Real-time determination of earthquake focal mechanism via deep learning

An immediate report of the source focal mechanism with full automation after a destructive earthquake is crucial for timely characterizing the faulting geometry, evaluating the stress perturbation, and assessing the aftershock patterns. Advanced technologies such as Artificial Intelligence (AI) has been introduced to solve various problems in real-time seismology, but the real-time source focal mechanism is still a challenge. Here we propose a novel deep learning method namely Focal Mechanism Network (FMNet) to address this problem. The FMNet trained with 787,320 synthetic samples successfully estimates the focal mechanisms of four 2019 Ridgecrest earthquakes with magnitude larger than Mw 5.4. The network learns the global waveform characteristics from theoretical data, thereby allowing the extensive applications of the proposed method to regions of potential seismic hazards with or without historical earthquake data. After receiving data, the network takes less than two hundred milliseconds for predicting the source focal mechanism reliably on a single CPU. The authors here present a deep learning method to determine the source focal mechanism of earthquakes in realtime. They trained their network with approximately 800k synthetic samples and managed to successfully estimate the focal mechanism of four 2019 Ridgecrest earthquakes with magnitudes larger than Mw 5.4.

• Publication year

  2020

• Venue

  Nature Communications

• Publication date

  2020-09-25

• Fields of study

  Medicine, Computer Science, Geology

• Identifiers
  DOI 10.1038/s41467-021-21670-xPMID 33664244PMCID 7933283
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Re-epithelialization and immune cell behaviour in an ex vivo human skin model

  2020cited by this paper
• Focal mechanisms of small earthquakes beneath the Japanese islands based on first-motion polarities picked using deep learning

  2020cited by this paper
• Earthquake transformer—an attentive deep-learning model for simultaneous earthquake detection and phase picking

  2020cited by this paper
• Were changes in stress state responsible for the 2019 Ridgecrest, California, earthquakes?

  2020cited by this paper
• Seismotectonics and Fault Geometries of the 2019 Ridgecrest Sequence: Insight From Aftershock Moment Tensor Catalog Using 3‐D Green's Functions

  2020cited by this paper
• U1 snRNP regulates cancer cell migration and invasion in vitro

  2020cited by this paper
• Comparison of Single-Trace and Multiple-Trace Polarity Determination for Surface Microseismic Data Using Deep Learning

  2020cited by this paper
• Cascading and pulse-like ruptures during the 2019 Ridgecrest earthquakes in the Eastern California Shear Zone

  2020cited by this paper
• High-Frequency Radiation and Earthquake Rupture Complexities: From Back Projection to a Machine Learning Approach

  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
• P-wave first-motion polarity determination of waveform data in western Japan using deep learning

  2019cited by this paper
• From Earthquake Source Parameters to Ground‐Motion Warnings near You: The ShakeAlert Earthquake Information to Ground‐Motion (eqInfo2GM) Method

  2019cited by this paper
• Hierarchical interlocked orthogonal faulting in the 2019 Ridgecrest earthquake sequence

  2019cited by this paper
• Annual Review of Earth and Planetary Sciences Earthquake Early Warning : Advances , Scientific Challenges , and Societal Needs

  2019cited by this paper
• Reliable Real‐Time Seismic Signal/Noise Discrimination With Machine Learning

  2019cited by this paper
• Locating induced earthquakes with a network of seismic stations in Oklahoma via a deep learning method

  2018cited by this paper
• P Wave Arrival Picking and First‐Motion Polarity Determination With Deep Learning

  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
• Machine Learning in Seismology: Turning Data into Insights

  2018cited by this paper
• Machine learning reveals cyclic changes in seismic source spectra in Geysers geothermal field

  2018cited by this paper
• Deep learning of aftershock patterns following large earthquakes

  2018cited by this paper
• KaKiOS-16: a probabilistic, non-linear, absolute location catalog of the 1981-2011 South Californian seismicity

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

  2017cited by this paper
• Estimating geomechanical parameters from microseismic plane focal mechanisms recorded during multistage hydraulic fracturing

