Machine learning reveals cyclic changes in seismic source spectra in Geysers geothermal field

Holtzman, B. K.; Paté, Arthur; Paisley, John; Waldhauser, F.; Repetto, Douglas

doi:10.1126/sciadv.aao2929

Cited by 85 publications

(61 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning (ML) analysis of seismic data is an expanding field, with recent studies focusing on event detection 21 , phase identification 22 , phase association 23,24 , or patterns in seismicity 25 . In the following, we investigate whether seismic signatures can be found in the period leading up to any known manifestation of major slow slip occurrence anywhere in the Cascadia region.…”

mentioning

confidence: 99%

An exponential build-up in seismic energy suggests a months-long nucleation of slow slip in Cascadia

et al. 2020

View full text Add to dashboard Cite

Slow slip events result from the spontaneous weakening of the subduction megathrust and bear strong resemblance to earthquakes, only slower. This resemblance allows us to study fundamental aspects of nucleation that remain elusive for classic, fast earthquakes. We rely on machine learning algorithms to infer slow slip timing from statistics of seismic waveforms. We find that patterns in seismic power follow the 14-month slow slip cycle in Cascadia, arguing in favor of the predictability of slow slip rupture. Here, we show that seismic power exponentially increases as the slowly slipping portion of the subduction zone approaches failure, a behavior that shares a striking similarity with the increase in acoustic power observed prior to laboratory slow slip events. Our results suggest that the nucleation phase of Cascadia slow slip events may last from several weeks up to several months.

show abstract

mentioning

confidence: 99%

An exponential build-up in seismic energy suggests a months-long nucleation of slow slip in Cascadia

et al. 2020

View full text Add to dashboard Cite

show abstract

“…We presume that variations in pore pressure, chemistry, or thermal properties may modulate or influence the emitted signal, but the origin of the signal is due to emissions coming from asperities on the fault interface. This is a point we intend to explore further in future work, along with evolution of these features with time (Holtzman et al, ).…”

Section: Discussionmentioning

confidence: 99%

Probing Slow Earthquakes With Deep Learning

Rouet‐Leduc

Hulbert

McBrearty

et al. 2020

Geophysical Research Letters

View full text Add to dashboard Cite

Slow earthquakes may trigger failure on neighboring locked faults that are stressed sufficiently to break, and slow slip patterns may evolve before a nearby great earthquake. However, even in the clearest cases such as Cascadia, slow earthquakes and associated tremor have only been observed in intermittent and discrete bursts. By training a convolutional neural network to detect known tremor on a single seismic station in Cascadia, we isolate and identify tremor and slip preceding and following known larger slow events. The deep neural network can be used for the detection of quasi‐continuous tremor, providing a proxy that quantifies the slow slip rate. Furthermore, the model trained in Cascadia recognizes tremor in other subduction zones and also along the San Andreas Fault at Parkfield, suggesting a universality of waveform characteristics and source processes, as posited from experiments and theory.

show abstract

“…Rather than other deep learning applications [7][8][9][10][11][12][13][14][15][16] where numerous earthquakes are tested, the current FMNet is only evaluated on four earthquakes with magnitudes larger than 5.4. This results from the limitation of historical moderate-to-large earthquakes that occurred in the study area.…”

Section: Discussionmentioning

confidence: 99%

“…The predicted focal mechanism of the real data can be retrieved by nding the peak values of the three output Gaussian probability distributions. This formalization of training labels greatly helps the convergence when training the network and the standard deviation of the Gaussian probability distribution affects the training convergence 15 . After testing, we nd the standard deviation of 10 achieves a stable training convergence for our neural network and thus is used in this study.…”

Section: Methodsmentioning

confidence: 99%

“…When a destructive earthquake occurs, real-time reporting of the earthquake parameters is of crucial importance for immediate destruction assessment and emergency evacuations. Recent efforts have been re ned towards applying AI technologies to estimate the source parameters because of its full automation, high e ciency, and human-like capability [4][5][6] , which has been remarkably demonstrated in numerous seismic processing tasks such as earthquake detection 7,8 , seismic phase picking [9][10][11] , magnitude estimation 12 , and other tasks [13][14][15][16][17] . Besides reporting the three basic parameters of an earthquake (i.e., origin time, location, and magnitude), it is also exceedingly important to derive the source focal mechanism in time to better understand various aspects of the earthquake.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-time determination of earthquake focal mechanism via deep learning

Kuang

Yuan²,

Zhang

2020

Preprint

View full text Add to dashboard Cite

An immediate report of the source focal mechanism with full automation after a destructive earthquake is crucial for timely characterizing the faulting geometry, evaluating the stress perturbation, and assessing the aftershock patterns. Advanced technologies such as Artificial Intelligence (AI) has been introduced to solve various problems in real-time seismology, but the real-time source focal mechanism is still a challenge. Here we propose a novel deep learning method namely Focal Mechanism Network (FMNet) to address this problem. The FMNet trained with 787,320 synthetic samples successfully estimates the focal mechanisms of four 2019 Ridgecrest earthquakes with magnitude larger than Mw 5.4. The network learns the global waveform characteristics from theoretical data, thereby allowing the extensive applications of the proposed method to regions of potential seismic hazards with or without historical earthquake data. After receiving data, the network takes less than two hundred milliseconds for predicting the source focal mechanism reliably on a single CPU.

show abstract

Machine learning reveals cyclic changes in seismic source spectra in Geysers geothermal field

Abstract: Machine learning methods identify subtle differences among seismic signals, enabling new insight into earthquake physics.

Cited by 85 publications

References 37 publications

An exponential build-up in seismic energy suggests a months-long nucleation of slow slip in Cascadia

An exponential build-up in seismic energy suggests a months-long nucleation of slow slip in Cascadia

Probing Slow Earthquakes With Deep Learning

Real-time determination of earthquake focal mechanism via deep learning

Contact Info

Product

Resources

About