Earthquake Early Warning Research Articles

Machine Learning-Powered Earthquake Early Warning System

The most devastating natural disasters on earth are earthquakes that causes long-term effects on geography, civilization, and human life. These unpredictable events pose a serious threat to infrastructure. Furthermore, the current Earthquake Early Warning (EEW) systems are facing issues such as limited warning times, false alarms, maintenance costs, high construction costs, and data interpretation. Highlighting these as an urgent need for mitigation measures, there is a need to improve the effectiveness of electronic alerts and public safety measures. For this transformative machine learning techniques and the integration of disparate data, can embark on creating social security and lives protecting from major environmental disasters like earthquakes. This paper has compared various Machine Learning (ML) techniques by training them by using two datasets: one from India and another from India United States Geological from Research World Database to improve the robustness and generality of the earthquake prediction model in the Earthquake Early Warning (EEW) framework. This represents a major advance for earthquake detection and promises to reduce response time. Among various ML Techniques, Random Forest has performed well in earthquake warning with 96.06% accuracy and 98.6% precision.

Earthquake detection in mountainous homes using the internet of things connected to photovoltaic energy supply

The North Sumatra region is an area with the potential for earthquakes originating from volcanic and oceanic eruptions which have resulted in many fatalities. Therefore, through the application of automatic monitoring and control system technology connected to the internet of things (IoTs), it is the right solution to provide efforts to increase security for residents of the house to always be vigilant. The security enhancement method referred to in this study is a home security system protection system by anticipating earthquakes. The advantage of this tool is that it applies a notification security system method with a sensitivity sensor which is automatically sent via email and sonor buzzer which also acts as sound vibrations due to an earthquake. The test results show that when a vibration occurs, the system will send a short email message to the user's smartphone so that the user will receive an email in the form of a warning message that the state of the house has an earthquake and the light-emitting diode (LED) interrupts and the buzzer is also on so that the alarm sounds which has been integrated into IoT. Then an integrated security monitoring system using the web can be monitored in real time.

An Evolutionary Gravitational Neocognitron Neural Network for Earthquake Parameters Observation in IoT System-Based Earthquake Early Warning

An earthquake early-warning system (EEWS) is essential for preserving human life. In terms of disaster management and EQ risk reduction, quickly determining the earthquake’s (EQ’s) magnitude and position is important. To prevent an EQ catastrophe, these parameters can be transmitted over an IoT network. The Evolutionary Gravitational Neocognitron Neural Network (EGNNN), a novel technique for real-time earthquake parameter observation, is introduced in this paper to enhance earthquake early warning (EEW) systems. The proposed framework uses various sophisticated data processing methods to analyze publically accessible earthquake data from sources like the Japan Meteorological Agency. The Morphological Filtering Extended Empirical Wavelet Transformation (MFEEWT) method is first used to pre-process seismic waveform input, significantly lowering noise levels in the data. After that, from the pre-processed waveforms the relevant features are extracted via the Fast Discrete Curvelet Transform with Wrapping (FDCT-WRP) and a Stacked Autoencoder (SAE). The EGNNN, an innovative neural network model created for earthquake parameter prediction, specifically location and magnitude, uses these extracted features as input. The Osprey optimization algorithm (OOA) is employed to enhance the EGNNN model. A crucial component of EEW systems, dependable and quick alert delivery is ensured by the proposed system’s integration with an Internet of Things (IoT) framework. The EGNNN swiftly evaluates earthquake parameters and sends this vital data to a centralized IoT system, enabling pertinent entities to act promptly. Performance evaluation is conducted on the Python platform, comparing the proposed technique with existing methods. The proposed method EGNNN-EPO-IoT achieves a higher warning time of 23.34%, 3.45%, and 7.86%; 12.23%, 32.21%, and 22.09% higher accuracy compared to the other existing techniques such as 3S-AE-CNN-EPO-IoT (3 sec-Autoencoder-Convolutional neural network-Earthquake parameter observation-IoT), XGB-EPO-IoT (Extreme Gradient Boosting-EPO-IoT), and SVM-EPO-IoT (Support Vector Machine-EPO-IoT).

