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
RapidLiq: Software for Near-Real-Time Prediction of Soil Liquefaction
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
- Award ID(s):
- 1751216
- NSF-PAR ID:
- 10344904
- Publisher / Repository:
- Designsafe-CI
- Date Published:
- Subject(s) / Keyword(s):
- ["soil liquefaction","geospatial modelling","near-real-time prediction"]
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The objective of this study is to develop data-driven predictive models for peak rotation and factor of safety for tipping-over failure of rocking shallow foundations during earthquake loading using multiple nonlinear machine learning (ML) algorithms and a supervised learning technique. Centrifuge and shaking table experimental results on rocking foundations have been used for the development of k-nearest neighbors regression (KNN), support vector regression (SVR), and random forest regression (RFR) models. The input features to ML models include critical contact area ratio of foundation; slenderness ratio and rocking coefficient of rocking system; peak ground acceleration and Arias intensity of earthquake motion; and a categorical binary feature that separates sandy soil foundations from clayey soil foundations. Based on repeated k-fold cross validation tests of models, we found that the overall average mean absolute percentage errors (MAPE) in predictions of all three nonlinear ML models varied between 0.46 and 0.60, outperforming a baseline multivariate linear regression ML model with corresponding MAPE of 0.68 to 0.75. The input feature importance analysis reveals that the peak rotation and tipping-over stability of rocking foundations are more sensitive to ground motion demand parameters than to rocking foundation capacity parameters or type of soil.more » « less
-
more » « less
Data Description:
To improve SOC estimation in the United States, we upscaled site-based SOC measurements to the continental scale using multivariate geographic clustering (MGC) approach coupled with machine learning models. First, we used the MGC approach to segment the United States at 30 arc second resolution based on principal component information from environmental covariates (gNATSGO soil properties, WorldClim bioclimatic variables, MODIS biological variables, and physiographic variables) to 20 SOC regions. We then trained separate random forest model ensembles for each of the SOC regions identified using environmental covariates and soil profile measurements from the International Soil Carbon Network (ISCN) and an Alaska soil profile data. We estimated United States SOC for 0-30 cm and 0-100 cm depths were 52.6 + 3.2 and 108.3 + 8.2 Pg C, respectively.
Files in collection (32):
Collection contains 22 soil properties geospatial rasters, 4 soil SOC geospatial rasters, 2 ISCN site SOC observations csv files, and 4 R scripts
gNATSGO TIF files:
├── available_water_storage_30arc_30cm_us.tif [30 cm depth soil available water storage]
├── available_water_storage_30arc_100cm_us.tif [100 cm depth soil available water storage]
├── caco3_30arc_30cm_us.tif [30 cm depth soil CaCO3 content]
├── caco3_30arc_100cm_us.tif [100 cm depth soil CaCO3 content]
├── cec_30arc_30cm_us.tif [30 cm depth soil cation exchange capacity]
├── cec_30arc_100cm_us.tif [100 cm depth soil cation exchange capacity]
├── clay_30arc_30cm_us.tif [30 cm depth soil clay content]
├── clay_30arc_100cm_us.tif [100 cm depth soil clay content]
├── depthWT_30arc_us.tif [depth to water table]
├── kfactor_30arc_30cm_us.tif [30 cm depth soil erosion factor]
├── kfactor_30arc_100cm_us.tif [100 cm depth soil erosion factor]
├── ph_30arc_100cm_us.tif [100 cm depth soil pH]
├── ph_30arc_100cm_us.tif [30 cm depth soil pH]
├── pondingFre_30arc_us.tif [ponding frequency]
├── sand_30arc_30cm_us.tif [30 cm depth soil sand content]
├── sand_30arc_100cm_us.tif [100 cm depth soil sand content]
├── silt_30arc_30cm_us.tif [30 cm depth soil silt content]
├── silt_30arc_100cm_us.tif [100 cm depth soil silt content]
├── water_content_30arc_30cm_us.tif [30 cm depth soil water content]
└── water_content_30arc_100cm_us.tif [100 cm depth soil water content]SOC TIF files:
├──30cm SOC mean.tif [30 cm depth soil SOC]
├──100cm SOC mean.tif [100 cm depth soil SOC]
├──30cm SOC CV.tif [30 cm depth soil SOC coefficient of variation]
└──100cm SOC CV.tif [100 cm depth soil SOC coefficient of variation]site observations csv files:
ISCN_rmNRCS_addNCSS_30cm.csv 30cm ISCN sites SOC replaced NRCS sites with NCSS centroid removed data
ISCN_rmNRCS_addNCSS_100cm.csv 100cm ISCN sites SOC replaced NRCS sites with NCSS centroid removed data
Data format:Geospatial files are provided in Geotiff format in Lat/Lon WGS84 EPSG: 4326 projection at 30 arc second resolution.
