Rapid prediction of earthquake ground shaking intensity using raw waveform data and a Convolutional Neural Network

This study describes a deep convolutional neural network (CNN) based technique to predict intensity measurements (IMs) of earthquake ground shaking. The input data to the CNN model consists of multistation, 3C acceleration waveforms recorded during the 2016 Central Italy earthquake sequence for M ≥ 3.0 events. Using a 10 s window starting at the earthquake origin time, we find that the CNN is capable of accurately predicting IMs at stations far from the epicentre which have not yet recorded the maximum ground shaking. The CNN IM predictions do not require previous knowledge of the earthquake source (location and magnitude). Comparison between the CNN model predictions and those obtained with the Bindi et al. GMPE (which requires location and magnitude) shows that the CNN model features similar error variance but smaller bias. Although the technique is not strictly designed for earthquake early warning, we find that it can provide useful estimates of ground motions within 15–20 s after earthquake origin time depending on various setup elements (e.g. times for data transmission, computation, latencies). The technique has been tested on raw data without any initial data pre-selection in order to closely replicate real-time data streaming. When noise examples were included with the earthquake data the CNN was found to be stable, accurately predicting the ground shaking intensity corresponding to the noise amplitude.

• Publication year

  2020

• Venue

  1st Croatian Conference on Earthquake Engineering

• Publication date

  2020-02-17

• Fields of study

  Physics, Computer Science, Engineering, Geology, Environmental Science

• Identifiers
  DOI 10.1093/gji/ggaa233arXiv 2002.06893
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• The New ShakeMap in Italy: Progress and Advances in the Last 10 Yr

  2019cited by this paper
• Physiological, epigenetic and genetic regulation in some olive cultivars under salt stress

  2019cited by this paper
• Artificial Neural Networks as Emerging Tools for Earthquake Detection

  2019cited by this paper
• An Investigation of Rapid Earthquake Characterization Using Single‐Station Waveforms and a Convolutional Neural Network

  2019cited by this paper
• Machine learning for data-driven discovery in solid Earth geoscience

  2019cited by this paper
• A Machine‐Learning Approach for Earthquake Magnitude Estimation

  2019cited by this paper
• On-site earthquake early warning: a partially non-ergodic perspective from the site effects point of view

  2018cited by this paper
• PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method

  2018cited by this paper
• The limits of earthquake early warning: Timeliness of ground motion estimates

  2018cited by this paper
• CRED: A Deep Residual Network of Convolutional and Recurrent Units for Earthquake Signal Detection

  2018cited by this paper
• A Deep Convolutional Neural Network for Localization of Clustered Earthquakes Based on Multistation Full Waveforms

  2018cited by this paper
• Spatial and Spectral Interpolation of Ground-Motion Intensity Measure Observations

  2018cited by this paper
• Similarity of fast and slow earthquakes illuminated by machine learning

  2018cited by this paper
• Earthquake early Warning ShakeAlert system: West coast wide production prototype

  2018cited by this paper
• Revised technical implementation plan for the ShakeAlert system—An earthquake early warning system for the West Coast of the United States

  2018cited by this paper
• Machine Learning in Seismology: Turning Data into Insights

  2018cited by this paper
• The 2016 central Italy seismic sequence: a first look at the mainshocks, aftershocks, and source models

  2017cited by this paper
• Convolutional neural network for earthquake detection and location

  2017cited by this paper
• Deep Learning with Python

  2017cited by this paper
• Fast magnitude determination using a single seismological station record implementing machine learning techniques

  2017cited by this paper
• Supervised machine learning on a network scale: application to seismic event classification and detection

  2017cited by this paper
• The ShakeMaps of the Amatrice, M6, earthquake

  2016cited by this paper
• Deep Learning

  2015cited by this paper
• Towards fully data driven ground-motion prediction models for Europe

  2014cited by this paper
• Efficient BackProp

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Proposal for a soil classification based on parameters alternative or complementary to Vs,30

  2011cited by this paper
• Earthquake early warning: Concepts, methods and physical grounds

  2011cited by this paper
• Ground motion prediction equations derived from the Italian strong motion database

  2011cited by this paper
• Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing

  2011cited by this paper
• Pattern classification with missing data: a review

  2010cited by this paper
• The Variability of Ground-Motion Prediction Models and Its Components

  2010cited by this paper
• A Survey on Transfer Learning

  2010cited by this paper
• ObsPy: A Python Toolbox for Seismology

  2010cited by this paper
• Uncertainty in early warning predictions of engineering ground motion parameters: What really matters?