A Convolutional Neural Networks Model Based on Wavelet Packet Transform for Enhanced Earthquake Early Warning

The earthquake early warning (EEW) system is critical in mitigating the effects of seismic hazards by providing valuable response time. Damage to buildings can be determined based on peak ground acceleration (PGA). If PGA can be predicted in advance, the seismic risk of a building can be estimated. A novel method for predicting PGA using wavelet packet transform (WPT) and convolutional neural networks (CNN) is proposed. Early arrival waves generated by earthquakes are decomposed using WPT to produce a matrix of wavelet coefficients. This matrix serves as the input to the CNN model to predict the PGA. To achieve the best prediction performance, different setups were investigated, including the use of Daubechies Wavelet 4 (db4) and four-level decomposition. The results indicate that this configuration yields better prediction accuracy. P-waves of three-second duration are commonly used for EEW. Compared to the prediction results of a CNN model used to validate the method, the proposed method has a lower average error and better use of early arrival waves with shorter duration. Overall, the proposed method demonstrates the potential of WPT and CNN in EEW systems. The proposed approach can utilize shorter early arrival waves to predict PGA and gain more reaction time to get rid of seismic hazards. To estimate structural damage using the predicted PGA under an impending earthquake, a method is proposed to quickly determine structural damage based on the predicted PGA and fragility curves. It provides a method to estimate the potential structural damage caused by an impending earthquake.

The Ojai California Earthquake of 20 August 2023: Earthquake Early Warning Performance and Alert Recipient Response in the Mw 5.1 Event

Abstract A magnitude 5.1 earthquake in California rarely generates more than momentary notice—a headline in local newspapers and a mention with footage on the evening news—then fades into obscurity for most people. But this earthquake, which occurred near the city of Ojai, is important for seismologists, social scientists, emergency managers, policymakers, and others who are engaged in implementing and improving earthquake early warning (EEW) technology and in assessing its value in public warnings. In this earthquake, ShakeAlert, the EEW system for the West Coast of the United States operated by the U.S. Geological Survey (USGS), was publicly activated and, for the first time, a substantial number of those who received alerts provided feedback on various aspects of the alerts they received. To capture data related to public attitudes and assessments regarding this and future alerts, a supplemental questionnaire was developed and associated with the “Did You Feel It?” (DYFI) earthquake reporting system, also operated by the USGS. The DYFI system received over 14,000 felt reports; 2490 of these were by people who received or expected to receive an alert before the onset of earthquake motion at their locations. This article analyzes the aggregate results of these EEW user reports, touching on the respondent’s situation upon receiving the alert, characteristics of the alert received, and, perhaps, most importantly, how the alert recipient responded if received before feeling earthquake motion. The new DYFI EEW supplemental questionnaire also inquired about respondent views of alert usefulness and preferences in future alerts. Our report provides a first glimpse of a range of behaviors, attitudes, and assessments by users of the recently implemented EEW system for the U.S. West Coast.

Employing Machine Learning for Seismic Intensity Estimation Using a Single Station for Earthquake Early Warning

