Ground motion prediction maps using seismic microzonation data and machine learning

Abstract. Past seismic events worldwide demonstrated that damage and death toll depend on both the strong ground motion (i.e., source effects) and the local site effects. The variability of earthquake ground motion distribution is caused by local stratigraphic and/or topographic setting and buried morphologies, that can give rise to amplification and resonances with respect to the ground motion expected at the reference site. Therefore, local site conditions can affect an area with damage related to the full collapse or loss in functionality of facilities, roads, pipelines, and other lifelines. To this concern, the near real time prediction of damage pattern over large areas is a crucial issue to support the rescue and operational interventions. A machine learning approach was adopted to produce ground motion prediction maps considering both stratigraphic and morphological conditions. A set of about 16'000 accelometric data and about 46'000 geological and geophysical data were retrieved from Italian and European databases. The intensity measures of interest were estimated based on 9 input proxies. The adopted machine learning regression model (i.e., Gaussian Process Regression) allows to improve both the precision and the accuracy in the estimation of the intensity measures with respect to the available near real time predictions methods (i.e., Ground Motion Prediction Equation and shaking maps). In addition, maps with a 50 × 50 m resolution were generated providing a ground motion variability in agreement with the results of advanced numerical simulations based on detailed sub-soil models. The variability at short distances (hundreds of meters) was demonstrated to be responsible for 30–40 % of the total variability of the predicted IM maps, making it desirable that seismic hazard maps also consider short-scale effects.

• Publication year

  2021

• Venue

  Natural Hazards and Earth System Sciences

• Publication date

  2021-10-04

• Fields of study

  Environmental Science, Computer Science, Engineering, Geology

• Identifiers
  DOI 10.5194/nhess-2021-282
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Evaluation of site effects at Amatrice (central Italy) after the August 24th, 2016, Mw 6.0 earthquake

  2021cited by this paper
• Conditioned Simulation of Ground-Motion Time Series at Uninstrumented Sites Using Gaussian Process Regression

  2021cited by this paper
• Spatial correlation of broadband earthquake ground motion in Norcia (Central Italy) from physics-based simulations

  2021cited by this paper
• Seismic amplification maps of Italy based on site-specific microzonation dataset and one-dimensional numerical approach

  2021cited by this paper
• ShakeMap operations, policies, and procedures

  2021influential reference
• Sensitivity of Earthquake Damage Estimation to the Input Data (Soil Characterization Maps and Building Exposure): Case Study in the Luchon Valley, France

  2021cited by this paper
• Spatial correlation of broadband ground motions from physics‐based numerical simulations

  2021cited by this paper
• A simplified vulnerability model for the extensive liquefaction risk assessment of buildings

  2020cited by this paper
• Hybrid predictor for ground-motion intensity with machine learning and conventional ground motion prediction equation

  2020cited by this paper
• Physical stratigraphy and geotechnical properties controlling the local seismic response in explosive volcanic settings: the Stracciacappa maar (central Italy)

  2020cited by this paper
• Evaluation of complex site effects through experimental methods and numerical modelling: The case history of Arquata del Tronto, central Italy

  2020cited by this paper
• Site effects and damage scenarios: The case study of two historic centers following the 2016 Central Italy earthquake

  2020cited by this paper
• The Italian approach to seismic microzonation

  2020cited by this paper
• Topographic and near-surface stratigraphic amplification of the seismic response of a mountain slope revealed by field monitoring and numerical simulations

  2020cited by this paper
• Ground motion amplification models for Japan using machine learning techniques

  2020cited by this paper
• Seismic emergency system evaluation: The role of seismic hazard and local effects

  2020cited by this paper
• Seismic site effects in the Red Zone of Amatrice hill detected via the mutual sustainment of experimental and computational approaches

  2020cited by this paper
• Rapid prediction of earthquake ground shaking intensity using raw waveform data and a Convolutional Neural Network

  2020cited by this paper
• Establishment of a seismic topographic effect prediction model in the Lushan Ms 7.0 earthquake area

  2020cited by this paper
• Modelling the spatial correlation of earthquake ground motion: Insights from the literature, data from the 2016–2017 Central Italy earthquake sequence and ground-motion simulations

  2020cited by this paper
• Data for: A new Vs30 map for Italy based on the seismic microzonation dataset

  2020cited by this paper
• A new Vs30 map for Italy based on the seismic microzonation dataset

  2020cited by this paper
• Effect of bedrock stiffness and thickness on numerical simulation of seismic site response. Italian case studies

  2020cited by this paper
• The New ShakeMap in Italy: Progress and Advances in the Last 10 Yr

  2019cited by this paper
• Geostatistics

  2019cited by this paper
• HSM: a synthetic damage-constrained seismic hazard parameter

  2019cited by this paper
• Quantifying local seismic amplification from regional charts and site specific numerical analyses: a case study

