microseismic data recorded by borehole geophones and find four types of microseismic events: two types of short-duration events and two types of LD events. Among the two types of LD events, one contains frequency-drop long-duration (FDLD) characteristics and the other exhibits low-frequency longduration (LFLD) characteristics. We employ an unsupervised machine learning algorithm based on the U-Net convolutional network to classify microseismic events. Our study shows that LFLD events occur only during the proppant injection period of hydraulic fracturing, and that the spatiotemporal distributions of the LFLD events gradually grow from the fracture stimulation wells outward with time. Also, the cumulative seismic moment of the LFLD events is proportional to the cumulative amount of injected proppant. These results can be used to optimize hydraulic fracturing parameters in unconventional reservoirs.

show abstract

Section: Introductionmentioning

confidence: 99%

Monitoring Subsurface Fracture Flow Using Unsupervised Deep Learning of Borehole Microseismic Waveform Data

Duan,

Huang,

Gross

et al. 2024

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The research findings of these scholars have achieved the identification of genuine microseismic signals from non-microseismic ones. On the other hand, Chien [40] built a convolutional self-coding network to identify real microseismic signals, classifying them according to the depth of the formation at which they were generated. Mousavi [41] studied the signal characteristics of deep and shallow microearthquakes and clustered them based on these characteristics using machine learning techniques.…”

Section: Introductionmentioning

confidence: 99%

Classification of Microseismic Signals Using Machine Learning

Chen,

Cui,

et al. 2024

Processes

View full text Add to dashboard Cite

The classification of microseismic signals represents a fundamental preprocessing step in microseismic monitoring and early warning. A microseismic signal source rock classification method based on a convolutional neural network is proposed. First, the characteristic parameters of the microseismic signals are extracted, and a convolutional neural network is constructed for the analysis of these parameters; then, the mapping relationship model between the characteristic parameters of the microseismic signals and the rock class is established. The feasibility of the proposed method in differentiating acoustic emission signals under different load conditions is verified by using acoustic emission data from laboratory uniaxial compression tests, Brazilian splitting tests, and shear tests. In the three distinct laboratory experiments, the proposed method achieved a source rock classification accuracy of greater than 90% for acoustic emission signals. The proposed and verified method provides a new basis for the preprocessing of microseismic signals.

show abstract

DASEventNet: AI‐Based Microseismic Detection on Distributed Acoustic Sensing Data From the Utah FORGE Well 16A (78)‐32 Hydraulic Stimulation

Yu,

Zhu,

Marone

et al. 2024

JGR Solid Earth

View full text Add to dashboard Cite

Distributed acoustic sensing (DAS) has emerged as a promising seismic technology for monitoring microearthquakes (MEQs) with high spatial resolution. Efficient algorithms are needed for processing large DAS data volumes. This study introduces a deep learning (DL) model based on a Residual Convolutional Neural Network (ResNet) for detecting MEQs using DAS data, named as DASEventNet. The test data were collected from the Utah FORGE 16A (78)‐32 hydraulic stimulation experiments conducted in April 2022. The DASEventNet model achieves a remarkable accuracy of 100% when discriminating MEQs from noise in the raw test set of 260 examples. Surprisingly, the model identified weak MEQ signatures that have been manually categorized as noise. The decision‐making process with the model is decoded by the classic activation map, which illuminates learning features of the DASEventNet model. These features provide clear illustrations of weak MEQs and varied noise types. Finally, we apply the trained model to the entire period (∼7 days) of continuous DAS recordings and find that it discovers >5,700 new MEQs, previously unregistered in the public Silixa DAS catalog. The DASEventNet model significantly outperforms the traditional seismic method Short‐Term Average/Long‐Term Average (STA/LTA), which detected only 1,307 MEQs. The DASEventNet detection threshold is Mw−1.80 compared to the minimum magnitude of Mw−1.14 detected by STA/LTA. The spatiotemporal distribution of the newly identified MEQs defines an extensive stimulation zone and more accurately characterizes fracture geometry. Our results highlight the potential of DL for long‐term, real‐time microseismic monitoring that can improve enhanced geothermal systems and other activities that include subsurface hydraulic fracturing.

show abstract

Automatic classification with an autoencoder of seismic signals on a distributed acoustic sensing cable

Cited by 4 publications

References 35 publications

Monitoring Subsurface Fracture Flow Using Unsupervised Deep Learning of Borehole Microseismic Waveform Data

Monitoring Subsurface Fracture Flow Using Unsupervised Deep Learning of Borehole Microseismic Waveform Data

Classification of Microseismic Signals Using Machine Learning

DASEventNet: AI‐Based Microseismic Detection on Distributed Acoustic Sensing Data From the Utah FORGE Well 16A (78)‐32 Hydraulic Stimulation

Contact Info

Product

Resources

About