An earthquake early-warning system (EEWS) is an indispensable tool for mitigating loss of life caused by earthquakes. The ability to rapidly assess the severity of an earthquake is crucial for effectively managing earthquake disasters and implementing successful risk-reduction strategies. In this regard, the utilization of an Internet of Things (IoT) network enables the real-time transmission of on-site intensity measurements. This paper introduces a novel approach based on machine-learning (ML) techniques to accurately and promptly determine earthquake intensity by analyzing the seismic activity 2 s after the onset of the p-wave. The proposed model, referred to as 2S1C1S, leverages data from a single station and a single component to evaluate earthquake intensity. The dataset employed in this study, named “INSTANCE,” comprises data from the Italian National Seismic Network (INSN) via hundreds of stations. The model has been trained on a substantial dataset of 50,000 instances, which corresponds to 150,000 seismic windows of 2 s each, encompassing 3C. By effectively capturing key features from the waveform traces, the proposed model provides a reliable estimation of earthquake intensity, achieving an impressive accuracy rate of 99.05% in forecasting based on any single component from the 3C. The 2S1C1S model can be seamlessly integrated into a centralized IoT system, enabling the swift transmission of alerts to the relevant authorities for prompt response and action. Additionally, a comprehensive comparison is conducted between the results obtained from the 2S1C1S method and those derived from the conventional manual solution method, which is considered the benchmark. The experimental results demonstrate that the proposed 2S1C1S model, employing extreme gradient boosting (XGB), surpasses several ML benchmarks in accurately determining earthquake intensity, thus highlighting the effectiveness of this methodology for earthquake early-warning systems (EEWSs).

Wave propagation in context of Moore–Gibson–Thompson thermoelasticity with Klein–Gordon nonlocality

Understanding plane and surface waves in elastic materials is crucial in various fields, including geophysics, seismology, and materials science, as they provide valuable information about the properties of the materials they travel through and can help in earthquake detection and analysis. In the present paper, the governing equations of Moore–Gibson–Thompson (MGT) thermoelasticity are modified in context of Klein–Gordon (KG) nonlocality. For linear, homogeneous and isotropic case, the governing equations in two-dimensions are solved to obtain the dispersion relations for possible plane waves. It is found that there exists one transverse and two coupled longitudinal waves in a two-dimensional model of MGT weakly nonlocal thermoelastic medium and the speeds of these plane waves are found to be dependent on KG nonlocal parameters. The coupled longitudinal waves are also found to be dependent on conductivity rate parameter. For linear, homogeneous and isotropic case, the governing equations in two-dimensions are also solved to obtain a Rayleigh wave secular equation at thermally insulated surface. For a numerical example of aluminium material, the speeds of transverse wave, coupled longitudinal waves and the Rayleigh wave are computed and graphically illustrated to visualize the effects of KG nonlocality parameters, conductivity rate parameter and the angular frequency on the wave speeds.

Threshold-based earthquake early warning for high-speed railways using deep learning

Earthquakes are disasters that threaten the operational safety of high-speed railways. To obtain reliable alerts for the earthquake monitoring and early warning systems of high-speed railways, based on magnitude and peak ground acceleration (PGA) thresholds (M = 5.5 and PGA = 40 cm/s2), an earthquake early warning (EEW) method for high-speed railways using deep learning is proposed. And the application of deep learning method in EEW for high-speed railway is explored. We design a single-station deep learning network architecture (named the CT architecture) by combining convolutional neural and transformer networks, and with that architecture, we train two separate models (CT-M and CT-PGA models) using the strong motion data recorded from the Kyoshin Network in Japan, which are used to predict whether the magnitude and PGA exceed the thresholds for issuing an alert. To verify the robustness of the method, we apply it to the M7.3 earthquake and M7.4 earthquake off the coast of Fukushima in 2021–2022. Results show that within 10 s after P-wave arrival, the accuracy of the alert reaches 90 %, and the average observed lead time reaches 18 s. The proposed method displays potential application on EEW systems for high-speed railways.

Deep learning for deep earthquakes: insights from OBS observations of the Tonga subduction zone

