scholarly journals Comparing Artificial Neural Networks with Traditional Ground-Motion Models for Small-Magnitude Earthquakes in Southern California

2021 ◽  
Author(s):  
Alexis Klimasewski ◽  
Valerie Sahakian ◽  
Amanda Thomas
Keyword(s):  
Machine Learning ◽  
Ground Motion ◽  
Southern California ◽  
Small Magnitude ◽  
Motion Models ◽  
Input Parameters ◽  
Ann Models ◽  
Artificial Neural ◽  
A Site ◽  
Ground Motion Models

ABSTRACT Traditional, empirical ground-motion models (GMMs) are developed by prescribing a functional form between predictive parameters and ground-motion intensity measures. Machine-learning techniques may serve as a fully data-driven alternative to widely used regression techniques, as they do not require explicitly defining these relationships. Although, machine-learning methods offer a nonparametric alternative to regression methods, there are few studies that develop and assess performance of traditional versus machine-learning GMMs side by side. We compare the performance and behavior of these two approaches: a mixed-effects maximum-likelihood (MEML) model and a feed-forward artificial neural network (ANN). We develop and train both models on the same dataset from southern California. We subsequently test both models on a dataset from the 2019 Ridgecrest sequence, in a new region and on magnitudes outside the range of the training dataset, to examine model portability. Our models estimate horizontal peak ground acceleration, and the input parameters include moment magnitude (M) and hypocentral distance (Rhyp), and some include a site parameter, either VS30 or κ0. We find that, with our small set of input parameters, the ANN generally shows more site-specific predictions than the MEML model with more variation between sites, and, performs better than their corresponding MEML model, when applied “blind” to our testing dataset (in which the MEML random effects cannot be considered). Although, previous studies have found that κ0 may be a better predictor of site effects than VS30, we found similar performance, suggesting that including a site parameter may be more important than the physical meaning of the parameter. Finally, when applying our models to our Ridgecrest dataset, we find that both methods perform well; however, the MEML models perform better with the new dataset than the ANN models, suggesting that future applications of ANN models may need to consider how to accommodate model portability.

Evaluation of Ground-Motion Models for USGS Seismic Hazard Models Using Near-Source Instrumental Ground-Motion Recordings of the Ridgecrest, California, Earthquake Sequence

2020 ◽  
Vol 110 (4) ◽  
pp. 1517-1529
Author(s):  
Daniel E. McNamara ◽  
Emily L. G. Wolin ◽  
Morgan P. Moschetti ◽  
Eric M. Thompson ◽  
Peter M. Powers ◽  
...  
Keyword(s):  
Seismic Hazard ◽  
Ground Motion ◽  
Southern California ◽  
Epistemic Uncertainty ◽  
Site Amplification ◽  
Earthquake Sequence ◽  
Scoring Method ◽  
Motion Models ◽  
Tectonically Active ◽  
Ground Motion Models

ABSTRACT We evaluated the performance of 12 ground-motion models (GMMs) for earthquakes in the tectonically active shallow crustal region of southern California using instrumental ground-motion observations from the 2019 Ridgecrest, California, earthquake sequence (Mw 4.0–7.1). The sequence was well recorded by the Southern California Seismic Network and rapid response portable aftershock monitoring stations. Ground-motion recordings of this size and proximity are rare, valuable, and independent of GMM development, allowing us to evaluate the predictive powers of GMMs. We first compute total residuals and compare the probability density functions, means, and standard deviations of the observed and predicted ground motions. Next we use the total residuals as inputs to the probabilistic scoring method (log-likelihood [LLH]). The LLH method provides a single score that can be used to weight GMMs in the U.S. Geological Survey (USGS) National Seismic Hazard Model (NSHM) logic trees. We also explore GMM performance for a range of earthquake magnitudes, wave propagation distances, and site characteristics. We find that the Next Generation Attenuation West-2 (NGAW2) active crust GMMs perform well for the 2019 Ridgecrest, California, earthquake sequence and thus validate their use in the 2018 USGS NSHM. However, significant ground-motion residual scatter remains unmodeled by NGAW2 GMMs due to complexities such as local site amplification and source directivity. Results from this study will inform logic-tree weights for updates to the USGS National NSHM. Results from this study support the use of nonergodic GMMs that can account for regional attenuation and site variations to minimize epistemic uncertainty in USGS NSHMs.

A Suite of Alternative Ground-Motion Models (GMMs) for Israel

2021 ◽  
Author(s):  
Soumya Kanti Maiti ◽  
Gony Yagoda-Biran ◽  
Ronnie Kamai
Keyword(s):  
Seismic Hazard ◽  
Ground Motion ◽  
Empirical Data ◽  
Epistemic Uncertainty ◽  
Ground Motions ◽  
Plate Boundary ◽  
Strong Motion ◽  
Engineering Applications ◽  
Motion Models ◽  
Ground Motion Models

ABSTRACT Models for estimating earthquake ground motions are a key component in seismic hazard analysis. In data-rich regions, these models are mostly empirical, relying on the ever-increasing ground-motion databases. However, in areas in which strong-motion data are scarce, other approaches for ground-motion estimates are sought, including, but not limited to, the use of simulations to replace empirical data. In Israel, despite a clear seismic hazard posed by the active plate boundary on its eastern border, the instrumental record is sparse and poor, leading to the use of global models for hazard estimation in the building code and all other engineering applications. In this study, we develop a suite of alternative ground-motion models for Israel, based on an empirical database from Israel as well as on four data-calibrated synthetic databases. Two host models are used to constrain model behavior, such that the epistemic uncertainty is captured and characterized. Despite the lack of empirical data at large magnitudes and short distances, constraints based on the host models or on the physical grounds provided by simulations ensure these models are appropriate for engineering applications. The models presented herein are cast in terms of the Fourier amplitude spectra, which is a linear, physical representation of ground motions. The models are suitable for shallow crustal earthquakes; they include an estimate of the median and the aleatory variability, and are applicable in the magnitude range of 3–8 and distance range of 1–300 km.

