An official website of the United States government
RapidLiq is a Windows software program for predicting liquefaction-induced ground failure using geospatial models, which are particularly suited for regional scale applications such as: (i) loss estimation and disaster simulation; (ii) city planning and policy development; (iii) emergency response; and (d) post-event reconnaissance (e.g., to remotely identify sites of interest). RapidLiq v1.0 includes four such models. One is a logistic regression model developed by Rashidian and Baise (2020), which has been adopted into United States Geological Survey (USGS) post-earthquake data products, but which is not often implemented by individuals owing to the geospatial variables that must be compiled. The other three models are machine and deep learning models (ML/DL) proposed by Geyin et al. (2021). These models are driven by algorithmic learning (benefiting from ML/DL insights) but pinned to a physical framework (benefiting from mechanics and the knowledge of regression modelers). While liquefaction is a physical phenomenon best predicted by mechanics, subsurface traits lack theoretical links to above-ground parameters, but correlate in complex, interconnected ways - a prime problem for ML/DL. All four models are described in an acompanying paper manuscript. All necessary predictor variables are compiled within RapidLiq, making user implementation trivial. The only required input is a ground motion raster easily downloaded within minutes of an earthquake, or available for enumerable future earthquake scenarios. This gives the software near-real-time capabilities, such that ground failure can be predicted at regional scale within minutes of an earthquake. The software outputs geotiff files mapping the probabilities of liquefaction-induced ground failure. These files may be viewed within the software or explored in greater detail using GIS or one of many free geotiff web explorers (e.g., http://app.geotiff.io/). The software also allows for tabular input, should a user wish to enter specific sites of interest and ground-motion parameters at those sites, rather than study the regional effects of an earthquake. RapidLiq v.1.0 operates in the contiguous U.S. and completes predictions within 10 seconds for most events.
more »
« less
U.S. National VS30 Models and Maps Informed by Remote Sensing and Machine Learning
Abstract The shear-wave velocity time averaged over the upper 30 m (VS30) is widely used as a proxy for site effects, forms the basis of seismic site class, and underpins site-amplification factors in empirical ground-motion models. Many earthquake simulations, therefore, require VS30. This presents a challenge at regional scale, given the infeasibility of subsurface testing over vast areas. Although various models for predicting VS30 have thus been proposed, the most popular U.S. national, or “background,” model is a regression equation based on just one variable. Given the growth of community data sets, satellite remote sensing, and algorithmic learning, more advanced and accurate solutions may be possible. Toward that end, we develop national VS30 models and maps using field data from over 7000 sites and machine learning (ML), wherein up to 17 geospatial parameters are used to predict subsurface conditions (i.e., VS30). Of the two models developed, that using geologic data performs marginally better, yet such data are not always available. Both models significantly outperform existing solutions in unbiased testing and are used to create new VS30 maps at ∼220 m resolution. These maps are updated in the vicinity of field measurements using regression kriging and cover the 50 U.S. states and Puerto Rico. Ultimately, and like any model, performance cannot be known where data is sparse. In this regard, alternative maps that use other models are proposed for steep slopes. More broadly, this study demonstrates the utility of ML for inferring below-ground conditions from geospatial data, a technique that could be applied to other data and objectives.