  2019cited by this paper
• Geostatistical analysis of strain localization in triaxial tests on sand

  2019cited by this paper
• Global terrain classification using 280 m DEMs: segmentation, clustering, and reclassification

  2018cited by this paper
• GIS-Based Study of Land Subsidence in the City of Bologna

  2018cited by this paper
• Prenolin: International benchmark on 1D nonlinear: Site-response analysis—validation phase exercise

  2018cited by this paper
• Site response analysis of an urban area: A multi-dimensional and non-linear approach

  2018cited by this paper
• On the vertical accuracy of the ALOS world 3D-30m digital elevation model

  2017cited by this paper
• The Macroseismic Intensity Distribution of the 30 October 2016 Earthquake in Central Italy (Mw 6.6): Seismotectonic Implications

  2017cited by this paper
• International Benchmark on Numerical Simulations for 1D, Nonlinear Site Response (PRENOLIN): Verification Phase Based on Canonical Cases

  2016cited by this paper
• OpenQuake Engine: An Open Hazard (and Risk) Software for the Global Earthquake Model

  2014cited by this paper
• Seismic microzonation of the central archaeological area of Rome: results and uncertainties

  2014cited by this paper
• Pan-European ground-motion prediction equations for the average horizontal component of PGA, PGV, and 5 %-damped PSA at spectral periods up to 3.0 s using the RESORCE dataset

  2013cited by this paper
• Ground motion prediction equations derived from the Italian strong motion database

  2011cited by this paper
• Seismic site effects by an optimized 2D BE/FE method II. Quantification of site effects in two-dimensional sedimentary valleys

  2008cited by this paper
• Geotechnical characterization of the upper Pleistocene-Holocene alluvial deposits of Roma (Italy) by means of multivariate geostatistics: Cross-validation results

  2008cited by this paper
• Relationships between Median Values and between Aleatory Variabilities for Different Definitions of the Horizontal Component of Motion

  2006cited by this paper
• Numerical evaluation of slope topography effects on seismic ground motion

  2005cited by this paper
• Multivariable geostatistics in S: the gstat package

  2004cited by this paper
• Geostatistics: Modeling Spatial Uncertainty

  2001cited by this paper
• GEOTECHNICAL AND GEOPHYSICAL DESCRIPTION OF EURO-SEISTEST, USING FIELD, LABORATORY TESTS AND MODERATE STRONG MOTION RECORDINGS

  1999cited by this paper
• VIBRATIONAL CHARACTERISTICS OF SOIL DEPOSITS WITH VARIABLE WAVE VELOCITY

  1982cited by this paper

• Comprehensive seismic hazard mapping for North Bengkulu, Southwest Sumatera, Indonesia: Planning for urban resilience and Safer cities

  2026cites this paper
• Enhanced Seismic Ground Motion Modeling With Conditional Variational Autoencoder

  2025cites this paper
• Conditional generative adversarial networks for the generation of strong ground motion parameters using KiK-net ground motion records

  2025cites this paper
• Machine learning and its integration with nonlinear ground response analysis in Bhaktapur District, Nepal

  2025cites this paper
• Training and validation of a machine learning model for seismic vulnerability of masonry buildings in aggregate and selection of key parameters

  2025cites this paper
• The Prediction Model of Seismic Variation in Complex Terrain based on the BP Neural Network with Cavities

  2024cites this paper
• Seismic resilience-based strategies for prioritization of interventions on a subregional area

  2024cites this paper
• QuakeFormer: A Uniform Approach to Earthquake Ground Motion Prediction Using Masked Transformers

  2024cites this paper
• Dynamic response prediction for slope during earthquake using modal analysis and deep learning methods

  2024cites this paper
• Seismic microzonation and soil-structure resonance analysis in Suryabinayak Municipality, Bhaktapur, Nepal: insights from ambient vibration measurements

  2024cites this paper
• Neural network prediction model for site response analysis based on the KiK-net database

  2024cites this paper
• A machine learning estimator trained on synthetic data for real-time earthquake ground-shaking predictions in Southern California

  2024cites this paper
• Analysis of earthquake-prone areas based on the seismic wave velocity, young's modulus, shear modulus, and Poisson’s ratio for disaster risk reduction in Bengkulu city, Indonesia

  2024cites this paper
• A scenario-based approach for immediate post-earthquake rockfall impact assessment

  2023cites this paper
• Explainable Machine-Learning Predictions for Peak Ground Acceleration

  2023cites this paper
• Handling Dataset with Geophysical and Geological Variables on the Bolivian Andes by the GMT Scripts

  2022cites this paper
• Empirical shaking scenarios for Europe: a feasibility study

  2022cites this paper
• Seismic Acceleration Estimation Method at Arbitrary Position Using Observations and Machine Learning

  2022cites this paper