This study describes a deep convolutional neural network (CNN) based technique for the prediction of intensity measurements (IMs) of ground shaking. The input data to the CNN model consists of multistation 3C broadband and accelerometric waveforms recorded during the 2016 Central Italy earthquake sequence for M $\ge$ 3.0. We find that the CNN is capable of predicting accurately the IMs at stations far from the epicenter and that have not yet recorded the maximum ground shaking when using a 10 s window starting at the earthquake origin time. The CNN IM predictions do not require previous knowledge of the earthquake source (location and magnitude). Comparison between the CNN model predictions and the predictions obtained with Bindi et al. (2011) GMPE (which require location and magnitude) has shown that the CNN model features similar error variance but smaller bias. Although the technique is not strictly designed for earthquake early warning, we found that it can provide useful estimates of ground motions within 15-20 sec 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 predicting accurately the ground shaking intensity corresponding to the noise amplitude.
MyShake is a free citizen science smartphone app that provides a range of features related to earthquakes. Features available globally include rapid post-earthquake notifications, live maps of earthquake damage as reported by MyShake users, safety tips and various educational features. The app also uses the accelerometer to detect earthquake shaking and to record and submit waveforms to a central archive. In addition, MyShake delivers earthquake early warning alerts in California, Oregon and Washington. In this study we compare the felt shaking reports provided by MyShake users in California w…
Public earthquake early warning systems have the potential to reduce individual risk by warning people of an incoming tremor but their development has been hampered by costly infrastructure. Furthermore, users' understanding of such a service and their reactions to warnings remains poorly studied. The smartphone app of the Earthquake Network initiative turns users' smartphones into motion detectors and provides the first example of purely smartphone-based earthquake early warnings, without the need for dedicated seismic station infrastructure and operating in multiple countries. We demonstrate…
In a recent study (Jozinović et al, 2020) we showed that convolutional neural networks (CNNs) applied to network seismic traces can be used for rapid prediction of earthquake peak ground motion intensity measures (IMs) at distant stations using only recordings from stations near the epicenter. The predictions are made without any previous knowledge concerning the earthquake location and magnitude. This approach differs from the standard procedure adopted by earthquake early warning systems (EEWSs) that rely on location and magnitude information. In the previous study, we used 10 s, raw, multis…
Earthquakes are major hazards to humans, buildings and infrastructure. Early warning methods aim to provide advance notice of incoming strong shaking to enable preventive action and mitigate seismic risk. Their usefulness depends on accuracy, the relation between true, missed and false alerts, and timeliness, the time between a warning and the arrival of strong shaking. Current approaches suffer from apparent aleatoric uncertainties due to simplified modelling or short warning times. Here we propose a novel early warning method, the deep-learning based transformer earthquake alerting model (TE…
Earthquakes are indeed triggered by fault dislocations, but whether this process alone can produce the actual earthquake energy released by the mainshock has long been questioned. Therefore, exploring the true source of energy that causes earthquakes after the first motion is necessary. Based on analyses of the waveforms and ray paths at seismic stations close to the epicenter, it is considered that strong earthquake vibrations may not be caused by S-waves. It is also proposed that the reservoirs in sedimentary strata contain large amounts of high-pressure fluids, whose pressures can be releas…
The method of waveforms cross correlation (WCC) is used to detect signals from aftershocks of the August 14, 2016 earthquake within Sakhalin Island, which had local magnitude ML = 6.1. Arrivals of regular P- and S-waves detected by the WCC method with various master events at 6 regional stations are associated into a set of seismic events called the cross correlation standard event list (XSEL). We compare the XSEL with the bulletin for the same aftershock sequence compiled in routine seismological processing. The principal advantage of the XSEL is expressed in the increasing number of found se…
