JLJiun-Ting Lin

Jiun-Ting Lin

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jiun-Ting Lin has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

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

    by Jiun-Ting Lin, Ana C. Aguiar, Qingkai Kong, Amanda C. Price, Stephen C. Myers

    Seismic data quality assessment (QA) is the first and one of the most important steps before conducting any further data analysis. Traditional methods involve checking various metrics, such as spike detection and power spectral density, by setting strict thresholds or comparing data against synthetic benchmarks. However, these approaches often rely on pre-existing knowledge and assumptions about data anomalies, leading to potential misclassification of unusual cases. Here, we propose a deep autoencoder model, an unsupervised learning approach that evaluates data quality without making assumptions about normal and anomalous data, which can be used to identify deviations in recorded data that may indicate nascent instrument failure. We test the model with the U.S. International Monitoring System (IMS) seismic stations and demonstrate the capability of detecting anomalies on a monthly scale. This could prompt station operators to examine potential problems early, allowing sufficient time for instrument maintenance to prevent data outages. In addition, we use a new manually selected testing dataset to compare our model performance against two supervised machine learning (ML) approaches and a standard QA package, as baseline models. When applied to the dataset containing known data anomalies, performance of the supervised and unsupervised ML approaches is similar, with an accuracy of 88.1% for our model compared to ∼90% for the supervised ML approach and 78.2% for the standard QA package. Our model outperforms the baseline models when applied to new stations, where new types of data anomalies can be station-specific and not included in the training dataset. Finally, we show model transferability by training the model with data from the Global Seismograph Network only and applying it to the IMS network data. The results suggest that our model is generalizable and can be applied to new stations with good accuracy.


  • Open Access

    An unexplained tsunami: Was there megathrust slip during the 2020 Mw7.6 Sand Point, Alaska, earthquake?

    by Sean Santellanes, Dara Goldberg, Pablo Koch, Diego Melgar, William Yeck, Brendan Crowell, Jiun-Ting Lin

    On October 19, 2020, the Mw7.6 Sand Point earthquake struck south of the Shumagin Islands in Alaska. Moment tensors indicate the earthquake was primarily strike-slip, yet the event produced an enigmatic tsunami that was larger and more widespread than expected for an earthquake of that magnitude and mechanism. Using a suite of hydrodynamic, seismic, and geodetic modeling techniques, we explore plausible causes of the tsunami. We find that strike-slip models consistent with the moment tensor orientation cannot produce the observed tsunami. Hydrodynamic inversion of sea surface deformation from deep ocean and tide gauge data suggest seafloor deformation more closely matches a megathrust, rather than a strike-slip, source. Static slip inversions, using sea level and Global Navigation Satellite System data, allow for a portion of co-seismic megathrust slip that can explain tsunamigenesis. Combining all available geophysical datasets to model the kinematic rupture, we show that considerable, relatively slow, megathrust slip is allowable in the Shumagin segment, concurrent with strike-slip faulting. We hypothesize that the slow megathrust rupture does not contribute much seismic radiation allowing it to previously go unnoticed with traditional seismic monitoring.


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

    by Jiun‐Ting Lin, Diego Melgar, Valerie J. Sahakian, Amanda M. Thomas, Jacob Searcy

    Earthquake early warning (EEW) systems aim to forecast the shaking intensity rapidly after an earthquake occurs and send warnings to affected areas before the onset of strong shaking. The system relies on rapid and accurate estimation of earthquake source parameters. However, it is known that source estimation for large ruptures in real‐time is challenging, and it often leads to magnitude underestimation. In a previous study, we showed that machine learning, HR‐GNSS, and realistic rupture synthetics can be used to reliably predict earthquake magnitude. This model, called Machine‐Learning Assessed Rapid Geodetic Earthquake model (M‐LARGE), can rapidly forecast large earthquake magnitudes with an accuracy of 99%. Here, we expand M‐LARGE to predict centroid location and fault size, enabling the construction of the fault rupture extent for forecasting shaking intensity using existing ground motion models. We test our model in the Chilean Subduction Zone with thousands of simulated and five real large earthquakes. The result achieves an average warning time of 40.5 s for shaking intensity MMI4+, surpassing the 34 s obtained by a similar GNSS EEW model. Our approach addresses a critical gap in existing EEW systems for large earthquakes by demonstrating real‐time fault tracking feasibility without saturation issues. This capability leads to timely and accurate ground motion forecasts and can support other methods, enhancing the overall effectiveness of EEW systems. Additionally, the ability to predict source parameters for real Chilean earthquakes implies that synthetic data, governed by our understanding of earthquake scaling, is consistent with the actual rupture processes.