  2017cited by this paper
• Machine Learning Predicts Laboratory Earthquakes

  2017cited by this paper
• Mastering the game of Go with deep neural networks and tree search

  2016cited by this paper
• Deep Learning

  2016cited by this paper
• FaceNet: A unified embedding for face recognition and clustering

  2015cited by this paper
• Isotropic source terms of San Jacinto fault zone earthquakes based on waveform inversions with a generalized CAP method

  2015cited by this paper
• Deep Learning

  2015cited by this paper
• Rethinking the Inception Architecture for Computer Vision

  2015cited by this paper
• Real-time earthquake monitoring using a search engine method

  2014cited by this paper
• Fully convolutional networks for semantic segmentation

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Observations of static Coulomb stress triggering of the November 2011 M5.7 Oklahoma earthquake sequence

  2014cited by this paper
• SRCMOD: An Online Database of Finite‐Fault Rupture Models

  2014cited by this paper
• Parametrization of general seismic potency and moment tensors for source inversion of seismic waveform data

  2013cited by this paper
• Aftershocks halted by static stress shadows

  2012cited by this paper
• ADADELTA: An Adaptive Learning Rate Method

  2012cited by this paper
• Focal Mechanism Determination Using High Frequency Waveform Matching and Its Application to Small Magnitude Induced Earthquakes

  2011cited by this paper
• Focal Mechanisms from Sparse Observations by Nonlinear Inversion of Amplitudes: Method and Tests on Synthetic and Real Data

  2009cited by this paper
• Three-Dimensional Splay Fault Geometry and Implications for Tsunami Generation

  2007cited by this paper
• A New Method for Determining Small Earthquake Source Parameters Using Short-Period P Waves

  2007cited by this paper
• Simplified algorithms for calculating double-couple rotation

  2007cited by this paper
• 3-D rotation of double-couple earthquake sources

  2006influential reference
• Fault Parameter Constraints Using Relocated Earthquakes: A Validation of First-Motion Focal-Mechanism Data

  2006cited by this paper
• A Fast Learning Algorithm for Deep Belief Nets

  2006cited by this paper
• Rupture Process of the 2004 Sumatra-Andaman Earthquake

  2005cited by this paper
• Finite Fault Modeling of Strong Ground Motions Using a Hybrid Deterministic–Stochastic Approach

  2005cited by this paper
• Stochastic Finite-Fault Modeling Based on a Dynamic Corner Frequency

  2005cited by this paper
• REAL-TIME SEISMOLOGY AND EARTHQUAKE DAMAGE MITIGATION

  2005cited by this paper
• Real-Time Seismology and Earthquake Damage Mitigation

  2005cited by this paper
• Observation of Long Supershear Rupture During the Magnitude 8.1 Kunlunshan Earthquake

  2003cited by this paper
• The Potential for Earthquake Early Warning in Southern California

  2003cited by this paper
• Using S/P Amplitude Ratios to Constrain the Focal Mechanisms of Small Earthquakes

  2003cited by this paper
• 85.12 FOCMEC: FOCal MEChanism determinations

  2003cited by this paper
• Aftershock triggering by complete Coulomb stress changes

  2002cited by this paper
• A New Method for Determining First-Motion Focal Mechanisms

  2002cited by this paper
• A note on the dynamic and static displacements from a point source in multilayered media

  2002cited by this paper
• Earthquake triggering by seismic waves following the Landers and Hector Mine earthquakes

  2001cited by this paper
• Triggering of earthquake aftershocks by dynamic stresses

  2000cited by this paper
• Real-time seismology and earthquake hazard mitigation

  1997cited by this paper
• Regional waveform calibration in the Pamir-Hindu Kush region

  1997cited by this paper
• Advancement in source estimation techniques using broadband regional seismograms

  1996cited by this paper
• Source Estimation from Broadband Regional Seismograms

  1994cited by this paper
• STATIC STRESS CHANGES AND THE TRIGGERING OF EARTHQUAKES

  1994cited by this paper
• Source retrieval from broadband regional seismograms: Hindu Kush region