We assess the level of cross correlation between P-waves generated by earthquakes in the Atlantic Ocean and measured by 22 array stations of the International Monitoring System (IMS). There are 931 events with 6,411 arrivals in 2011 and 2012. Station TORD was the most sensitive and detected 868 from 931 events. We constructed several 931 by 931 matrices of cross correlation coefficients (CCs) for individual stations and also for average and cumulative CCs. These matrices characterize the detection performance of the involved stations and the IMS. Sixty earthquakes located in the northern hemis…
A scenario-based Neo-Deterministic approach to Seismic Hazard Assessment (NDSHA) is available nowadays, which permits considering a wide range of possible seismic sources as the starting point for deriving scenarios by means of full waveforms modeling. The method does not make use of attenuation relations and naturally supplies realistic time series of ground shaking, including reliable estimates of ground displacement, readily applicable to complete engineering analysis. Based on the neo-deterministic approach, an operational integrated procedure for seismic hazard assessment has been develop…
The reliable statistical characterization of the spatial and temporal properties of large earthquakes occurrence is one of the most debated issues in seismic hazard assessment, due to the unavoidably limited observations from past events. We show that pattern recognition techniques, which are designed in a formal and testable way, may provide significant space-time constraints about impending strong earthquakes. This information, when combined with physically sound methods for ground shaking computation, like the neo-deterministic approach (NDSHA), may produce effectively preventive seismic ha…
Low-magnitude seismic activity between the Kamchatka July 20 and July 29, 2025, earthquakes. Spatio-temporal evolution recovered using waveform cross-correlation
The MyShake project aims to build a global smartphone seismic network to facilitate large-scale earthquake early warning and other applications by leveraging the power of crowdsourcing. The MyShake mobile application first detects earthquake shaking on a single phone. The earthquake is then confirmed on the MyShake servers using a "network detection" algorithm that is activated by multiple single-phone detections. In this part one of the two paper series, we present a network detection algorithm and a simulation platform to test earthquake scenarios at various locations around the world. The p…
Precise real time estimates of earthquake magnitude and location are essential for early warning and rapid response. While recently multiple deep learning approaches for fast assessment of earthquakes have been proposed, they usually rely on either seismic records from a single station or from a fixed set of seismic stations. Here we introduce a new model for real-time magnitude and location estimation using the attention based transformer networks. Our approach incorporates waveforms from a dynamically varying set of stations and outperforms deep learning baselines in both magnitude and locat…
Earthquake hypocenters form the basis for a wide array of seismological analyses. Pick-based earthquake location workflows rely on the accuracy of phase pickers and may be biased when dealing with complex earthquake sequences in heterogeneous media. Time-reversal imaging of passive seismic sources with the cross-correlation imaging condition has potential for earthquake location with high accuracy and high resolution, but carries a large computational cost. Here we present an alternative deep-learning approach for earthquake location by combining the benefits of neural operators for wave propa…
Smartphone-based earthquake early warning systems implemented by citizen science initiatives are characterized by a significant variability in their smartphone network geometry. This has an direct impact on the earthquake detection capability and performance of the system. Here, a simulation framework based on the Monte Carlo method is implemented for making inference on relevant quantities of the earthquake detection such as the detection distance from the epicentre, the detection delay and the warning time for people exposed to high ground shaking levels. The framework is applied to Haiti, w…
Spatio-temporal evolution of low-magnitude seismicity before the May 24, 2013, Sea of Okhotsk earthquake recovered by waveform cross correlation. Is it an earthquake prediction case?