  • Open Access

    Detection of Hidden Low-Frequency Earthquakes in Southern Vancouver Island with Deep Learning

    by Jiun-Ting Lin, Amanda Thomas, Loïc Bachelot, Douglas Toomey, Jake Searcy, Diego Melgar

    Low-frequency earthquakes (LFEs) are small-magnitude earthquakes that are depleted in high-frequency content relative to traditional earthquakes of the same magnitude. These events occur in conjunction with slow slip events (SSEs) and can be used to infer the space and time evolution of SSEs. However, because LFEs have weak signals, and the methods used to identify them are computationally expensive, LFEs are not routinely cataloged in most places. Here, we develop a deep-learning model that learns from the existing LFEs catalog to detect LFEs in 14 years of continuous waveform data in southern Vancouver Island. The result shows significant increases in detection rates at individual stations. We associate the detections and locate them using a grid search approach in a 3D regional velocity model, resulting in over 1 million LFEs during the performing period. Our resulting catalog is consistent with the tremor catalog during periods of large-magnitude SSEs. However, there are cases where it registers far more LFEs than the tremor catalog. We highlight a 16-day period in May 2010, our model detects nearly 3,000 LFEs, whereas the tremor catalog contains only one tremor in the same region. This suggests the possibility of hidden small-magnitude SSEs that are undetected by current approaches. Our approach improves the temporal and spatial resolution of the LFEs activities and provides new opportunities to understand deep subduction zone processes in this region.


  • Learning source, path and site effects: CNN-based on-site intensity prediction for earthquake early warning

    by Hongcai Zhang, Diego Melgar, Valerie Sahakian, Jake Searcy, Jiun-Ting Lin

    To provide timely and accurate seismic alerts for potential users during the earthquake early warning (EEW) process, several algorithms have been proposed and implemented. Some of the most common rely on the characterization of the earthquake magnitude and location, and then use a ground motion model to forecast shaking intensity at a user's location. It has been noted that with this approach the scatter in the forecasted intensities can be significant and may affect the reliability and usefulness of the warnings. To ameliorate this, we propose a single station machine learning (ML) algorithm. We build a four-layer convolutional neural network (CNN), named it CONIP (Convolutional neural network ONsite Intensity Prediction), and test it using two data sets to study the feasibility of seismic intensity forecasting from only the first few seconds of a waveform. With only limited waveforms, mainly P waves, our CONIP model will forecast the on-site seismic intensity. We find that compared with existing methods, the forecasted seismic intensities are much more accurate. To understand the nature of this improvement we carry out a residual decomposition and quantify to what degree the ML model learns site, regional path, and source information during the training. We find that source and site effects are easily learned by the algorithm. Path effects, on the other hand, can be learned but will depend largely on the number, location, and coverage of stations. Overall, the ML model performance is a substantial improvement over traditional approaches. Our results are currently only applicable for small and moderate intensities but, we argue, could in future work be supplemented by simulations to supplement the training data sets at higher intensities. We believe that ML algorithms will play a dominant role in the next generation of EEW systems.


  • Open Access

    Early warning for great earthquakes from characterization of crustal deformation patterns with deep learning

    by Jiun-Ting Lin, Diego Melgar, Amanda Thomas, Jake Searcy

    Although infrequent, large (Mw7.5+) earthquakes can be extremely damaging and occur on subduction and intraplate faults worldwide. Earthquake early warning (EEW) systems aim to provide advanced warning before strong shaking and tsunami onsets. These systems estimate earthquake magnitude using the early metrics of waveforms, relying on empirical scaling relationships of abundant past events. However, both the rarity and complexity of great events make it challenging to characterize them, and EEW algorithms often underpredict magnitude and the resulting hazards. Here we propose a model, M-LARGE, that leverages the power of deep learning to characterize crustal deformation patterns of large earthquakes in real time. We demonstrate the algorithm in the Chilean Subduction Zone by training it with more than six million different simulated rupture scenarios recorded on the Chilean GNSS network. M-LARGE successfully performs reliable magnitude estimation on the testing dataset with an accuracy of 99%. Furthermore, the model successfully predicts the magnitude of five real Chilean earthquakes that occurred in the last 11 years. These events were damaging, large enough to be recorded by the modern HR-GNSS instrument in the last decade, and provide valuable ground truth. M-LARGE tracks the evolution of the source process and can make faster and more accurate magnitude estimation, significantly outperforming other similar EEW algorithms.