SUMMARY Applications of machine learning in seismology have greatly improved our capability of detecting earthquakes in large seismic data archives. Most of these efforts have been focused on continental shallow earthquakes, but here we introduce an integrated deep-learning-based workflow to detect deep earthquakes recorded by a temporary array of ocean-bottom seismographs (OBSs) and land-based stations in the Tonga subduction zone. We develop a new phase picker, PhaseNet-TF, to detect and pick P- and S-wave arrivals in the time–frequency domain. The frequency-domain information is critical for analysing OBS data, particularly the horizontal components, because they are contaminated by signals of ocean-bottom currents and other noise sources in certain frequency bands. PhaseNet-TF shows a much better performance in picking S waves at OBSs and land stations compared to its predecessor PhaseNet. The predicted phases are associated using an improved Gaussian Mixture Model Associator GaMMA-1D and then relocated with a double-difference package teletomoDD. We further enhance the model performance with a semi-supervised learning approach by iteratively refining labelled data and retraining PhaseNet-TF. This approach effectively suppresses false picks and significantly improves the detection of small earthquakes. The new catalogue of Tonga deep earthquakes contains more than 10 times more events compared to the reference catalogue that was analysed manually. This deep-learning-enhanced catalogue reveals Tonga seismicity in unprecedented detail, and better defines the lateral extent of the double-seismic zone at intermediate depths and the location of four large deep-focus earthquakes relative to background seismicity. It also offers new potential for deciphering deep earthquake mechanisms, refining tomographic models, and understanding of subduction processes.

Earthquake prediction using satellite data: Advances and ahead challenges

Due to the considerable loss of life and damages caused by powerful Earthquakes, along with the strengthening of structures and disaster management systems, many researches are being conducted associated with the possibility of creating Earthquake warning systems. However, no reliable scientific report on successful Earthquake prediction has been published so far. Although there are a couple of published scientific papers indicating the detection of unusual changes in physical and chemical parameters obtained from ground stations, but due to the limitations of in-situ measurement in terms of number, location, time and cost, there was no noticeable progress in Earthquake warning. After the advent of remote sensing satellites, the number of statistical studies related to Earthquake precursors increased significantly, and most of them emphasized the existence of abnormal behaviors in physical and chemical precursors around the time (about 1–30 days before) and locations of powerful Earthquakes. In this study, an attempt has been made to address the advances and challenges in the way of Earthquake prediction using satellite data and provide a perspective of the future of these researches. It should be noted that the increase in the number of satellites designed and launched specially for Earthquake studies, the variety of available Earthquake precursors (multi-precursor analysis), the development of classic and intelligent anomaly detection and predictor algorithms (multi-method analysis), the provision of intelligent systems for the integration of various precursors (fusion and decision systems), the creation of cloud storing and processing data services (Google Earth Engine, Giovanni, etc.) and the development of intelligent user interfaces for public, have made researchers more hopeful for the appearance of low-uncertainty Earthquake warning systems in the near future.

SeismoNet: A proximal policy optimization-based earthquake early warning system using dilated convolution layers and online data augmentation

In seismic safety, Earthquake Early Warning (EEW) systems are indispensable for mitigating earthquake hazards. These systems strive to quickly evaluate earthquake magnitudes to determine which events warrant immediate alerts. Despite their importance, conventional approaches to rapid earthquake classification face significant hurdles, particularly with the skewed data distribution where instances requiring alerts are far less common. This study proposes an EEW method, called SeismoNet, that leverages a 7-second snapshot of three-dimensional seismic waveforms from the China Earthquake Network Center (CENC). SeismoNet incorporates a trio of dilated convolution layers to distill essential features for effective classification, addressing the critical challenge of data imbalance. Our novel integration of the Off-policy Proximal Policy Optimization (Off-policy PPO) algorithm enriches the model by rewarding accurate classifications, refining its sensitivity to less frequent yet critical seismic events. The training approach is conceptualized as a sequence of decision-making steps, with each seismic sample treated as a unique scenario. The model, acting as a decision-making agent, is rewarded or penalized based on its ability to differentiate between less and more common events. To further enhance classification accuracy, we employ a generative adversarial network (GAN) for dynamic data augmentation and a regularization technique to prevent common pitfalls like mode collapse and training instability. The efficacy of SeismoNet is underscored by its superior performance metrics, including an F-measure of 88.14% and a geometric mean of 90.66%, outperforming existing deep-learning solutions, traditional algorithms, and transfer learning methods. Our exhaustive evaluations, including ablation studies that remove key components like dilated convolutions and PPO, affirm the vital contribution of these elements to SeismoNet’s exceptional capability in EEW. SeismoNet can successfully issue timely warnings for significant seismic events, allowing for essential preventative measures and significantly reducing the potential impact on these communities.