  1993cited by this paper
• Source parameters of the June 29, 1992 Little Skull Mountain Earthquake from complete regional waveforms at a single station

  1993cited by this paper
• Determination of source parameters at regional distances with three‐component sparse network data

  1993cited by this paper
• The determination of source parameters for small earthquakes from a single, very broadband seismic station

  1991cited by this paper
• 3-D rotation of double-couple earthquake sources

  1991cited by this paper
• Use of focal mechanisms to determine stress: A control study

  1987cited by this paper

• Deep learning for the localization of seismic sources based on synthetic full waveform and wavelet de-noising

  2026cites this paper
• SeismicXM: A Cross-Task Foundation Model for Single-Station Seismic Waveform Processing

  2026cites this paper
• SourceNet: Interpretable Sim-to-Real Inference on Variable-Geometry Sensor Arrays for Earthquake Source Inversion

  2026cites this paper
• Temporal and spatial evolution patterns of earthquake clusters in the southern Sichuan industrial mining zone—Advanced analysis based on multisource data fusion and machine learning

  2026cites this paper
• DeconNet: An Automated Framework for Resolving Finite-Source Attributes of Small Earthquakes with Array-Based Neural Network Deconvolution

  2026cites this paper
• Study of Methods for Automatic Segmentation of Geological Profile Images Based on Diffusion Models

  2025cites this paper
• Early warning for fault-slip risk based on genetic algorithm-back propagation neural network: An intelligent mathematical evaluation model study

  2025cites this paper
• A Mutil-conditional Diffusion Transformer for Versatile Seismic Wave Generation

  2025cites this paper
• CrazyBeachball: A MATLAB GUI-based software package for focal mechanism inversion

  2025cites this paper
• Research on Microseismic Magnitude Prediction Method Based on Improved Residual Network and Transfer Learning

  2025cites this paper
• A Novel Time–Frequency Similarity Method for P-Wave First-Motion Polarity Detection

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

  2025cites this paper
• Deprem Şiddet Tahmini İçin Derin Öğrenme Yöntemlerinin Karşılaştırılması ve Model Önerisi

  2025cites this paper
• DASFormer: self-supervised pretraining for earthquake monitoring

  2025cites this paper
• Machine learning techniques for predictive modelling in geotechnical engineering: a succinct review

  2025cites this paper
• Real-Time Reconstruction of Ground Motion During Small Magnitude Earthquakes: A Pilot Study

  2025cites this paper
• An Interpretable and Domain-Informed Real-Time Hybrid Earthquake Early Warning for Ground Shaking Intensity Prediction

  2025cites this paper
• Machine Learning-based Analysis of the 2015 M5.8 Alxa Left Banner Earthquake Sequence

  2025cites this paper
• Deriving focal mechanism solutions of small to moderate earthquakes in Sichuan, China via a deep learning method

  2025cites this paper
• SourceNet: A Deep-Learning-Based Method for Determining Earthquake Source Parameters

  2025cites this paper
• Enhancing inverse modeling in groundwater systems through machine learning: a comprehensive comparative study

  2025cites this paper
• GFFMNet: Prediction Method for Coal Mine Seismic Focal Mechanisms Based on GCN

  2025cites this paper
• P‐Wave First‐Motion Polarity Determination Using Order Statistics and Entropy Theory (POSE) With Applications to Southeastern Tibetan Plateau

  2025cites this paper
• Waveform inversion incorporating topography and 3D structures: An essential path to unraveling focal mechanisms and rupture characteristics in complex tectonic regions

  2025cites this paper
• A Deep-Learning-Based Framework for Focal Mechanism Determination and Its Application to the 2022 Luding Earthquake Sequence

  2025cites this paper
• Estimate The Focal Mechanism of Earthquake in Indonesia By Using 1-D Convolutional Neural Network (CNN)

  2025cites this paper
• Data‐Knowledge Driven Hybrid Deep Learning for Earthquake Early Warning

  2024cites this paper
• Determination of earthquake focal mechanism via multi-task learning

  2024cites this paper
• Deep learning based standard rainbow inversion algorithm for retrieving droplet refractive index and size

