Deep Learning Models Augment Analyst Decisions for Event Discrimination

Linville, Lisa; Pankow, K. L.; Draelos, Timothy J.

doi:10.1029/2018gl081119

Cited by 97 publications

(52 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…phase onset picking and earthquake detection methods to lower the magnitude detection level (e.g., Ross et al, 2018a;Zhu et al, 2019a;Walter et al, 2020;Mousavi et al, 2020, amongst others); ii.) discriminate between volcanic and tectonic earthquakes (e.g., Esposito et al, 2006) and, in the future, after updating INSTANCE with new data and metadata, discriminate earthquakes and other sources of seismic energy (e.g., sonic booms, quarry blasts, underwater explosions) often felt by the population (e.g., Del Pezzo et al, 2003;Linville et al, 2019); iii.) the rapid and accurate characterization of the earthquake source, distance, depth (e.g., Perol et al, 2018;Trugman and Shearer, 2018;Kriegerowski et al, 2018;Zhang et al, 2020;Lomax et al, 2019;Mousavi and Beroza, 2020;Münchmeyer et al, 2021) and of the ground shaking (e.g., Alavi, 2011;Derras et al, 2012;Derras, 2014;Jozinovic et al, 2020;Münchmeyer et al, 2020).…”

Section: Applicationsmentioning

confidence: 99%

INSTANCE – the Italian seismic dataset for machine learning

Michelini

Cianetti

Gaviano

et al. 2021

Preprint

View full text Add to dashboard Cite

Abstract. The Italian earthquake waveform data are here collected in a dataset suited for machine learning analysis (ML) applications. The dataset consists of near 1.2 million three-component (3C) waveform traces from about 50,000 earthquakes and more than 130,000 noise 3C waveform traces, for a total of about 43,000 hours of data and an average of 21 3C traces are provided per event. The earthquake list is based on the Italian seismic bulletin (http://terremoti.ingv.it/bsi) of the ``Istituto Nazionale di Geofisica e Vulcanologia'' between January 2005 and January 2020 and it includes events in the magnitude range between 0.0 and 6.5. The waveform data have been recorded primarily by the Italian National Seismic Network (network code IV) and include both weak (HH, EH channels) and strong motion recordings (HN channels). All the waveform traces have a length of 120 s, are sampled at 100 Hz, and are provided both in counts and ground motion units after deconvolution of the instrument transfer functions. The waveform dataset is accompanied by metadata consisting of more than 100 parameters providing comprehensive information on the earthquake source, the recording stations, the trace features, and other derived quantities. This rich set of metadata allows the users to target the data selection for their own purposes. Many of these metadata can be used as labels in ML analysis or for other studies. The dataset, assembled in HDF5 format, is available at http://doi.org/10.13127/instance (Michelini et al., 2021).

show abstract

Section: Applicationsmentioning

confidence: 99%

INSTANCE – the Italian seismic dataset for machine learning

Michelini

Cianetti

Gaviano

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Buscombe and Carini, ; Buscombe et al ., ; Buscombe and Ritchie, ; Linville et al . ; Luo et al ., ; Jiang et al ., ; Reichstein et al ., ). The basic premise of applications such as these, compared to those of other machine learning subcategories, is that it circumvents the need (and the effort required) to make decisions about what extracted image features are important to a specific task, which tends to make the models both more subjective and more powerful.…”

Section: Introductionmentioning

confidence: 99%

SediNet: a configurable deep learning model for mixed qualitative and quantitative optical granulometry

Buscombe

2019

Earth Surf Processes Landf

View full text Add to dashboard Cite

I describe a configurable machine‐learning framework to estimate a suite of continuous and categorical sedimentological properties from photographic imagery of sediment, and to exemplify how machine learning can be a powerful and flexible tool for automated quantitative and qualitative measurements from remotely sensed imagery. The model is tested on a dataset consisting of 409 images and associated detailed label data. The data are from a much wider sedimentological spectrum than previous optical granulometry studies, consisting of both well‐ and poorly sorted sediment, terrigenous, carbonate, and volcaniclastic sands and gravels and their mixtures, and grain sizes spanning over two orders of magnitude. I demonstrate the model framework by configuring it in several ways, to estimate two categories (describing grain shape and population, respectively) and nine numeric grain size percentiles in pixels from a single input image. Grain size is then recovered using the physical size of a pixel. Finally, I demonstrate that the model can be configured and trained to estimate equivalent sieve diameters directly from image features, without the need for area‐to‐mass conversion formulas and without even knowing the scale of one pixel. Thus it is the only optical granulometry method proposed to date that does not necessarily require image scaling. The flexibility of the model framework should facilitate numerous application in the spatiotemporal monitoring of the grain size distribution, shape, mineralogy and other quantities of interest of sedimentary deposits as they evolve, as well as other texture‐based proxies extracted from remotely sensed imagery. © 2019 John Wiley & Sons, Ltd.

show abstract

“…Machine learning is a tool to map relationships through a functional model defined using information extracted from data. Various studies concluded that supervised machine learning can identify subtle seismic waveform variations to classify earthquakes, tremors, landslides, avalanches, and mining explosions (Aguiar & Beroza, 2014; Hammer et al, 2013; Linville et al, 2019; Mousavi et al, 2016; Perol et al, 2018; Ross, Meier, & Hauksson, 2018; Ross, Meier, Hauksson, & Heaton, 2018; Rouet‐Leduc et al, 2019). Correctly labeled data with a diverse mixture of seismic signals and a large enough quantity with respect to the complexity of the classification task and type of employed model are necessary for supervised model training (Bishop, 2006).…”

Section: Introductionmentioning

confidence: 99%

Identifying Different Classes of Seismic Noise Signals Using Unsupervised Learning

Johnson

Ben‐Zion

Meng

et al. 2020

Geophysical Research Letters

View full text Add to dashboard Cite

Proper classification of nontectonic seismic signals is critical for detecting microearthquakes and developing an improved understanding of ongoing weak ground motions. We use unsupervised machine learning to label five classes of nonstationary seismic noise common in continuous waveforms. Temporal and spectral features describing the data are clustered to identify separable types of emergent and impulsive waveforms. The trained clustering model is used to classify every 1 s of continuous seismic records from a dense seismic array with 10–30 m station spacing. We show that dominate noise signals can be highly localized and vary on length scales of hundreds of meters. The methodology demonstrates the complexity of weak ground motions and improves the standard of analyzing seismic waveforms with a low signal‐to‐noise ratio. Application of this technique will improve the ability to detect genuine microseismic events in noisy environments where seismic sensors record earthquake‐like signals originating from nontectonic sources.

show abstract

Deep Learning Models Augment Analyst Decisions for Event Discrimination

Cited by 97 publications

References 20 publications

INSTANCE – the Italian seismic dataset for machine learning

INSTANCE – the Italian seismic dataset for machine learning

SediNet: a configurable deep learning model for mixed qualitative and quantitative optical granulometry

Identifying Different Classes of Seismic Noise Signals Using Unsupervised Learning

Contact Info

Product

Resources

About