  • Open Access

    Potential megathrust co-seismic slip during the 2020 Sand Point, Alaska strike-slip earthquake

    by Sean R Santellanes, Diego Melgar, Brendan W Crowell, Jiun-Ting Lin

    On October 2020, a Mw 7.6 earthquake struck to the south of the Shumagin Islands in Alaska, nearly 3 months after the Mw 7.8 Simeonof megathrust event. The initial models of the earthquake indicated a largely strike-slip rupture; however, the observed tsunami was much larger and widespread than expected for the focal mechanism. We investigate what sea surface deformation is necessary to recreate the tsunami waveforms using water-level inversion techniques. We find that the sea surface deformation does not resemble that expected from a purely strike-slip earthquake. We then carry out slip inversions with water level and static GNSS data as input. We explore the likelihood of megathrust co-seismic slip aiding tsunamigenesis. We propose that, concurrently with strike-slip faulting, it is likely that a considerable slip occurred on the megathrust westward and updip from the previous July 2020 event. We also propose that a smaller submarine landslide is likely to have occurred in an area prone to them. The Sand Point earthquake potentially released ~2 meters of accumulated slip in the western Shumagin Gap, but likely did not slip updip of ~15 km depth.


  • Open Access

    Rayleigh‐Love Discrepancy Highlights Temporal Changes in Near‐Surface Radial Anisotropy After the 2004 Great Sumatra Earthquake

    by W. Yu, T.‐R. A. Song, J. Su, J.‐T. Lin

    Strong ground motions from large earthquakes are capable of damaging near‐surface sediments and promoting notable reductions in their seismic velocity structures. These velocity reductions can be monitored using either body waves or surface waves from repeatable seismic sources, such as repeating earthquakes (REs) or ambient seismic noise. Here, we compile a decade‐long catalog of REs since the 2004 Mw 9.2 Sumatra Earthquake, and monitor the temporal velocity changes from Rayleigh waves (δVLR) and Love waves (δVLQ). We observe a δVLR of −0.16% and δVLR/δVLQ ratio of ∼6, inconsistent with velocity reductions in isotropic media. To reconcile the observations, we carry out analyses of sensitivity kernels of surface waves in isotropic and vertical transversely isotropic (VTI) media and forward waveform modeling. The modeling reveals that the observed large δVLR/δVLQ ratio can be explained by strong dβV (−4%) and weak dβH (−0.615%) reductions and an increase in radial anisotropy in the near surface. These changes are best explained by a 2% increase in crack density of aligned horizontal cracks in overpressured sediments near the compressive subduction zone forearc. Temporal variations of δVLR/δVLQ ratios and radial anisotropy after consecutive great earthquakes are consistent with laboratory experiments under cyclic loading and unloading.


  • Open Access

    Early Warning for Great Earthquakes From Characterization of Crustal Deformation Patterns With Deep Learning

    by J.‐T. Lin, D. Melgar, A. M. Thomas, J. Searcy

    Although infrequent, large (Mw7.5+) earthquakes can be extremely damaging and occur on subduction and intraplate faults worldwide. Earthquake early warning (EEW) systems aim to provide advanced warning before strong shaking and tsunami onsets. These systems estimate earthquake magnitude using the early metrics of waveforms, relying on empirical scaling relationships of abundant past events. However, both the rarity and complexity of great events make it challenging to characterize them, and EEW algorithms often underpredict magnitude and the resulting hazards. Here, we propose a model, M‐LARGE, that leverages deep learning to characterize crustal deformation patterns of large earthquakes for a specific region in real‐time. We demonstrate the algorithm in the Chilean Subduction Zone by training it with more than six million different simulated rupture scenarios recorded on the Chilean GNSS network. M‐LARGE performs reliable magnitude estimation on the testing data set with an accuracy of 99%. Furthermore, the model successfully predicts the magnitude of five real Chilean earthquakes that occurred in the last 11 years. These events were damaging, large enough to be recorded by the modern high rate global navigation satellite system instrument, and provide valuable ground truth. M‐LARGE tracks the evolution of the source process and can make faster and more accurate magnitude estimation, significantly outperforming other similar EEW algorithms. This is the first demonstration of our approach. Future work toward generalization is outstanding and will include the addition of more training and testing data, interfacing with existing EEW methods, and applying the method to different tectonic settings to explore performance in these regions.


  • Open Access

    Potential megathrust co-seismic slip during the 2020 Sand Point, Alaska strike-slip earthquake

    by Sean R Santellanes, Diego Melgar, Brendan W Crowell, Jiun-Ting Lin

    In October 2020, a Mw 7.6 earthquake struck to the south of the Shumagin Islands in Alaska, nearly 3 months after the Mw 7.8 Simeonof megathrust event. The initial models of the earthquake indicated a largely strike-slip rupture; however, the observed tsunami was much larger and widespread than expected for the focal mechanism. We investigate what sea surface deformation is necessary to recreate the tsunami waveforms using water-level inversion techniques. We find that the sea surface deformation does not resemble that expected from a purely strike-slip earthquake. Instead we propose that it is likely that considerable slip occurred on the megathrust, westward and updip from the previous July event. The Sand Point earthquake potentially released ~2 meters of accumulated slip in the western Shumagin Gap, but likely did not slip updip of ~15 km depth, which still leaves a significant hazard for a shallow tsunamigenic earthquake in the future.