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

  2024influential citation
• Transfer learning framework for multi-scale crack type classification with sparse microseismic networks

  2024cites this paper
• Seismic Signal Discrimination of Earthquakes and Quarry Blasts in North-East Italy Using Deep Neural Networks

  2024cites this paper
• Threshold-based earthquake early warning for high-speed railways using deep learning

  2024cites this paper
• Deep reinforcement learning for inverting earthquake focal mechanism and its potential application to marine earthquakes

  2024influential citation
• Extracting longitudinal waves by utilizing the symmetry of piezoelectric sphere

  2024cites this paper
• Leveraging internet of things and emerging technologies for earthquake disaster management: Challenges and future directions

  2024cites this paper
• Roof arch collapse of underground cavern in fractured rock mass: In situ monitoring and numerical modeling

  2024cites this paper
• PRIME-DP: Pre-trained Integrated Model for Earthquake Data Processing

  2024cites this paper
• Deep learning for identifying earthquake precursors: Applications and challenges in subsurface fluid signals

  2024cites this paper
• Performance Comparison of PhaseNet and Blockly Earthquake Transformer in Automatic First Arrival Picking on the Cianjur Earthquake

  2024cites this paper
• Unsupervised clustering of mining-induced microseismicity provides insights into source mechanisms

  2024cites this paper
• Self-evolving artificial intelligence framework to better decipher short-term large earthquakes

  2024cites this paper
• Fast and full characterization of large earthquakes from prompt elastogravity signals

  2024cites this paper
• Identification of strong motion record baseline drift based on Bayesian-optimized Transformer network

  2024cites this paper
• Present status and prospective on the seismic hazard studies of major seismic gaps in the Sichuan-Yunnan region

  2024cites this paper
• Advances in Deep Learning for Earthquake Monitoring and Forecasting: Techniques, Applications, and Future Directions

  2024cites this paper
• ANALYSIS OF FAULT PATTERNS THAT CAUSE DESTRUCTIVE EARTHQUAKES IN MAINLAND WEST JAVA

  2024cites this paper
• Insights on earthquake nucleation revealed by numerical simulation and unsupervised machine learning of laboratory-scale earthquake

  2024cites this paper
• Predictive model for peak ground velocity using long short-term memory networks

  2024cites this paper
• Discrimination of earthquakes, explosions, and collapses based on the deep learning: Applications to DiTing 2.0 dataset

  2024cites this paper
• Automatic location of surface-monitored microseismicity with deep learning

  2024cites this paper
• Analysis of Seismic Activity Using Deep Learning

  2024cites this paper
• NA-GCAP: A New Full Moment Tensor Inversion Method Based on the Renewed GRTM and NA Method

  2023cites this paper
• Simultaneous Seismic Phase Picking and Polarity Determination with an Attention-Based Neural Network

  2023cites this paper
• Seismicity-based 3D model of ruptured seismogenic faults in the North-South Seismic Belt, China

  2023cites this paper
• An Efficient Deep Learning Image Condition for Locating Earthquakes

  2023cites this paper
• Machine learning in microseismic monitoring

  2023cites this paper
• Analysis of alternative strategies applied to Naïve-Bayes classifier into the recognition of electrofacies: Application in well-log data at Recôncavo Basin, North-East Brazil

  2023cites this paper
• Application of MEMS Data to Fast Inversion of Rupture Process: Tests with Recordings from the IRREEW Network

  2023cites this paper
• Sensing prior constraints in deep neural networks for solving exploration geophysical problems

  2023cites this paper
• Multi-task multi-station earthquake monitoring: An all-in-one seismic Phase picking, Location, and Association Network (PLAN)

  2023cites this paper
• Earthquake Damage Prediction and Rapid Assessment of Building Damage Using Deep Learning

  2023cites this paper
• Cluster Analysis of Moment Tensor Solutions and its Application to Rockburst Risk Assessment in Underground Coal Mines

  2023cites this paper
• Dependency of the learning technique on the problem nature