Earthquake monitoring by seismic networks typically involves a workflow consisting of phase detection/picking, association, and location tasks. In recent years, the accuracy of these individual stages has been improved through the use of machine learning techniques. In this study, we introduce a new, end-to-end approach that improves overall earthquake detection accuracy by jointly optimizing each stage of the detection pipeline. We propose a neural network architecture for the task of multi-station processing of seismic waveforms recorded over a seismic network. This end-to-end architecture c…
Geodetic earthquake early warning (EEW) algorithms complement point-source seismic systems by estimating fault-finiteness and unsaturated moment magnitude for the largest, most damaging earthquakes. Because such earthquakes are rare, it has been difficult to demonstrate that geodetic warnings improve ground motion estimation significantly. Here, we quantify and compare timeliness and accuracy of magnitude and ground motion estimates in simulated real time from seismic and geodetic observations for a suite of globally-distributed, large earthquakes. Magnitude solutions saturate for the seismic …
Prediction of the Kamchatka July 29, 2025, earthquake by the evolution of low-magnitude seismicity recovered using waveform cross-correlation at IMS seismic arrays
MyShake harnesses private/personal smartphones to build a global seismic network. It uses the accelerometers embedded in all smartphones to record ground motions induced by earthquakes, returning recorded waveforms to a central repository for analysis and research. A demonstration of the power of citizen science, MyShake expanded to 6 continents within days of being launched, and has recorded 757 earthquakes in the first 2 years of operation. The data recorded by MyShake phones has the potential to be used in scientific applications, thereby complementing current seismic networks. In this pape…
East China University of Technology（东华理工大学）；Dalhousie University（达尔豪斯大学）；Stanford University（斯坦福大学）
Earthquake early warning systems are required to report earthquake locations and magnitudes as quickly as possible before the damaging S wave arrival to mitigate seismic hazards. Deep learning techniques provide potential for extracting earthquake source information from full seismic waveforms instead of seismic phase picks. We developed a novel deep learning earthquake early warning system that utilizes fully convolutional networks to simultaneously detect earthquakes and estimate their source parameters from continuous seismic waveform streams. The system determines earthquake location and m…
The recent evolution of induced seismicity in Central United States calls for exhaustive catalogs to improve seismic hazard assessment. Over the last decades, the volume of seismic data has increased exponentially, creating a need for efficient algorithms to reliably detect and locate earthquakes. Today's most elaborate methods scan through the plethora of continuous seismic records, searching for repeating seismic signals. In this work, we leverage the recent advances in artificial intelligence and present ConvNetQuake, a highly scalable convolutional neural network for earthquake detection a…
The MyShake project aims to build a global smartphone seismic network to facilitate large-scale earthquake early warning and other applications by leveraging the power of crowdsourcing. The MyShake mobile application first detects earthquake shaking on a single phone. The earthquake is then confirmed on the MyShake servers using a "network detection" algorithm that is activated by multiple single-phone detections. In part two of this two paper series, we report the first order performance of MyShake's Earthquake Early Warning (EEW) capability in various selected locations around the world. Due…
Relative relocation methods are commonly used to precisely relocate earthquake clusters consisting of similar waveforms. Repeating waveforms are often recorded at volcanoes, where, however, the crust structure is expected to contain strong heterogeneities and therefore the 1D velocity model assumption that is made in most location strategies is not likely to describe reality. A peculiar cluster of repeating low-frequency seismic events was recorded on the south flank of Katla volcano (Iceland) from 2011. As the hypocentres are located at the rim of the glacier, the seismicity may be due to vol…
In this study we develop a single-station deep-learning approach for fast and reliable estimation of earthquake magnitude directly from raw waveforms. We design a regressor composed of convolutional and recurrent neural networks that is not sensitive to the data normalization, hence waveform amplitude information can be utilized during the training. Our network can predict earthquake magnitudes with an average error close to zero and standard deviation of ~0.2 based on single-station waveforms without instrument response correction. We test the network for both local and duration magnitude sca…