Broad observation area and high resolution using identifier for synthetic aperture radars

AbstractTo achieve broad observation areas and high resolution, synthetic aperture radars adopt wavelet‐transformed observation areas that contain information on position and velocity. The observation area adopts pseudosignals with scattering information about the position and velocity in three dimensions. The wavelet transform (WT) is applied to micromoving targets to obtain a pseudosignal, and each micromoving target is defined by an Identifier (ID) of parameter scale a and parameter shift b. Because the interval of each micromoving target is minimised by the WT, the array of all micromoving targets becomes a continuum that can be represented by straight or curved lines. Every micromoving target can be identified by an ID as long as the micromoving targets do not overlap. Every moving signal in a three‐dimensional space can be identified by the abovementioned ID. The results demonstrated that the observation area can be broadened by employing the minimum number of units with micromoving targets. In addition, micromoving targets in the observation area can be obtained at a high resolution (3 cm), and the position of the ID does not change owing to noise. The developments presented can contribute to the fast detection of earthquakes.

Follow the Trace: Becoming a Seismo-Detective with a Campus-Based Raspberry Shake Seismometer

Abstract Seismic signals, whether caused by earthquakes, other natural phenomena, or artificial noise sources, have specific characteristics in the time and frequency domains that contain crucial information reflecting their source. The analysis of seismic time series is an essential part of every seismology-oriented study program. Enabling students to work with data collected from their own campus, including signals from both anthropogenic and natural seismic sources, can provide vivid, practical examples to make abstract concepts communicated in classes more concrete and relevant. Data from research-grade broadband seismometers enable us to record time series of vibrations at a broad range of frequencies; however, these sensors are costly and are often deployed in remote places. Participation in the Raspberry Shake citizen science network enables seismology educators to record seismic signals on our own campuses and use these recordings in our classrooms and for public outreach. Yale University installed a Raspberry Shake three-component, low-cost seismometer in the Earth and Planetary Sciences department building in Summer 2022, enabling the detection of local, regional, and teleseismic earthquakes, microseismic noise, and anthropogenic noise sources from building construction, an explosive event in a steam tunnel, and general building use. Here, we discuss and illustrate the use of data from our Raspberry Shake in outreach and education activities at Yale. In particular, we highlight a series of ObsPy-based exercises that will be used in courses taught in our department, including our upper-level Introduction to Seismology course and our undergraduate classes on Natural Disasters and Forensic Geoscience.

Evaluation of the single-frequency variometric approach based on low-cost GNSS observations and different satellite combinations for detecting short-term dynamic behaviors

This study presents the capability of the single-frequency (SF) variometric approach (VA) technique with low-cost GNSS observations to detect short-term dynamic behaviors. Harmonic oscillations with amplitudes between 5 and 20 mm and frequencies between 0.3 and 5.0 Hz were generated employing a single-axis shake table to investigate the performance of the SF-VA technique in the structural health monitoring (SHM) system. Besides, a Mw 6.9 Kobe, 1995 earthquake simulation was generated using the shake table to analyze the SF-VA performance for the earthquake early warning (EEW) system. A low-cost u-blox ZED-F9P GNSS receiver and ANN-MB-00 patch antenna were used to collect GNSS observations at a 20 Hz sampling rate during the experiments. The observations were processed using the MATLAB-based open-source PPPH-VA software in real-time (RT) mode, considering eight different satellite combinations. The capability of the SF-VA technique to detect horizontal dynamic behaviors in RT mode was investigated in the frequency and time domains, accepting the displacements from the linear variable differential transformer sensor as a reference. The results in the frequency domain demonstrate that the SF-VA technique with low-cost GNSS observations can successfully detect the peak frequency value of short-term harmonic oscillations up to 5 Hz. Moreover, time domain findings emphasize that the short-time dynamic oscillations can be determined with the SF-VA technique with an accuracy ranging from 0.8 to 6.4 mm. Earthquake simulation experiment results demonstrate that the strong ground motions caused by mega earthquakes can be determined at mm-level by the SF-VA method. The results of both experiments show that multi-GNSS observations contribute to the SF-VA technique considerably. Overall, the findings reveal that the SHM and EEW systems can be operated with low-cost GNSS receivers, and the natural frequency of the man-made structures and accurate displacement values of seismic waveforms can be determined in RT with the SF-VA technique.

