Similarity of fast and slow earthquakes illuminated by machine learning

Hulbert, Claudia; Rouet‐Leduc, Bertrand; Johnson, Paul A.; Ren, Christopher X.; Rivière, Jacques; Bolton, David; Marone, Chris

doi:10.1038/s41561-018-0272-8

Cited by 144 publications

(161 citation statements)

References 28 publications

Supporting

Mentioning

149

Contrasting

Order By: Relevance

“…We find that the best features identified in Cascadia follow very similar patterns compared to those identified in the laboratory. In the case of laboratory slow slip events, the most important feature by far for forecasting failure time is the seismic power 13,34 , shown in Fig. 3c.…”

Section: Seismic Power Analysis and The Occurrence Of Slow Slip Inmentioning

confidence: 99%

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

et al. 2020

Self Cite

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

Section: Seismic Power Analysis and The Occurrence Of Slow Slip Inmentioning

confidence: 99%

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

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our XGBoost model isolates consistent frequencies present throughout the majority of the eruptions in our data set, with a surprisingly good performance for a single station. This type of analysis could potentially be utilized to search for previously undetected precursory pre-eruptive signals, in a similar approach to Rouet-Leduc, Hulbert, and Johnson (2018), and provide a path toward estimating the onset of eruptions, although it is important to note that there is little evidence for a continuously emitting source at the Piton de la Fournaise, unlike at the Juan de Fuca plate.…”

Section: Discussionmentioning

confidence: 99%

“…The aim here is to capture distributions of the seismic data within the time windows and relationships across different frequency bands for a given window. This has been shown to be an effective technique to parametrize geophysical time series data in various settings such as simulations (Ren et al, ), laboratory experiments (Hulbert et al, ; Rouet‐Leduc et al, ; Rouet‐Leduc, Hulbert, Bolton, et al, ), and real Earth (Rouet‐Leduc, Hulbert, & Johnson, ). In this case, these features consist of a range of percentiles and the range of the data, as well as normalized and nonnormalized higher‐order moments (see the supporting information for table describing features).…”

Section: Regional Settingmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Reveals the Seismic Signature of Eruptive Behavior at Piton de la Fournaise Volcano

Ren

Peltier

Ferrazzini

et al. 2020

Geophysical Research Letters

Self Cite

View full text Add to dashboard Cite

Volcanic tremor is key to our understanding of active magmatic systems, but due to its complexity, there is still a debate concerning its origins and how it can be used to characterize eruptive dynamics. In this study we leverage machine learning techniques using 6 years of continuous seismic data from the Piton de la Fournaise volcano (La Réunion island) to describe specific patterns of seismic signals recorded during eruptions. These results unveil what we interpret as signals associated with various eruptive dynamics of the volcano, including the effusion of a large volume of lava during the August–October 2015 eruption as well as the closing of the eruptive vent during the September–November 2018 eruption. The machine learning workflow we describe can easily be applied to other active volcanoes, potentially leading to an enhanced understanding of the temporal and spatial evolution of volcanic eruptions.

show abstract

“…As shown in [26] instantaneous statistical characteristics of AD appear as a "fingerprint" of the fault zone stress state. The variance of the seismic signal is the most important feature, although other statistical characteristics are also important [26,29,31]. The authors of [13] stressed that the kurtosis of the acoustic signal is an additional powerful feature for the prediction of TTF.…”

Section: Feature Engineeringmentioning

confidence: 99%

Machine Learning Modelling and Feature Engineering in Seismology Experiment

Брыков

Petryshynets

Pruncu

et al. 2020

Sensors

View full text Add to dashboard Cite

This article aims to discusses machine learning modelling using a dataset provided by the LANL (Los Alamos National Laboratory) earthquake prediction competition hosted by Kaggle. The data were obtained from a laboratory stick-slip friction experiment that mimics real earthquakes. Digitized acoustic signals were recorded against time to failure of a granular layer compressed between steel plates. In this work, machine learning was employed to develop models that could predict earthquakes. The aim is to highlight the importance and potential applicability of machine learning in seismology The XGBoost algorithm was used for modelling combined with 6-fold cross-validation and the mean absolute error (MAE) metric for model quality estimation. The backward feature elimination technique was used followed by the forward feature construction approach to find the best combination of features. The advantage of this feature engineering method is that it enables the best subset to be found from a relatively large set of features in a relatively short time. It was confirmed that the proper combination of statistical characteristics describing acoustic data can be used for effective prediction of time to failure. Additionally, statistical features based on the autocorrelation of acoustic data can also be used for further improvement of model quality. A total of 48 statistical features were considered. The best subset was determined as having 10 features. Its corresponding MAE was 1.913 s, which was stable to the third decimal point. The presented results can be used to develop artificial intelligence algorithms devoted to earthquake prediction.

show abstract

Similarity of fast and slow earthquakes illuminated by machine learning

Cited by 144 publications

References 28 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

Machine Learning Reveals the Seismic Signature of Eruptive Behavior at Piton de la Fournaise Volcano

Machine Learning Modelling and Feature Engineering in Seismology Experiment

Contact Info

Product

Resources

About