Recovery of low-magnitude seismic events before the July 29, 2025, Kamchatka megathrust earthquake using waveform cross-correlation enhanced by the addition of stochastic noise
Slow earthquakes may trigger failure on neighboring locked faults that are stressed enough to break, and slow slip patterns may evolve before a nearby great earthquake. However, even in the clearest cases such as Cascadia, slow earthquakes and associated tremor have only been observed in intermittent and discrete bursts. By training a convolutional neural network to detect known tremor on a single seismic station in Cascadia, we isolate and identify tremor and slip preceding and following known larger slow events. The deep neural network can be used for the detection of quasi-continuous tremor…
Seismic-phase detection using multiple deep learning models for global and local representations of waveforms
Earthquake Research Institute, The University of Tokyo（东京大学地震研究所）；Graduate School of Information Science and Technology, The University of Tokyo（东京大学信息科学与技术研究生院）
Objective testing is a key issue in the process of revision and improvement of seismic hazard assessments. Therefore we continue the rigorous comparative analysis of past and newly available hazard maps for the territory of Italy against the seismic activity observed in reality. The final Global Seismic Hazard Assessment Program (GSHAP) results and the most recent version of Seismic Hazard Harmonization in Europe (SHARE) project maps, along with the reference hazard maps for the Italian seismic code, all obtained by probabilistic seismic hazard assessment (PSHA), are cross-compared to the thre…
The rapid characterisation of earthquake parameters such as its magnitude is at the heart of Earthquake Early Warning (EEW). In traditional EEW methods the robustness in the estimation of earthquake parameters have been observed to increase with the length of input data. Since time is a crucial factor in EEW applications, in this paper we propose a deep learning based magnitude classifier and, further we investigate the effect of using five different durations of seismic waveform data after first P wave arrival of length 1s, 3s, 10s, 20s and 30s. This is accomplished by testing the performance…
Rapid Earthquake-to-Tsunami Waveform Generation via Large-Scale Multi-GPU FFT Convolution Applied to the Cascadia Subduction Zone
Oden Institute for Computational Engineering；Sciences The University of Texas at Austin Austin, TX, USA；Sciences, Walker Department of Mechanical Engineering The University of Texas at Austin Austin, TX, USA
We apply cross correlation between multichannel seismic waveforms as a technique for signal detection and automatic event building at the International Data Centre (IDC). This technique allows detecting signals with amplitudes by at least a factor of two lower than those found in the current version of IDC processing. Previously, we processed with a cross correlation detector aftershock sequences of a large earthquake with thousands of aftershocks detected by the International Monitoring System (IMS) and a middle-size earthquake (hundreds of aftershocks). Our study has revealed that the offici…
Earthquakes can be detected by matching spatial patterns or phase properties from 1-D seismic waves. Current earthquake detection methods, such as waveform correlation and template matching, have difficulty detecting anomalous earthquakes that are not similar to other earthquakes. In recent years, machine-learning techniques for earthquake detection have been emerging as a new active research direction. In this paper, we develop a novel earthquake detection method based on dictionary learning. Our detection method first generates rich features via signal processing and statistical methods and …
The accurate and automated determination of earthquake locations is still a challenging endeavor. However, such information is critical for monitoring seismic activity and assessing potential hazards in real time. Recently, a convolutional neural network was applied to detect earthquakes from single-station waveforms and approximately map events across several large surface areas. In this study, we locate 194 earthquakes induced during oil and gas operations in Oklahoma, USA, within an error range of approximately 4.9 km on average to the epicenter and 1.0 km to the depth in catalogs with data…
Frictional heat during earthquake rupture raises the pressure of fault zone fluids and affects the rupture process and its seismic radiation. Here, we investigate the role of two key parameters governing thermal-pressurization of pore fluids -- hydraulic diffusivity and shear-zone half-width -- on earthquake rupture dynamics, kinematic source properties and ground-motions. We conduct 3D strike-slip dynamic rupture simulations assuming a rate-and-state dependent friction law with strong velocity-weakening coupled to thermal-pressurization of pore fluids. Dynamic rupture evolution and ground-sha…
Effects of stochastic and natural seismic noise on the performance of waveform cross-correlation used to recover low-magnitude seismicity prior to the July 29, 2025, Kamchatka earthquake