Magnitude estimation and site characterization in southwestern British Columbia: application to earthquake early warning

In this study, we took a close look at the Ocean Networks Canada’s earthquake early warning system in southwestern British Columbia through analysis of the magnitude estimates by this system and characterization of site conditions for both onshore and offshore stations. Using magnitude values estimated at each station, over hundreds of notifications, we provided station terms to correct the magnitudes for stations that systematically generate high or low magnitude values. Moreover, by compiling a rich ground motion amplitude dataset and applying the horizontal-to-vertical spectral ratio method from Fourier amplitude of acceleration and response spectral acceleration, we investigated site characterization through evaluation of non-linear site response behavior and estimation of the site dominant frequency (fpeak) and its peak amplitude (Apeak) for each station. In general, no strong evidence of non-linearity is observed at any stations considering the magnitude-distance distribution of ground motions in this study. Offshore sites show fpeak and Apeak in the range of approximately 1.7–6 Hz and 0.4–1.2 (in base-10 log unit), respectively, whereas onshore sites show approximately 1–6 Hz for fpeak and 0.3–0.7 (in base-10 log unit) for Apeak.

ConvEQ: Convolutional neural network for earthquake phase classification using short time frequency transform

We present ConvEQ as a tool for discriminating seismic phases, leveraging artificial intelligence technique (Convolutional Neural Network) for short-time Frequency Transform of the seismic signal. Timely detection of the vertical (P) wave from an earthquake can generate a warning several tens of precious seconds before the more destructive waves strike. We propose a train-for-each-station approach for an Internet-of-Things-based Smart Earthquake Early Warning System, where lightweight neural networks trained for the seismic data belonging to each station are implemented on edge devices directly interfaced with seismometers. The approach has the potential to get the most from the sparse seismic network for Pakistan and other third-world countries. We train networks for multi-station and single-station data and achieve 96% and 99% accuracy, respectively, proving that train-for-each-station maximizes accuracy. The total processing time (including preprocessing and inference) is about 30ms for each event, thus suitable for real-time deployment. We further compare the performance of ConvEQ on simulated real-time data with several state-of-the-art contemporary algorithms. Our proposed approach demonstrates a robust response on diverse metrics. The ConvEQZ classifies the vertical seismic signal component with high accuracy and the ConvEQX can classify any seismic data component, inculcating robustness against connectivity issues.

Uttarakhand State Earthquake Early Warning System: A Case Study of the Himalayan Environment.

The increased seismic activity observed in the Himalayas, coupled with the expanding urbanization of the surrounding areas in northern India, poses significant risks to both human lives and property. Developing an earthquake early warning system in the region could help in alleviating these risks, especially benefiting cities and towns in mountainous and foothill regions close to potential earthquake epicenters. To address this concern, the government and the science and engineering community collaborated to establish the Uttarakhand State Earthquake Early Warning System (UEEWS). The government of Uttarakhand successfully launched this full-fledged operational system to the public on 4 August 2021. The UEEWS includes an array of 170 accelerometers installed in the seismogenic areas of the Uttarakhand. Ground motion data from these sensors are transmitted to the central server through the dedicated private telecommunication network 24 hours a day, seven days a week. This system is designed to issue warnings for moderate to high-magnitude earthquakes via a mobile app freely available for smartphone users and by blowing sirens units installed in the buildings earmarked by the government. The UEEWS has successfully issued alerts for light earthquakes that have occurred in the instrumented region and warnings for moderate earthquakes that have triggered in the vicinity of the instrumented area. This paper provides an overview of the design of the UEEWS, details of instrumentation, adaptation of attributes and their relation to earthquake parameters, operational flow of the system, and information about dissemination of warnings to the public.