more »
« less
- Award ID(s):
- 1751216
- PAR ID:
- 10438255
- Date Published:
- Journal Name:
- Seismological Research Letters
- ISSN:
- 0895-0695
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Semi-empirical models based on in situ geotechnical tests have been the standard-of-practice for predicting soil liquefaction since 1971. More recently, prediction models based on free, readily available data were proposed. These “geospatial” models rely on satellite remote-sensing to infer subsurface traits without in situ tests. Using 15,223 liquefaction case-histories from 24 earthquakes, this study assesses the performance of 23 models based on geotechnical or geospatial data using standardized metrics. Uncertainty due to finite sampling of case-histories is accounted for and used to establish statistical significance. Geotechnical predictions are significantly more efficient on a global scale, yet successive models proposed over the last 20 years show little or no demonstrable improvement. In addition, geospatial models perform equally well for large subsets of the data—a provocative finding given the relative time- and cost-requirements underlying these predictions. Through this performance comparison, lessons for improving each class of model are elucidated in detail.more » « less
-
Abstract One of the main sources of seismic noise below 0.05 Hz is the atmospheric pressure variation, especially when surface pressure variations are large. When surface broadband seismic stations are equipped with pressure sensors, there is high coherence between pressure and seismic signals at low frequencies. The amount of ground deformation under surface pressure variations reflects the characteristics of near‐surface elastic structure and allows us to estimate near‐surface shear‐modulus structure using an inversion method. In the inversion method, we have the surface observable η(f) = Sz/Sp, where f is a frequency between 0.01 and 0.05 Hz, and Sz and Sp are the power spectral densities of vertical seismic data and of surface pressure data. We derive depth sensitivity kernels for η(f) with which we invert for elastic moduli of the shallow structure. Between 0.01 and 0.05 Hz, sensitivity kernels typically have peaks at depths within the uppermost 100 m. Based on vertically heterogeneous 1‐D structures, we estimate Vs30 at 744 USArray Transportable Array stations. Vs30 is the time‐averaged shear‐wave velocity from the surface to the 30‐m depth. We compare our results with various surficial geology maps. Although Vs30 has high horizontal variability over a short distance on the scale of hundreds of meters, we find correlations between Vs30 and large‐scale geological structures, such as mapped units and surficial materials. We find good agreement between estimated Vs30 and mapped Quaternary sediment depths, where stations with thicker underlying sediment tend to have slower Vs30.more » « less
-
SUMMARY The ability to accurately and reliably obtain images of shallow subsurface anomalies within the Earth is important for hazard monitoring and a fundamental understanding of many geologic structures, such as volcanic edifices. In recent years, machine learning (ML) has gained increasing attention as a novel approach for addressing complex problems in the geosciences. Here we present an ML-based inversion method to integrate cosmic-ray muon and gravity data sets for shallow subsurface density imaging at a volcano. Starting with an ensemble of random density anomalies, we use physics-based forward calculations to find the corresponding set of expected gravity and muon attenuation observations. Given a large enough ensemble of synthetic density patterns and observations, the ML algorithm is trained to recognize the expected spatial relations within the synthetic input–output pairs, learning the inherent physical relationships between them. Once trained, the ML algorithm can then interpolate the best-fitting anomalous pattern given data that were not used in training, such as those obtained from field measurements. We test the validity of our ML algorithm using field data from the Showa-Shinzan lava dome (Mt Usu, Japan) and show that our model produces results consistent with those obtained using a more traditional Bayesian joint inversion. Our results are similar to the previously published inversion, and suggest that the Showa-Shinzan lava dome consists of a relatively high-density (2200–2400 km m–3) cylindrical anomaly, about 300 m in diameter. Adding noise to synthetic training and testing data sets shows that, as expected, the ML algorithm is most robust in areas of high sensitivity, as determined by the forward kernels. Overall, we discover that ML offers a viable alternate method to a Bayesian joint inversion when used with gravity and muon data sets for subsurface density imaging.more » « less
-
Eric Calais; Silvia Chacón-Barrantes; Roby Douilly; O’Leary Gonzalez; Xyoli Pérez-Campos; Richard Robertson, Elizabeth Vanacore (Ed.)The Mw 7.2 Nippes, Haiti, earthquake occurred on 14 August 2021 in Haiti’s southwest peninsula and in the midst of significant social, economic, and political crises. A hybrid reconnaissance mission (i.e., combined remote and field investigation) was coordinated to document damage to the built environment after the event. This article evaluates two ground‐motion records available in Haiti in the context of the geology of the region and known areas with significant damage, such as Les Cayes. We also present a new map of time‐averaged shear‐wave velocity values to 30 m depth (VS30 ) for Les Cayes and Port‐au‐Prince based on the geostatistical approach of kriging and accounting for region‐specific geology proxies and field measurements of VS30 . Case studies of ground failure observations, including landslides and liquefaction triggering, are described as well as the intersection of social and engineering observations. Maps depicting this important intersection are provided to facilitate the assessment of how natural hazards and social conflicts have influenced the vulnerability of Haiti’s population to earthquakes.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1785/0220220181