  2009cited by this paper
• The Status of Earthquake Early Warning around the World: An Introductory Overview

  2009cited by this paper
• TriNet “ShakeMaps”: Rapid Generation of Peak Ground Motion and Intensity Maps for Earthquakes in Southern California

  1999cited by this paper
• Regional seismic event classification at the NORESS array: Seismological measurements and the use of trained neural networks

  1990cited by this paper
• Artificial intelligence techniques in seismic signal interpretation

  1989cited by this paper

• Developing intensity prediction equations from ground-motion parameters in the northwestern Himalaya

  2026cites this paper
• Testing Audio Compression Autoencoders for Seismology: Moving Toward Foundation Models

  2026cites this paper
• Designing a model for earthquake timing and magnitude prediction based on neural networks and particle swarm optimization (PSO) algorithm

  2026influential citation
• A multi-scale deep learning framework for real-time post-earthquake damage estimation leveraging wavelet-driven GoogLeNet-FC

  2026cites this paper
• CNeXt-DANet: ConvNeXt with dual attention for violence detection in surveillance videos

  2026cites this paper
• Graph Neural Network-Based Latency Prediction for Stream Processing Task

  2025cites this paper
• Anomaly Detection in Seismic Data with Deep Learning: Application for Instrument Failure Detection and Forecasting

  2025cites this paper
• Onsite intensity prediction for earthquake early warning with multimodal deep learning

  2025cites this paper
• Real-Time Prediction of S-Wave Accelerograms from P-Wave Signals Using LSTM Networks with Integrated Fragility-Based Structural Damage Alerts for Induced Seismicity

  2025cites this paper
• Persistent Homology-induced Graph Ensembles for Time Series Regressions

  2025cites this paper
• Predicting peak ground acceleration using the ConvMixer network

  2025cites this paper
• Alternative ground motion model for CENA region using a deep neural network integrated with transfer learning technique

  2025cites this paper
• An Attention-Based Framework With Multistation Information for Earthquake Early Warnings

  2025cites this paper
• Masked graph neural network for rapid ground motion prediction in Italy

  2025influential citation
• RATE: A Retrieval-Augmented Transformer for Regional Earthquake Early Warning

  2025cites this paper
• Uncertainty-Aware Earthquake Forecasting Using a Bayesian Neural Network with Elastic Weight Consolidation

  2025cites this paper
• A dual-enhanced long short-term memory earthquake prediction method based on improved and hybrid rice-inspired gray wolf optimizers

  2025cites this paper
• A Multi-Task Regression Model for Seismic Key Parameters Prediction Based on Transformer and ResNet Parallel Architecture Considering Fusion Mechanisms

  2025cites this paper
• Peak ground acceleration prediction for on-site earthquake early warning with deep learning

  2024influential citation
• Exploring challenges in deep learning of single-station ground motion records

  2024cites this paper
• Prediction of ground motion intensity measures using support vector machine in analysing spatial correlation

  2024cites this paper
• A single-sensor method for structural damage localization in wind turbine blades: Laboratory assessment on a blade segment

  2024cites this paper
• Interpretability and spatial efficacy of deep-learning-based on-site early warning framework using explainable artificial intelligence and geographically weighted random forests

  2024cites this paper
• Advancements in Disaster Prediction: A Systematic Review of Earthquake, Flood, and Cyclone Forecasting Techniques

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

  2024cites this paper
• Multi-scale convolution networks for seismic event classification with windowed self-attention

  2024cites this paper
• Using Deep Learning for Rapid Earthquake Parameter Estimation in Single-Station Single-Component Earthquake Early Warning System

  2024cites this paper
• An All‐In‐One Rapid Prediction of Ground Motion Intensity Measures Hybrid Network for Multi‐Task in the North‐South Seismic Belt of China