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

Abstract Conventional earthquake early warning systems (EEWS) rely on mathematical functions that utilize P-wave parameters extracted over a 3 s window to estimate peak ground acceleration (PGA). Advancements in the capabilities of deep neural networks to approximate universal functions, coupled with the availability of strong seismic event data, offer an unprecedented opportunity to evaluate the relationship between variable snapshots of P-wave data and the PGA of strong-motion earthquakes. This convergence of technology and data opens new avenues for research into utilizing smaller snapshots of P-wave in EEWS. Our study centers on the utilization of a long short-term memory (LSTM) neural network to model long dependencies within the P-wave of 1839 earthquakes recorded by the Kiyonshin Network (K-NET) for the prediction of PGA of S waves. Our methodology involves experiments that ultimately evaluate the network’s performance on 4, 3, and 2 s of P-wave snapshots. Our findings indicate that there is sufficient information in 2 s of temporal accelerometer readings after the onset of P waves to predict PGA accurately with an LSTM network.

Adapting PLUM: Earthquake Early Warning with Node-Level Processing in New Zealand

Is running the Propagation of Local Undamped Motion (PLUM) algorithm in a community-engaged earthquake early warning (EEW) network feasible, and can it function effectively at the node level without centralised processing units? This study investigates the practicality of deploying the PLUM algorithm within a node-level architecture, shifting away from traditional centralised seismic data processing methods. The study uses cost-effective MEMS-based seismographs to decentralise EEW. The preliminary phase of the research included the deployment of sensors and the establishment of a two-tiered Primary-Secondary node structure for node-level intensity prediction and alert generation, with the sensors functioning as independent prediction points. Future work includes threshold calibration for optimal alert issuance, and network expansion to reduce blind spots. This work-in-progress paper discusses progress towards a scalable, efficient EEW system that could serve as a replicable model for earthquake-prone regions globally, aiming for operational readiness that empowers communities against the threat of earthquakes.

Introducing ViDA3, An Earthquake Early Warning Algorithm for Offshore Hypocenter Determination Using Onshore Seismic Networks

ABSTRACT The objective functions adopted by earthquake early warning (EEW) location algorithms are inadequate for out-of-network earthquakes. As a result, the real-time locations of these earthquakes are often erroneous. The consequences of mislocating out-of-network earthquakes are that their magnitudes are miscalculated, and the loci of their shaking predictions map are shifted. Given that the largest earthquakes occur in subduction settings, improving real-time out-of-network earthquake location is of great importance. In this study, the Virtual Dynamically Assembled Array Algorithm (ViDA3) is introduced, which addresses the location issue of offshore and off-network earthquakes. The guiding principle underlying the new EEW location algorithm is that standard seismic networks may be viewed as a collection of medium-sized seismic arrays, with each array consisting of three or more network stations. The potential of array seismology for EEW against out-of-network earthquakes stems primarily from the slowness vector, which points at the direction of the epicentral region. Thus, this region may be constrained merely by intersecting two or more such vectors. In addition, the length of the slowness vector depends on the hypocentral distance and depth and is thus vital for addressing an acute problem in a subduction setting—discriminating between upper crust and deep slab earthquakes. Furthermore, when the slowness of the P phase is known, the slowness of the S phase is deduced, and the S-phase arrival is searched for using the shift-and-sum practice. What makes ViDA3 so attractive is that, in locations where a real-time network is already in place, these added values may be achieved without extra hardware or substantial budget requirements. We present the result of ViDA3 real-time operation on a shallow earthquake offshore Vancouver Island and the result of its replay on a deep slab earthquake in northern Chile. ViDA3 performance is further assessed using a dataset of seismograms from the Mendocino Triple Junction area. It is concluded that ViDA3 location scheme outperforms currently available EEW location algorithms for out-of-network earthquakes.