Based on waveform data from a profile of aftershocks following the north-south trace of the June 28, 1992 Landers rupture across the Mojave desert, we construct a new velocity model for the Mojave region which features a thin, slow crust. Using this model, we obtain source parameters, including depth and duration, for each of the aftershocks in the profile, and in addition, any significant (M>3.7) Joshua Tree--Landers aftershock between April, 1992 and October, 1994 for which coherent TERRAscope data were available. In all, we determine source parameters and stress-drops for 45 significant (M_…
Usual inversion for earthquake source parameters from tsunami wave data incorporates subjective elements. Noisy and possibly insufficient data also results in instability and non-uniqueness in most deterministic inversions. Here we employ the satellite altimetry data for the 2004 Sumatra-Andaman tsunami event to invert the source parameters. Using a finite fault model that represents the extent of rupture and the geometry of the trench, we perform a non-linear joint inversion of the slips, rupture velocities and rise times with minimal a priori constraints. Despite persistently good waveform f…
We compute a series of finite-source parameter inversions of the fault rupture of the 2004 Parkfield earthquake based on 1 Hz GPS records only. We confirm that some of the co-seismic slip at shallow depth (<5 km) constrained by InSAR data processing results from early post-seismic deformation. We also show 1) that if located very close to the rupture, a GPS receiver can saturate while it remains possible to estimate the ground velocity (~1.2 m/s) near the fault, 2) that GPS waveforms inversions constrain that the slip distribution at depth even when GPS monuments are not located directly above…
Convergent representations of elastic-wave structure emerge across deliberately distinct seismic training routes
Institute of Geophysics, China Earthquake Administration（中国地震局地球物理研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Laboratory of Seismology and Physics of Earth’s Interior, School of Earth and Space Sciences, University of Science and Technology of China（中国科学技术大学地球和空间科学学院地球内部地震学与物理学实验室）；Institute of Advanced Technology, University of Science and Technology of China（中国科学技术大学先进技术研究院）
Zymergen（Zymergen公司）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；Berkeley Seismological Laboratory（伯克利地震实验室）；AT&T（美国电话电报公司）；University of California, Berkeley（加州大学伯克利分校）
After significant earthquakes, we can see images posted on social media platforms by individuals and media agencies owing to the mass usage of smartphones these days. These images can be utilized to provide information about the shaking damage in the earthquake region both to the public and research community, and potentially to guide rescue work. This paper presents an automated way to extract the damaged building images after earthquakes from social media platforms such as Twitter and thus identify the particular user posts containing such images. Using transfer learning and ~6500 manually l…
Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；University of New Mexico（新墨西哥大学）；Southern University of Science and Technology（南方科技大学）；University of Utah（犹他大学）
This paper combines the power of deep-learning with the generalizability of physics-based features, to present an advanced method for seismic discrimination between earthquakes and explosions. The proposed method contains two branches: a deep learning branch operating directly on seismic waveforms or spectrograms, and a second branch operating on physics-based parametric features. These features are high-frequency P/S amplitude ratios and the difference between local magnitude (ML) and coda duration magnitude (MC). The combination achieves better generalization performance when applied to new …
Earthquake monitoring workflows are designed to detect earthquake signals and to determine source characteristics from continuous waveform data. Recent developments in deep learning seismology have been used to improve tasks within earthquake monitoring workflows that allow the fast and accurate detection of up to orders of magnitude more small events than are present in conventional catalogs. To facilitate the application of machine-learning algorithms to large-volume seismic records, we developed a cloud-based earthquake monitoring workflow, QuakeFlow, that applies multiple processing steps …
The 11/5/2011 Lorca, Spain earthquake (Mw5.2) and related seismicity produced extensive damage in the town of Lorca and vicinity. During these earthquakes, evidence of rotations and permanent deformations in structures were observed. To analyze these aspects and study the source properties from the near field, the displacement time histories were obtained including the static component at Lorca station. Displacement time histories were computed by an appropriate double time integration procedure of accelerograms. Using these data, the foreshock and mainshock slip distributions were calculated …