  2024cites this paper
• Data‐Knowledge Driven Hybrid Deep Learning for Earthquake Early Warning

  2024cites this paper
• VGG Model for Peak Ground Acceleration Prediction

  2024cites this paper
• Short-term comprehensive prediction method for regional earthquakes based on multi-source information fusion

  2024cites this paper
• Earthquake Risk Assessment in Seismically Active Areas of Qinghai Province Based on Geographic Big Data

  2024cites this paper
• Deep learning-based epicenter localization using single-station strong motion records

  2024cites this paper
• Deep Learning Peak Ground Acceleration Prediction Using Single-Station Waveforms

  2024cites this paper
• Predicting Peak Ground Acceleration of Strong-Motion Earthquakes Using Variable Snapshots of P-Wave Data with Long Short-Term Memory Neural Network

  2024cites this paper
• GRAPES: Earthquake Early Warning by Passing Seismic Vectors Through the Grapevine

  2024cites this paper
• TXED: The Texas Earthquake Dataset for AI

  2024cites this paper
• Earthquake Early Magnitude Prediction Using 3D Point Cloud Based Deep Learning Model: Case of 2018 Osaka Earthquake

  2024cites this paper
• Multiple-Input Fourier Neural Operator (MIFNO) for source-dependent 3D elastodynamics

  2024cites this paper
• Realtime Selection of Optimal Source Parameters Using Ground Motion Envelopes

  2024cites this paper
• Uncertainty propagation from crustal geologies to rock-site ground motion with a Fourier Neural Operator

  2024cites this paper
• Estimation of ground motion parameters via multi-task deep neural networks

  2024cites this paper
• Recent advances in earthquake seismology using machine learning

  2024influential citation
• An Early Forecast of Long‐Period Ground Motions of Large Earthquakes Based on Deep Learning

  2023cites this paper
• Application of grey wolf optimizer to develop new global GMPE for estimating peak ground acceleration

  2023cites this paper
• Efficient regional seismic risk assessment via deep generative learning of surrogate models

  2023cites this paper
• Hazard-informed optimization of seismic networks for earthquake early warning—the case of the Lower Rhine Embayment (western Germany)

  2023cites this paper
• On-site instrumental seismic intensity prediction for China via recurrent neural network and transfer learning

  2023cites this paper
• Most complicated lock pattern-based seismological signal framework for automated earthquake detection

  2023cites this paper
• Seismic severity estimation using convolutional neural network for earthquake early warning

  2023cites this paper
• BTRPP: A Rapid PGA Prediction Model Based on Machine Learning

  2023cites this paper
• Earthquake activity as captured using the network approach

  2023cites this paper
• Identifying Informative Nodes in Attributed Spatial Sensor Networks Using Attention for Symbolic Abstraction in a GNN-based Modeling Approach

  2023cites this paper
• Real-Time Seismic Intensity Measurements Prediction for Earthquake Early Warning: A Systematic Literature Review

  2023cites this paper
• A Normalized ANN Model for Earthquake Estimation

  2023cites this paper
• Real-Time Seismic Intensity Prediction Using Self-Supervised Contrastive GNN for Earthquake Early Warning

  2023influential citation
• Cumulative absolute velocity prediction for earthquake early warning with deep learning

  2023influential citation
• Earthquake Detection Using Stacked Normalized Recurrent Neural Network (SNRNN)

  2023cites this paper
• Spatial-temporal graph convolutional networks (STGCN) based method for localizing acoustic emission sources in composite panels

  2023cites this paper
• Graph construction on complex spatiotemporal data for enhancing graph neural network-based approaches

  2023cites this paper
• An automated earthquake classification model based on a new butterfly pattern using seismic signals

  2023cites this paper
• Prediction Model for Peak Ground Acceleration Using Deep Learning

  2023cites this paper
• A Novel Approach for Earthquake Prediction Using Random Forest and Neural Networks

  2023cites this paper
• Convolutional Neural Network for Earthquake Ground Motion Prediction Model in Earthquake Early Warning System in West Java

  2023cites this paper
• Real‐Time Fault Tracking and Ground Motion Prediction for Large Earthquakes With HR‐GNSS and Deep Learning