  2023cites this paper
• Earthquake focal mechanisms with distributed acoustic sensing

  2023cites this paper
• Investigation on Prediction of Sandstone Failure Under Uniaxial Compression Based on Supervised Deep Learning

  2023cites this paper
• Locating Tremor Using Least-Squares Interferometric Source Location Imaging Method

  2023cites this paper
• An envelope-based machine learning workflow for locating earthquakes in the southern Sichuan Basin

  2023cites this paper
• Deep Learning for Earthquake Disaster Assessment: Objects, Data, Models, Stages, Challenges, and Opportunities

  2023cites this paper
• TraceNet: An Effective Deep-Learning-Based Method for Baseline Correction of Near-Field Acceleration Records

  2023cites this paper
• When it comes to Earth observations in AI for disaster risk reduction, is it feast or famine? A topical review

  2023cites this paper
• SeisCLIP: A Seismology Foundation Model Pre-Trained by Multimodal Data for Multipurpose Seismic Feature Extraction

  2023cites this paper
• Seismic Foundation Model (SFM): a next generation deep learning model in geophysics

  2023cites this paper
• Global Nuclear Explosion Discrimination Using a Convolutional Neural Network

  2023cites this paper
• When Geoscience Meets Foundation Models: Toward a general geoscience artificial intelligence system

  2023cites this paper
• Autonomous Earthquake Location via Deep Reinforcement Learning

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

  2023cites this paper
• Seismic Velocity Inversion via Physical Embedding Recurrent Neural Networks (RNN)

  2023cites this paper
• Inversion techniques for focal mechanism determination of small-magnitude earthquakes: a comparative study using the Burewala earthquake (Mw\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \us

  2023cites this paper
• Seismic arrival-time picking on distributed acoustic sensing data using semi-supervised learning

  2023cites this paper
• Exploring a CNN model for earthquake magnitude estimation using HR-GNSS data

  2023cites this paper
• EQDetect: Earthquake phase arrivals and first motion polarity applying deep learning

  2022cites this paper
• Hybrid Deep-Learning Network for Rapid On-Site Peak Ground Velocity Prediction

  2022cites this paper
• A data-driven artificial neural network model for the prediction of ground motion from induced seismicity: The case of The Geysers geothermal field

  2022cites this paper
• Relative Focal Mechanism Inversion and Its Application to Ridgecrest Sequence

  2022cites this paper
• Earthquake hotspot and coldspot: Where, why and how?

  2022cites this paper
• EdgePhase: A Deep Learning Model for Multi‐Station Seismic Phase Picking

  2022cites this paper
• Deep compressed seismic learning for fast location and moment tensor inferences with natural and induced seismicity

  2022cites this paper
• Waveform Features Strongly Control Subcrater Classification Performance for a Large, Labeled Volcano Infrasound Dataset

  2022cites this paper
• Earthquake Detection and Focal Mechanism Calculation Using Artificial Intelligence

  2022cites this paper
• Immune optimization inspired artificial natural killer cell earthquake prediction method

  2022cites this paper
• Waveform Energy Focusing Tomography With Passive Seismic Sources

  2022cites this paper
• Deep Learning‐Based H‐κ Method (HkNet) for Estimating Crustal Thickness and Vp/Vs Ratio From Receiver Functions

  2022cites this paper
• Detecting Large Explosions With Machine Learning Models Trained on Synthetic Infrasound Data

  2022cites this paper
• Investigations and new insights on earthquake mechanics from fault slip experiments

  2022cites this paper
• Time Variable Stress Inversion of Centroid Moment Tensor Data Using Gaussian Processes

  2022cites this paper
• Inversion of seismic source parameters from satellite InSAR data based on deep learning

  2021cites this paper
• An Improved Tandem Neural Network Architecture for Inverse Modeling of Multicomponent Reactive Transport in Porous Media

  2021cites this paper
• Earthquake Magnitude Estimation Based on Machine Learning: Application to Earthquake Early Warning System

  2021cites this paper
• Automatic Waveform Quality Control for Surface Waves Using Machine Learning

  2021cites this paper