Testing non-linear amplification factors used in ground motion models

2021 ◽  
Author(s):  
Karina Loviknes ◽  
Danijel Schorlemmer ◽  
Fabrice Cotton ◽  
Sreeram Reddy Kotha
Keyword(s):  
Ground Motion ◽  
Site Effects ◽  
Ground Motions ◽  
Site Amplification ◽  
Building Codes ◽  
Linear Amplification ◽  
Motion Models ◽  
Earthquake Predictability ◽  
Non Linear ◽  
Ground Motion Models

<p>Non-linear site effects are mainly expected for strong ground motions and sites with soft soils and more recent ground-motion models (GMM) have started to include such effects. Observations in this range are, however, sparse, and most non-linear site amplification models are therefore partly or fully based on numerical simulations. We develop a framework for testing of non-linear site amplification models using data from the comprehensive Kiban-Kyoshin network in Japan. The test is reproducible, following the vision of the Collaboratory for the Study of Earthquake Predictability (CSEP), and takes advantage of new large datasets to evaluate <span>whether or not</span> non-linear site effects predicted by site-amplification models are supported by empirical data. The site amplification models are tested using residuals between the observations and predictions from a GMM based only on magnitude and distance. When the GMM is derived without any site term, the site-specific variability extracted from the residuals is expected to capture the site response of a site. The non-linear site amplification models are tested against a linear amplification model on individual well-record<span>ing</span> stations. Finally, the result is compared to building codes where non-linearity is included. The test shows that for most of the sites selected as having sufficient records, the non-linear site-amplification models do not score better than the linear amplification model. This suggests that including non-linear site amplification in GMMs and building codes may not yet be justified, at least not in the range of ground motions considered in the test (peak ground acceleration < 0.2 g).</p>

Relational database used for ground-motion model development in the NGA-sub project

2021 ◽  
pp. 875529302110552
Author(s):  
Silvia Mazzoni ◽  
Tadahiro Kishida ◽  
Jonathan P Stewart ◽  
Victor Contreras ◽  
Robert B Darragh ◽  
...  
Keyword(s):  
Subduction Zone ◽  
Ground Motion ◽  
Data Storage ◽  
Relational Database ◽  
Model Development ◽  
Intensity Measures ◽  
Motion Models ◽  
Ground Motion Model ◽  
Ground Motion Models ◽  
Pseudo Spectral

The Next-Generation Attenuation for subduction zone regions project (NGA-Sub) has developed data resources and ground motion models for global subduction zone regions. Here we describe the NGA-Sub database. To optimize the efficiency of data storage, access, and updating, data resources for the NGA-Sub project are organized into a relational database consisting of 20 tables containing data, metadata, and computed quantities (e.g. intensity measures, distances). A database schema relates fields in tables to each other through a series of primary and foreign keys. Model developers and other users mostly interact with the data through a flatfile generated as a time-stamped output of the database. We describe the structure of the relational database, the ground motions compiled for the project, and the means by which the data can be accessed. The database contains 71,340 three-component records from 1880 earthquakes from seven global subduction zone regions: Alaska, Central America and Mexico, Cascadia, Japan, New Zealand, South America, and Taiwan. These data were processed on a component-specific basis to minimize noise effects in the data and remove baseline drifts. Provided ground motion intensity measures include peak acceleration, peak velocity, and 5%-damped pseudo-spectral accelerations for a range of oscillator periods.

Are Near-Fault Fling Effects Captured in the New NGA West2 Ground Motion Models?

2015 ◽  
Vol 31 (3) ◽  
pp. 1629-1645 ◽  
Author(s):  
Ronnie Kamai ◽  
Norman Abrahamson
Keyword(s):  
Ground Motion ◽  
Vertical Component ◽  
Strong Motion ◽  
Motion Processing ◽  
Large Set ◽  
Pass Filter ◽  
Motion Models ◽  
Finite Fault ◽  
Maximum Period ◽  
Ground Motion Models

We evaluate how much of the fling effect is removed from the NGA database and accompanying GMPEs due to standard strong motion processing. The analysis uses a large set of finite-fault simulations, processed with four different high-pass filter corners, representing the distribution within the PEER ground motion database. The effects of processing on the average horizontal component, the vertical component, and peak ground motion values are evaluated by taking the ratio between unprocessed and processed values. The results show that PGA, PGV, and other spectral values are not significantly affected by processing, partly thanks to the maximum period constraint used when developing the NGA GMPEs, but that the bias in peak ground displacement should not be ignored.

Sign in / Sign up

Export Citation Format

Share Document