Geospatial projection:
GEOGCS["GCS_WGS_1984", DATUM["D_WGS_1984", SPHEROID["WGS_1984",6378137,298.257223563]], PRIMEM["Greenwich",0], UNIT["Degree",0.017453292519943295]] (base) [jbk@theseus ltar_regionalization]$ g.proj -w GEOGCS["wgs84", DATUM["WGS_1984", SPHEROID["WGS_1984",6378137,298.257223563]], PRIMEM["Greenwich",0], UNIT["degree",0.0174532925199433]] -
null (Ed.)The 2019 Ridgecrest earthquake sequence produced a 4 July M 6.5 foreshock and a 5 July M 7.1 mainshock, along with 23 events with magnitudes greater than 4.5 in the 24 hr period following the mainshock. The epicenters of the two principal events were located in the Indian Wells Valley, northwest of Searles Valley near the towns of Ridgecrest, Trona, and Argus. We describe observed liquefaction manifestations including sand boils, fissures, and lateral spreading features, as well as proximate non‐ground failure zones that resulted from the sequence. Expanding upon results initially presented in a report of the Geotechnical Extreme Events Reconnaissance Association, we synthesize results of field mapping, aerial imagery, and inferences of ground deformations from Synthetic Aperture Radar‐based damage proxy maps (DPMs). We document incidents of liquefaction, settlement, and lateral spreading in the Naval Air Weapons Station China Lake US military base and compare locations of these observations to pre‐ and postevent mapping of liquefaction hazards. We describe liquefaction and ground‐failure features in Trona and Argus, which produced lateral deformations and impacts on several single‐story masonry and wood frame buildings. Detailed maps showing zones with and without ground failure are provided for these towns, along with mapped ground deformations along transects. Finally, we describe incidents of massive liquefaction with related ground failures and proximate areas of similar geologic origin without ground failure in the Searles Lakebed. Observations in this region are consistent with surface change predicted by the DPM. In the same region, geospatial liquefaction hazard maps are effective at identifying broad percentages of land with liquefaction‐related damage. We anticipate that data presented in this article will be useful for future liquefaction susceptibility, triggering, and consequence studies being undertaken as part of the Next Generation Liquefaction project.more » « less
-
In the U.S. Pacific Northwest (PNW), the historic earthquake record is often insufficient to provide inputs to seismic-hazard analyses or to inform ground-motion predictions for certain seismic sources (e.g., the Cascadia Subduction Zone, CSZ). As a result, paleoseismic studies are commonly used to infer information about the seismic hazard. However, among the many forms of coseismic evidence, soil liquefaction provides the best, if not only, evidence from which the intensities of previous ground motions may be constrained. Accordingly, the overarching goal of this research is to use paleoliquefaction to elucidate previous ground motions in the PNW – both for CSZ events and others – and to further constrain the locations, magnitudes, and recurrence rates of such ruptures. Towards that goal, this paper: (i) reviews current paleoliquefaction inverse-analysis methods and their limited, prior applications in the PNW; (ii) compiles all PNW paleoliquefaction evidence from the literature into a GIS database, resulting in data from 185 study sites (e.g., feature locations, types, sizes, and ages); and (iii) develops maps – specific to the CSZ – that forecast paleoliquefaction for 30 different simulations of a CSZ event. These maps can be used to guide field explorations for new evidence, such that they are conducted efficiently and strategically, considering the apparent utility of evidence toward constraint of CSZ ground-motion models. Of additional utility, this process provides regional ground-motion predictions for physics-based simulations of an M9 event, to include expected site effects. Collectively, the maps of expected shaking intensity and liquefaction may be useful in downstream hazard modelling, regional loss estimation, policy development, and science communication. Ultimately, as more paleoliquefaction evidence is identified and studied, better constraint of regional ground-motion hazards will result. Version 2 (this posting) supersedes Version 1 (10.17603/ds2-jm19-2w09). Updates include GIS rasters that provide regional ground-motion intensity predictions (PGA, PGV) for 30 physics-based simulations of an M9 event, to include expected site effectsmore » « less