  2023cites this paper
• Performance Analysis of Machine Learning and Deep Learning Architecture for Earthquake Magnitude Prediction

  2023cites this paper
• Neural Network-Based Strong Motion Prediction for On-Site Earthquake Early Warning

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

  2022cites this paper
• Deep Multi-scale Dilated Convolution Neural Network with Attention Mechanism: A Novel Method for Earthquake Magnitude Classification

  2022cites this paper
• Multivariate Time Series Regression on Seismic Data Using Adaptive Residual CNNs

  2022influential citation
• Hybrid Deep-Learning Network for Rapid On-Site Peak Ground Velocity Prediction

  2022cites this paper
• Real-time prediction of earthquake potential damage: A case study for the 8 January 2022 MS 6.9 Menyuan earthquake in Qinghai, China

  2022cites this paper
• Strong-motion Earthquake Prediction Model using Convolutional Extreme Learning Machine

  2022cites this paper
• An Early Warning System for Earthquake Prediction from Seismic Data Using Batch Normalized Graph Convolutional Neural Network with Attention Mechanism (BNGCNNATT)

  2022influential citation
• Graph neural networks for multivariate time series regression with application to seismic data

  2022influential citation
• Time Series and Non-Time Series Models of Earthquake Prediction Based on AETA Data: 16-Week Real Case Study

  2022cites this paper
• Research on Identification of Natural and Unnatural Earthquake Events Based on AlexNet Convolutional Neural Network

  2022cites this paper
• Learning source, path, and site effects: CNN-based Onsite Intensity Prediction for Earthquake Early Warning

  2022cites this paper
• Forecasting Surface Velocity Fields Associated With Laboratory Seismic Cycles Using Deep Learning

  2022cites this paper
• Early Earthquake Detection Using Batch Normalization Graph Convolutional Neural Network (BNGCNN)

  2022cites this paper
• A deep learning approach for the development of an Early Earthquake Warning system

  2022cites this paper
• Machine intelligence in dynamical systems: \A state‐of‐art review

  2022cites this paper
• CREIME—A Convolutional Recurrent Model for Earthquake Identification and Magnitude Estimation

  2022cites this paper
• The Choice of Time–Frequency Representations of Non-Stationary Signals Affects Machine Learning Model Accuracy: A Case Study on Earthquake Detection from LEN-DB Data

  2022cites this paper
• Earthquake Early Warning System Using Ncheck and Hard-Shared Orthogonal Multitarget Regression on Deep Learning

  2022cites this paper
• Diagnosis of Intracranial Tumors via the Selective CNN Data Modeling Technique

  2022cites this paper
• Multivariate Time Series Regression with Graph Neural Networks

  2022influential citation
• A deep neural network framework for real‐time on‐site estimation of acceleration response spectra of seismic ground motions

  2022cites this paper
• Earthquake magnitude and location estimation from real time seismic waveforms with a transformer network

  2021cites this paper
• Onsite Early Prediction of PGA Using CNN With Multi-Scale and Multi-Domain P-Waves as Input

  2021influential citation
• Magnitude Estimation for Earthquake Early Warning Using a Deep Convolutional Neural Network

  2021influential citation
• Transfer learning: Improving neural network based prediction of earthquake ground shaking for an area with insufficient training data

  2021cites this paper
• A CNN-BiLSTM model with attention mechanism for earthquake prediction

  2021cites this paper
• Early Peak Ground Acceleration Prediction for On-Site Earthquake Early Warning Using LSTM Neural Network

  2021cites this paper
• Ground motion prediction maps using seismic microzonation data and machine learning

  2021cites this paper
• Research on the Garbage Classification Problem Based on Convolutional Neural Network

  2021cites this paper
• Erratum: Rapid prediction of earthquake ground shaking intensity using raw waveform data and a convolutional neural network

  2021cites this paper
• Identification of Low‐Frequency Earthquakes on the San Andreas Fault With Deep Learning

  2021cites this paper
• INSTANCE – the Italian seismic dataset for machine learning

  2021influential citation
• A Deep Learning-Based Electromagnetic Signal for Earthquake Magnitude Prediction

  2021cites this paper